ADDRESSING DRIVABLE ARTIFACTS FOR MOTION PLANNING
CROSS-REFERENCE TO RELATED APPLICATION
[1] This application claims the benefit of the filing date of U.S. Provisional Application No. 63/590,094, filed October 13, 2023, the entirety of which is incorporated herein by reference.
BACKGROUND
[2] Autonomous or semi-autonomous vehicles navigate through environments based on sensor and other data. The navigation can include operations to avoid obstacles in the environment.
BRIEF DESCRIPTION OF THE FIGURES
[3] FIG. 1 is an example environment in which a vehicle including one or more components of an autonomous system can be implemented;
[4] FIG. 2 is a diagram of one or more systems of a vehicle including an autonomous system;
[5] FIG. 3 is a diagram of components of one or more devices and/or one or more systems of FIGS. 1 and 2;
[6] FIG. 4 is a diagram of certain components of an autonomous system;
[7] FIG. 5 is a flowchart of a process for trajectory adjustment;
[8] FIG. 6 is a diagram of an implementation of a process for trajectory adjustment;
[9] FIG. 7 is a diagram of an environment having a drivable artifact;
[10] FIG. 8 is a flowchart of a process for velocity adjustment;
[11] FIG. 9 is a diagram of an implementation of a process for velocity adjustment;
[12] FIG. 10 is a diagram of an environment having a drivable artifact;
[13] FIG. 11 is a flowchart of a process for trajectory selection;
[14] FIG. 12 is a diagram of an implementation of a process for trajectory selection;
[15] FIG. 13 is a diagram of an environment having a drivable artifact; and [16] FIG. 14 is a flowchart of a process for addressing drivable artifacts for motion planning.
DETAILED DESCRIPTION
[17] In the following description numerous specific details are set forth in order to provide a thorough understanding of the present disclosure for the purposes of explanation. It will be apparent, however, that the embodiments described by the present disclosure can be practiced without these specific details. In some instances, well-known structures and devices are illustrated in block diagram form in order to avoid unnecessarily obscuring aspects of the present disclosure.
[18] Specific arrangements or orderings of schematic elements, such as those representing systems, devices, modules, instruction blocks, data elements, and/or the like are illustrated in the drawings for ease of description. However, it will be understood by those skilled in the art that the specific ordering or arrangement of the schematic elements in the drawings is not meant to imply that a particular order or sequence of processing, or separation of processes, is required unless explicitly described as such. Further, the inclusion of a schematic element in a drawing is not meant to imply that such element is required in all embodiments or that the features represented by such element may not be included in or combined with other elements in some embodiments unless explicitly described as such.
[19] Further, where connecting elements such as solid or dashed lines or arrows are used in the drawings to illustrate a connection, relationship, or association between or among two or more other schematic elements, the absence of any such connecting elements is not meant to imply that no connection, relationship, or association can exist. In other words, some connections, relationships, or associations between elements are not illustrated in the drawings so as not to obscure the disclosure. In addition, for ease of illustration, a single connecting element can be used to represent multiple connections, relationships or associations between elements. For example, where a connecting element represents communication of signals, data, or instructions (e.g., “software instructions”), it should be understood by those skilled in the art that such element can represent one or multiple signal paths (e.g., a bus), as may be needed, to affect the communication.
[20] Although the terms first, second, third, and/or the like are used to describe various elements, these elements should not be limited by these terms. The terms first, second, third, and/or the like are used only to distinguish one element from another. For example, a first contact could be termed a second contact and, similarly, a second contact could be termed a first contact without departing from the scope of the described embodiments. The first contact and the second contact are both contacts, but they are not the same contact.
[21] The terminology used in the description of the various described embodiments herein is included for the purpose of describing particular embodiments only and is not intended to be limiting. As used in the description of the various described embodiments and the appended claims, the singular forms “a,” “an” and “the” are intended to include the plural forms as well and can be used interchangeably with “one or more” or “at least one,” unless the context clearly indicates otherwise. It will also be understood that the term “and/or” as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items. It will be further understood that the terms “includes,” “including,” “comprises,” and/or “comprising,” when used in this description specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
[22] As used herein, the terms “communication” and “communicate” refer to at least one of the reception, receipt, transmission, transfer, provision, and/or the like of information (or information represented by, for example, data, signals, messages, instructions, commands, and/or the like). For one unit (e.g., a device, a system, a component of a device or system, combinations thereof, and/or the like) to be in communication with another unit means that the one unit is able to directly or indirectly receive information from and/or send (e.g., transmit) information to the other unit. This may refer to a direct or indirect connection that is wired and/or wireless in nature. Additionally, two units may be in communication with each other even though the information transmitted may be modified, processed, relayed, and/or routed between the first and second unit. For example, a first unit may be in communication with a second unit even though the first unit passively receives information and does not actively transmit information to the second unit. As another example, a first unit may be in communication with a second unit if at least one intermediary unit (e.g., a third unit located between the first unit and the second unit) processes information received from the first unit and transmits the processed information to the second unit. In some embodiments, a message may refer to a network packet (e.g., a data packet and/or the like) that includes data.
[23] As used herein, the term “if” is, optionally, construed to mean “when”, “upon”, “in response to determining,” “in response to detecting,” and/or the like, depending on the context. Similarly, the phrase “if it is determined” or “if [a stated condition or event] is detected” is, optionally, construed to mean “upon determining,” “in response to determining,” “upon detecting [the stated condition or event],” “in response to detecting [the stated condition or event],” and/or the like, depending on the context. Also, as used herein, the terms “has”, “have”, “having”, or the like are intended to be open-ended terms. Further, the phrase “based on” is intended to mean “based at least partially on” unless explicitly stated otherwise.
[24] Reference will now be made in detail to embodiments, examples of which are illustrated in the accompanying drawings. In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the various described embodiments. However, it will be apparent to one of ordinary skill in the art that the various described embodiments can be practiced without these specific details. In other instances, well-known methods, procedures, components, circuits, and networks have not been described in detail so as not to unnecessarily obscure aspects of the embodiments.
[25] General Overview
[26] In some aspects and/or embodiments, systems, methods, and computer program products described herein include and/or implement vehicle movement adaptive to drivable artifacts. Drivable artifacts are roadway features over which vehicles can travel at the cost of passenger experience. Based on detection of drivable artifacts, parameters of vehicle movement, such as trajectory and/or speed, can be adjusted. In some cases, drivable artifact detection is integrated into trajectory selection, e.g., based on consideration of multiple candidate trajectories.
[27] By virtue of the implementation of systems, methods, and computer program products described herein, techniques for addressing drivable artifacts for motion planning can provide faster, more computationally efficient motion planning for a vehicle and improved experience of passengers in the vehicle. For example, in some embodiments, a differentiation between drivable artifacts and obstacles facilitates faster and more efficient motion planning, e.g., because more computationally-intensive methods can be avoided in favor of smaller adaptations, e.g., based on post-processing a computed trajectory. In addition, in some embodiments, addressing drivable artifacts as different from obstacles facilitates autonomous decision-making by a vehicle to proceed with traversal of artifacts, where avoiding the artifacts might require lengthy or dangerous re-routing. Moreover, user/passenger experience can be improved, e.g., by reducing route traversal time, enhancing passenger comfort, and reducing degradation of vehicle components.
[28] Referring now to FIG. 1 , illustrated is example environment 100 in which vehicles that include autonomous systems, as well as vehicles that do not, are operated. As illustrated, environment 100 includes vehicles 102a-102n, objects 104a-104n, routes 106a-106n, area 108, vehicle-to-infrastructure (V2I) device 110, network 112, remote autonomous vehicle (AV) system 114, fleet management system 116, and V2I system 118. Vehicles 102a-102n, vehicle-to-infrastructure (V2I) device 110, network 112, autonomous vehicle (AV) system 114, fleet management system 116, and V2I system 118 interconnect (e.g., establish a connection to communicate and/or the like) via wired connections, wireless connections, or a combination of wired or wireless connections. In some embodiments, objects 104a-104n interconnect with at least one of vehicles 102a- 102n, vehicle-to-infrastructure (V2I) device 110, network 112, autonomous vehicle (AV) system 114, fleet management system 116, and V2I system 118 via wired connections, wireless connections, or a combination of wired or wireless connections.
[29] Vehicles 102a-102n (referred to individually as vehicle 102 and collectively as vehicles 102) include at least one device configured to transport goods and/or people. In some embodiments, vehicles 102 are configured to be in communication with V2I device 110, remote AV system 114, fleet management system 116, and/or V2I system 118 via network 112. In some embodiments, vehicles 102 include cars, buses, trucks, trains, and/or the like. In some embodiments, vehicles 102 are the same as, or similar to, vehicles 200, described herein (see FIG. 2). In some embodiments, a vehicle 200 of a set of vehicles 200 is associated with an autonomous fleet manager. In some embodiments, vehicles 102 travel along respective routes 106a-106n (referred to individually as route 106 and collectively as routes 106), as described herein. In some embodiments, one or more vehicles 102 include an autonomous system (e.g., an autonomous system that is the same as or similar to autonomous system 202).
[30] Objects 104a-104n (referred to individually as object 104 and collectively as objects 104) include, for example, at least one vehicle, at least one pedestrian, at least one cyclist, at least one structure (e.g., a building, a sign, a fire hydrant, etc.), and/or the like. Each object 104 is stationary (e.g., located at a fixed location for a period of time) or mobile (e.g., having a velocity and associated with at least one trajectory). In some embodiments, objects 104 are associated with corresponding locations in area 108.
[31] Routes 106a-106n (referred to individually as route 106 and collectively as routes 106) are each associated with (e.g., prescribe) a sequence of actions (also known as a trajectory) connecting states along which an AV can navigate. Each route 106 starts at an initial state (e.g., a state that corresponds to a first spatiotemporal location, velocity, and/or the like) and ends at a final goal state (e.g., a state that corresponds to a second spatiotemporal location that is different from the first spatiotemporal location) or goal region (e.g. a subspace of acceptable states (e.g., terminal states)). In some embodiments, the first state includes a location at which an individual or individuals are to be picked-up by the AV and the second state or region includes a location or locations at which the individual or individuals picked-up by the AV are to be dropped-off. In some embodiments, routes 106 include a plurality of acceptable state sequences (e.g., a plurality of spatiotemporal location sequences), the plurality of state sequences associated with (e.g., defining) a plurality of trajectories. In an example, routes 106 include only high level actions or imprecise state locations, such as a series of connected roads dictating turning directions at roadway intersections. Additionally, or alternatively, routes 106 may include more precise actions or states such as, for example, specific target lanes or precise locations within the lane areas and targeted speed at those positions. In an example, routes 106 include a plurality of precise state sequences along the at least one high level action sequence with a limited lookahead horizon to reach intermediate goals, where the combination of successive iterations of limited horizon state sequences cumulatively correspond to a plurality of trajectories that collectively form the high level route to terminate at the final goal state or region.
[32] Area 108 includes a physical area (e.g. , a geographic region) within which vehicles 102 can navigate. In an example, area 108 includes at least one state (e.g., a country, a province, an individual state of a plurality of states included in a country, etc.), at least one portion of a state, at least one city, at least one portion of a city, etc. In some embodiments, area 108 includes at least one named thoroughfare (referred to herein as a “road”) such as a highway, an interstate highway, a parkway, a city street, etc. Additionally, or alternatively, in some examples area 108 includes at least one unnamed road such as a driveway, a section of a parking lot, a section of a vacant and/or undeveloped lot, a dirt path, etc. In some embodiments, a road includes at least one lane (e.g., a portion of the road that can be traversed by vehicles 102). In an example, a road includes at least one lane associated with (e.g., identified based on) at least one lane marking.
[33] Vehicle-to-lnfrastructure (V2I) device 110 (sometimes referred to as a Vehicle-to- Infrastructure or Vehicle-to-Everything (V2X) device) includes at least one device configured to be in communication with vehicles 102 and/or V2I infrastructure system 118. In some embodiments, V2I device 110 is configured to be in communication with vehicles 102, remote AV system 114, fleet management system 116, and/or V2I system 118 via network 112. In some embodiments, V2I device 110 includes a radio frequency identification (RFID) device, signage, cameras (e.g., two-dimensional (2D) and/or three- dimensional (3D) cameras), lane markers, streetlights, parking meters, etc. In some embodiments, V2I device 110 is configured to communicate directly with vehicles 102. Additionally, or alternatively, in some embodiments V2I device 110 is configured to communicate with vehicles 102, remote AV system 114, and/or fleet management system 116 via V2I system 118. In some embodiments, V2I device 110 is configured to communicate with V2I system 118 via network 112. [34] Network 112 includes one or more wired and/or wireless networks. In an example, network 112 includes a cellular network (e.g., a long term evolution (LTE) network, a third generation (3G) network, a fourth generation (4G) network, a fifth generation (5G) network, a code division multiple access (CDMA) network, etc.), a public land mobile network (PLMN), a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), a telephone network (e.g., the public switched telephone network (PSTN), a private network, an ad hoc network, an intranet, the Internet, a fiber opticbased network, a cloud computing network, etc., a combination of some or all of these networks, and/or the like.
[35] Remote AV system 114 includes at least one device configured to be in communication with vehicles 102, V2I device 110, network 112, fleet management system 116, and/or V2I system 118 via network 112. In an example, remote AV system 114 includes a server, a group of servers, and/or other like devices. In some embodiments, remote AV system 114 is co-located with the fleet management system 116. In some embodiments, remote AV system 114 is involved in the installation of some or all of the components of a vehicle, including an autonomous system, an autonomous vehicle compute, software implemented by an autonomous vehicle compute, and/or the like. In some embodiments, remote AV system 114 maintains (e.g., updates and/or replaces) such components and/or software during the lifetime of the vehicle.
[36] Fleet management system 116 includes at least one device configured to be in communication with vehicles 102, V2I device 110, remote AV system 114, and/or V21 infrastructure system 118. In an example, fleet management system 116 includes a server, a group of servers, and/or other like devices. In some embodiments, fleet management system 116 is associated with a ridesharing company (e.g., an organization that controls operation of multiple vehicles (e.g., vehicles that include autonomous systems and/or vehicles that do not include autonomous systems) and/or the like).
[37] In some embodiments, V2I system 118 includes at least one device configured to be in communication with vehicles 102, V2I device 110, remote AV system 114, and/or fleet management system 116 via network 112. In some examples, V2I system 118 is configured to be in communication with V2I device 110 via a connection different from network 112. In some embodiments, V2I system 118 includes a server, a group of servers, and/or other like devices. In some embodiments, V2I system 118 is associated with a municipality or a private institution (e.g., a private institution that maintains V2I device 110 and/or the like).
[38] The number and arrangement of elements illustrated in FIG. 1 are provided as an example. There can be additional elements, fewer elements, different elements, and/or differently arranged elements, than those illustrated in FIG. 1. Additionally, or alternatively, at least one element of environment 100 can perform one or more functions described as being performed by at least one different element of FIG. 1. Additionally, or alternatively, at least one set of elements of environment 100 can perform one or more functions described as being performed by at least one different set of elements of environment 100.
[39] Referring now to FIG. 2, vehicle 200 (which may be the same as, or similar to vehicle 102 of FIG. 1 ) includes or is associated with autonomous system 202, powertrain control system 204, steering control system 206, and brake system 208. In some embodiments, vehicle 200 is the same as or similar to vehicle 102 (see FIG. 1 ). In some embodiments, autonomous system 202 is configured to confer vehicle 200 autonomous driving capability (e.g., implement at least one driving automation or maneuver-based function, feature, device, and/or the like that enable vehicle 200 to be partially or fully operated without human intervention including, without limitation, fully autonomous vehicles (e.g., vehicles that forego reliance on human intervention such as Level 5 ADS- operated vehicles), highly autonomous vehicles (e.g., vehicles that forego reliance on human intervention in certain situations such as Level 4 ADS-operated vehicles), conditional autonomous vehicles (e.g., vehicles that forego reliance on human intervention in limited situations such as Level 3 ADS-operated vehicles) and/or the like. In one embodiment, autonomous system 202 includes operational or tactical functionality required to operate vehicle 200 in on-road traffic and perform part or all of Dynamic Driving Task (DDT) on a sustained basis. In another embodiment, autonomous system 202 includes an Advanced Driver Assistance System (ADAS) that includes driver support features. Autonomous system 202 supports various levels of driving automation, ranging from no driving automation (e.g., Level 0) to full driving automation (e.g., Level 5). For a detailed description of fully autonomous vehicles and highly autonomous vehicles, reference may be made to SAE International's standard J3016: Taxonomy and Definitions for Terms Related to On-Road Motor Vehicle Automated Driving Systems, which is incorporated by reference in its entirety. In some embodiments, vehicle 200 is associated with an autonomous fleet manager and/or a ridesharing company.
[40] Autonomous system 202 includes a sensor suite that includes one or more devices such as cameras 202a, LiDAR sensors 202b, radar sensors 202c, and microphones 202d. In some embodiments, autonomous system 202 can include more or fewer devices and/or different devices (e.g., ultrasonic sensors, inertial sensors, GPS receivers (discussed below), odometry sensors that generate data associated with an indication of a distance that vehicle 200 has traveled, and/or the like). In some embodiments, autonomous system 202 uses the one or more devices included in autonomous system 202 to generate data associated with environment 100, described herein. The data generated by the one or more devices of autonomous system 202 can be used by one or more systems described herein to observe the environment (e.g., environment 100) in which vehicle 200 is located. In some embodiments, autonomous system 202 includes communication device 202e, autonomous vehicle compute 202f, drive-by-wire (DBW) system 202h, and safety controller 202g.
[41] Cameras 202a include at least one device configured to be in communication with communication device 202e, autonomous vehicle compute 202f, and/or safety controller 202g via a bus (e.g., a bus that is the same as or similar to bus 302 of FIG. 3). Cameras 202a include at least one camera (e.g., a digital camera using a light sensor such as a Charge-Coupled Device (CCD), a thermal camera, an infrared (IR) camera, an event camera, and/or the like) to capture images including physical objects (e.g., cars, buses, curbs, people, and/or the like). In some embodiments, camera 202a generates camera data as output. In some examples, camera 202a generates camera data that includes image data associated with an image. In this example, the image data may specify at least one parameter (e.g., image characteristics such as exposure, brightness, etc., an image timestamp, and/or the like) corresponding to the image. In such an example, the image may be in a format (e.g., RAW, JPEG, PNG, and/or the like). In some embodiments, camera 202a includes a plurality of independent cameras configured on (e.g., positioned on) a vehicle to capture images for the purpose of stereopsis (stereo vision). In some examples, camera 202a includes a plurality of cameras that generate image data and transmit the image data to autonomous vehicle compute 202f and/or a fleet management system (e.g., a fleet management system that is the same as or similar to fleet management system 116 of FIG. 1 ). In such an example, autonomous vehicle compute 202f determines depth to one or more objects in a field of view of at least two cameras of the plurality of cameras based on the image data from the at least two cameras. In some embodiments, cameras 202a is configured to capture images of objects within a distance from cameras 202a (e.g., up to 100 meters, up to a kilometer, and/or the like). Accordingly, cameras 202a include features such as sensors and lenses that are optimized for perceiving objects that are at one or more distances from cameras 202a.
[42] In an embodiment, camera 202a includes at least one camera configured to capture one or more images associated with one or more traffic lights, street signs and/or other physical objects that provide visual navigation information. In some embodiments, camera 202a generates traffic light data associated with one or more images. In some examples, camera 202a generates TLD (Traffic Light Detection) data associated with one or more images that include a format (e.g., RAW, JPEG, PNG, and/or the like). In some embodiments, camera 202a that generates TLD data differs from other systems described herein incorporating cameras in that camera 202a can include one or more cameras with a wide field of view (e.g., a wide-angle lens, a fish-eye lens, a lens having a viewing angle of approximately 120 degrees or more, and/or the like) to generate images about as many physical objects as possible.
[43] Light Detection and Ranging (LiDAR) sensors 202b include at least one device configured to be in communication with communication device 202e, autonomous vehicle compute 202f, and/or safety controller 202g via a bus (e.g., a bus that is the same as or similar to bus 302 of FIG. 3). LiDAR sensors 202b include a system configured to transmit light from a light emitter (e.g., a laser transmitter). Light emitted by LiDAR sensors 202b include light (e.g., infrared light and/or the like) that is outside of the visible spectrum. In some embodiments, during operation, light emitted by LiDAR sensors 202b encounters a physical object (e.g., a vehicle) and is reflected back to LiDAR sensors 202b. In some embodiments, the light emitted by LiDAR sensors 202b does not penetrate the physical objects that the light encounters. LiDAR sensors 202b also include at least one light detector which detects the light that was emitted from the light emitter after the light encounters a physical object. In some embodiments, at least one data processing system associated with LiDAR sensors 202b generates an image (e.g., a point cloud, a combined point cloud, and/or the like) representing the objects included in a field of view of LiDAR sensors 202b. In some examples, the at least one data processing system associated with LiDAR sensor 202b generates an image that represents the boundaries of a physical object, the surfaces (e.g., the topology of the surfaces) of the physical object, and/or the like. In such an example, the image is used to determine the boundaries of physical objects in the field of view of LiDAR sensors 202b.
[44] Radio Detection and Ranging (radar) sensors 202c include at least one device configured to be in communication with communication device 202e, autonomous vehicle compute 202f, and/or safety controller 202g via a bus (e.g., a bus that is the same as or similar to bus 302 of FIG. 3). Radar sensors 202c include a system configured to transmit radio waves (either pulsed or continuously). The radio waves transmitted by radar sensors 202c include radio waves that are within a predetermined spectrum. In some embodiments, during operation, radio waves transmitted by radar sensors 202c encounter a physical object and are reflected back to radar sensors 202c. In some embodiments, the radio waves transmitted by radar sensors 202c are not reflected by some objects. In some embodiments, at least one data processing system associated with radar sensors 202c generates signals representing the objects included in a field of view of radar sensors 202c. For example, the at least one data processing system associated with radar sensor 202c generates an image that represents the boundaries of a physical object, the surfaces (e.g., the topology of the surfaces) of the physical object, and/or the like. In some examples, the image is used to determine the boundaries of physical objects in the field of view of radar sensors 202c.
[45] Microphones 202d includes at least one device configured to be in communication with communication device 202e, autonomous vehicle compute 202f, and/or safety controller 202g via a bus (e.g., a bus that is the same as or similar to bus 302 of FIG. 3). Microphones 202d include one or more microphones (e.g., array microphones, external microphones, and/or the like) that capture audio signals and generate data associated with (e.g., representing) the audio signals. In some examples, microphones 202d include transducer devices and/or like devices. In some embodiments, one or more systems described herein can receive the data generated by microphones 202d and determine a position of an object relative to vehicle 200 (e.g., a distance and/or the like) based on the audio signals associated with the data.
[46] Communication device 202e includes at least one device configured to be in communication with cameras 202a, LiDAR sensors 202b, radar sensors 202c, microphones 202d, autonomous vehicle compute 202f, safety controller 202g, and/or DBW (Drive-By-Wire) system 202h. For example, communication device 202e may include a device that is the same as or similar to communication interface 314 of FIG. 3. In some embodiments, communication device 202e includes a vehicle-to-vehicle (V2V) communication device (e.g., a device that enables wireless communication of data between vehicles).
[47] Autonomous vehicle compute 202f include at least one device configured to be in communication with cameras 202a, LiDAR sensors 202b, radar sensors 202c, microphones 202d, communication device 202e, safety controller 202g, and/or DBW system 202h. In some examples, autonomous vehicle compute 202f includes a device such as a client device, a mobile device (e.g., a cellular telephone, a tablet, and/or the like), a server (e.g., a computing device including one or more central processing units, graphical processing units, and/or the like), and/or the like. In some embodiments, autonomous vehicle compute 202f is the same as or similar to autonomous vehicle compute 400, described herein. Additionally, or alternatively, in some embodiments autonomous vehicle compute 202f is configured to be in communication with an autonomous vehicle system (e.g., an autonomous vehicle system that is the same as or similar to remote AV system 114 of FIG. 1 ), a fleet management system (e.g., a fleet management system that is the same as or similar to fleet management system 116 of FIG. 1 ), a V2I device (e.g., a V2I device that is the same as or similar to V2I device 110 of FIG. 1 ), and/or a V2I system (e.g., a V2I system that is the same as or similar to V2I system 118 of FIG. 1 ).
[48] Safety controller 202g includes at least one device configured to be in communication with cameras 202a, LiDAR sensors 202b, radar sensors 202c, microphones 202d, communication device 202e, autonomous vehicle computer 202f, and/or DBW system 202h. In some examples, safety controller 202g includes one or more controllers (electrical controllers, electromechanical controllers, and/or the like) that are configured to generate and/or transmit control signals to operate one or more devices of vehicle 200 (e.g., powertrain control system 204, steering control system 206, brake system 208, and/or the like). In some embodiments, safety controller 202g is configured to generate control signals that take precedence over (e.g., overrides) control signals generated and/or transmitted by autonomous vehicle compute 202f.
[49] DBW system 202h includes at least one device configured to be in communication with communication device 202e and/or autonomous vehicle compute 202f. In some examples, DBW system 202h includes one or more controllers (e.g., electrical controllers, electromechanical controllers, and/or the like) that are configured to generate and/or transmit control signals to operate one or more devices of vehicle 200 (e.g., powertrain control system 204, steering control system 206, brake system 208, and/or the like). Additionally, or alternatively, the one or more controllers of DBW system 202h are configured to generate and/or transmit control signals to operate at least one different device (e.g., a turn signal, headlights, door locks, windshield wipers, and/or the like) of vehicle 200.
[50] Powertrain control system 204 includes at least one device configured to be in communication with DBW system 202h. In some examples, powertrain control system 204 includes at least one controller, actuator, and/or the like. In some embodiments, powertrain control system 204 receives control signals from DBW system 202h and powertrain control system 204 causes vehicle 200 to make longitudinal vehicle motion, such as start moving forward, stop moving forward, start moving backward, stop moving backward, accelerate in a direction, decelerate in a direction or to make lateral vehicle motion such as performing a left turn, performing a right turn, and/or the like. In an example, powertrain control system 204 causes the energy (e.g., fuel, electricity, and/or the like) provided to a motor of the vehicle to increase, remain the same, or decrease, thereby causing at least one wheel of vehicle 200 to rotate or not rotate.
[51] Steering control system 206 includes at least one device configured to rotate one or more wheels of vehicle 200. In some examples, steering control system 206 includes at least one controller, actuator, and/or the like. In some embodiments, steering control system 206 causes the front two wheels and/or the rear two wheels of vehicle 200 to rotate to the left or right to cause vehicle 200 to turn to the left or right. In other words, steering control system 206 causes activities necessary for the regulation of the y-axis component of vehicle motion.
[52] Brake system 208 includes at least one device configured to actuate one or more brakes to cause vehicle 200 to reduce speed and/or remain stationary. In some examples, brake system 208 includes at least one controller and/or actuator that is configured to cause one or more calipers associated with one or more wheels of vehicle 200 to close on a corresponding rotor of vehicle 200. Additionally, or alternatively, in some examples brake system 208 includes an automatic emergency braking (AEB) system, a regenerative braking system, and/or the like.
[53] In some embodiments, vehicle 200 includes at least one platform sensor (not explicitly illustrated) that measures or infers properties of a state or a condition of vehicle 200. In some examples, vehicle 200 includes platform sensors such as a global positioning system (GPS) receiver, an inertial measurement unit (IMU), a wheel speed sensor, a wheel brake pressure sensor, a wheel torque sensor, an engine torque sensor, a steering angle sensor, and/or the like. Although brake system 208 is illustrated to be located in the near side of vehicle 200 in FIG. 2, brake system 208 may be located anywhere in vehicle 200.
[54] Referring now to FIG. 3, illustrated is a schematic diagram of a device 300. As illustrated, device 300 includes processor 304, memory 306, storage component 308, input interface 310, output interface 312, communication interface 314, and bus 302. In some embodiments, device 300 corresponds to at least one device of vehicles 102 (e.g., at least one device of a system of vehicles 102), at least one device of remote AV system 114, at least one device of fleet management system 116, at least one device of vehicle- to-infrastructure system 118, at least one device of vehicle-to-infrastructure device 110, at least one device of autonomous vehicle compute 400, at least one device of autonomous vehicle compute 202f, and/or one or more devices of network 112 (e.g., one or more devices of a system of network 112). In some embodiments, one or more devices of vehicles 102 (e.g., one or more devices of a system of vehicles 102), one or more devices of remote AV system 114, one or more devices of fleet management system 116, one or more devices of vehicle-to-infrastructure system 118, one or more devices of vehicle-to-infrastructure device 110, one or more devices of autonomous vehicle compute 400, one or more devices of autonomous vehicle compute 202f, and/or one or more devices of network 112 (e.g., one or more devices of a system of network 112) include at least one device 300 and/or at least one component of device 300. As shown in FIG. 3, device 300 includes bus 302, processor 304, memory 306, storage component 308, input interface 310, output interface 312, and communication interface 314.
[55] Bus 302 includes a component that permits communication among the components of device 300. In some cases, processor 304 includes a processor (e.g., a central processing unit (CPU), a graphics processing unit (GPU), an accelerated processing unit (APU), and/or the like), a microphone, a digital signal processor (DSP), and/or any processing component (e.g., a field-programmable gate array (FPGA), an application specific integrated circuit (ASIC), and/or the like) that can be programmed to perform at least one function. Memory 306 includes random access memory (RAM), readonly memory (ROM), and/or another type of dynamic and/or static storage device (e.g., flash memory, magnetic memory, optical memory, and/or the like) that stores data and/or instructions for use by processor 304.
[56] Storage component 308 stores data and/or software related to the operation and use of device 300. In some examples, storage component 308 includes a hard disk (e.g., a magnetic disk, an optical disk, a magneto-optic disk, a solid state disk, and/or the like), a compact disc (CD), a digital versatile disc (DVD), a floppy disk, a cartridge, a magnetic tape, a CD-ROM, RAM, PROM, EPROM, FLASH-EPROM, NV-RAM, and/or another type of computer readable medium, along with a corresponding drive.
[57] Input interface 310 includes a component that permits device 300 to receive information, such as via user input (e.g., a touchscreen display, a keyboard, a keypad, a mouse, a button, a switch, a microphone, a camera, and/or the like). Additionally or alternatively, in some embodiments input interface 310 includes a sensor that senses information (e.g., a global positioning system (GPS) receiver, an accelerometer, a gyroscope, an actuator, and/or the like). Output interface 312 includes a component that provides output information from device 300 (e.g., a display, a speaker, one or more lightemitting diodes (LEDs), and/or the like).
[58] In some embodiments, communication interface 314 includes a transceiver-like component (e.g., a transceiver, a separate receiver and transmitter, and/or the like) that permits device 300 to communicate with other devices via a wired connection, a wireless connection, or a combination of wired and wireless connections. In some examples, communication interface 314 permits device 300 to receive information from another device and/or provide information to another device. In some examples, communication interface 314 includes an Ethernet interface, an optical interface, a coaxial interface, an infrared interface, a radio frequency (RF) interface, a universal serial bus (USB) interface, a Wi-Fi® interface, a cellular network interface, and/or the like.
[59] In some embodiments, device 300 performs one or more processes described herein. Device 300 performs these processes based on processor 304 executing software instructions stored by a computer-readable medium, such as memory 305 and/or storage component 308. A computer-readable medium (e.g., a non-transitory computer readable medium) is defined herein as a non-transitory memory device. A non-transitory memory device includes memory space located inside a single physical storage device or memory space spread across multiple physical storage devices.
[60] In some embodiments, software instructions are read into memory 306 and/or storage component 308 from another computer-readable medium or from another device via communication interface 314. When executed, software instructions stored in memory 306 and/or storage component 308 cause processor 304 to perform one or more processes described herein. Additionally or alternatively, hardwired circuitry is used in place of or in combination with software instructions to perform one or more processes described herein. Thus, embodiments described herein are not limited to any specific combination of hardware circuitry and software unless explicitly stated otherwise.
[61] Memory 306 and/or storage component 308 includes data storage or at least one data structure (e.g., a database and/or the like). Device 300 is capable of receiving information from, storing information in, communicating information to, or searching information stored in the data storage or the at least one data structure in memory 306 or storage component 308. In some examples, the information includes network data, input data, output data, or any combination thereof.
[62] In some embodiments, device 300 is configured to execute software instructions that are either stored in memory 306 and/or in the memory of another device (e.g., another device that is the same as or similar to device 300). As used herein, the term “module” refers to at least one instruction stored in memory 306 and/or in the memory of another device that, when executed by processor 304 and/or by a processor of another device (e.g., another device that is the same as or similar to device 300) cause device 300 (e.g., at least one component of device 300) to perform one or more processes described herein. In some embodiments, a module is implemented in software, firmware, hardware, and/or the like.
[63] The number and arrangement of components illustrated in FIG. 3 are provided as an example. In some embodiments, device 300 can include additional components, fewer components, different components, or differently arranged components than those illustrated in FIG. 3. Additionally or alternatively, a set of components (e.g., one or more components) of device 300 can perform one or more functions described as being performed by another component or another set of components of device 300.
[64] Referring now to FIG. 4, illustrated is an example block diagram of an autonomous vehicle compute 400 (sometimes referred to as an “AV stack”). As illustrated, autonomous vehicle compute 400 includes perception system 402 (sometimes referred to as a perception module), planning system 404 (sometimes referred to as a planning module), localization system 406 (sometimes referred to as a localization module), control system 408 (sometimes referred to as a control module), and database 410. In some embodiments, perception system 402, planning system 404, localization system 406, control system 408, and database 410 are included and/or implemented in an autonomous navigation system of a vehicle (e.g., autonomous vehicle compute 202f of vehicle 200). Additionally, or alternatively, in some embodiments, perception system 402, planning system 404, localization system 406, control system 408, and database 410 are included in one or more standalone systems (e.g., one or more systems that are the same as or similar to autonomous vehicle compute 400 and/or the like). In some examples, perception system 402, planning system 404, localization system 406, control system 408, and database 410 are included in one or more standalone systems that are located in a vehicle and/or at least one remote system as described herein. In some embodiments, any and/or all of the systems included in autonomous vehicle compute 400 are implemented in software (e.g., in software instructions stored in memory), computer hardware (e.g., by microprocessors, microcontrollers, application-specific integrated circuits (ASICs), Field Programmable Gate Arrays (FPGAs), and/or the like), or combinations of computer software and computer hardware. It will also be understood that, in some embodiments, autonomous vehicle compute 400 is configured to be in communication with a remote system (e.g., an autonomous vehicle system that is the same as or similar to remote AV system 114, a fleet management system 116 that is the same as or similar to fleet management system 116, a V2I system that is the same as or similar to V2I system 118, and/or the like).
[65] In some embodiments, perception system 402 receives data associated with at least one physical object (e.g., data that is used by perception system 402 to detect the at least one physical object) in an environment and classifies the at least one physical object. In some examples, perception system 402 receives image data captured by at least one camera (e.g., cameras 202a), the image associated with (e.g., representing) one or more physical objects within a field of view of the at least one camera. In such an example, perception system 402 classifies at least one physical object based on one or more groupings of physical objects (e.g., bicycles, vehicles, traffic signs, pedestrians, and/or the like). In some embodiments, perception system 402 transmits data associated with the classification of the physical objects to planning system 404 based on perception system 402 classifying the physical objects.
[66] In some embodiments, planning system 404 receives data associated with a destination and generates data associated with at least one route (e.g., routes 106) along which a vehicle (e.g., vehicles 102) can travel along toward a destination. In some embodiments, planning system 404 periodically or continuously receives data from perception system 402 (e.g., data associated with the classification of physical objects, described above) and planning system 404 updates the at least one trajectory or generates at least one different trajectory based on the data generated by perception system 402. In other words, planning system 404 may perform tactical function-related tasks that are required to operate vehicle 102 in on-road traffic. Tactical efforts involve maneuvering the vehicle in traffic during a trip, including but not limited to deciding whether and when to overtake another vehicle, change lanes, or selecting an appropriate speed, acceleration, deceleration, etc. In some embodiments, planning system 404 receives data associated with an updated position of a vehicle (e.g., vehicles 102) from localization system 406 and planning system 404 updates the at least one trajectory or generates at least one different trajectory based on the data generated by localization system 406.
[67] In some embodiments, localization system 406 receives data associated with (e.g., representing) a location of a vehicle (e.g., vehicles 102) in an area. In some examples, localization system 406 receives LiDAR data associated with at least one point cloud generated by at least one LiDAR sensor (e.g., LiDAR sensors 202b). In certain examples, localization system 406 receives data associated with at least one point cloud from multiple LiDAR sensors and localization system 406 generates a combined point cloud based on each of the point clouds. In these examples, localization system 406 compares the at least one point cloud or the combined point cloud to two-dimensional (2D) and/or a three-dimensional (3D) map of the area stored in database 410. Localization system 406 then determines the position of the vehicle in the area based on localization system 406 comparing the at least one point cloud or the combined point cloud to the map. In some embodiments, the map includes a combined point cloud of the area generated prior to navigation of the vehicle. In some embodiments, maps include, without limitation, high- precision maps of the roadway geometric properties, maps describing road network connectivity properties, maps describing roadway physical properties (such as traffic speed, traffic volume, the number of vehicular and cyclist traffic lanes, lane width, lane traffic directions, or lane marker types and locations, or combinations thereof), and maps describing the spatial locations of road features such as crosswalks, traffic signs or other travel signals of various types. In some embodiments, the map is generated in real-time based on the data received by the perception system.
[68] In another example, localization system 406 receives Global Navigation Satellite System (GNSS) data generated by a global positioning system (GPS) receiver. In some examples, localization system 406 receives GNSS data associated with the location of the vehicle in the area and localization system 406 determines a latitude and longitude of the vehicle in the area. In such an example, localization system 406 determines the position of the vehicle in the area based on the latitude and longitude of the vehicle. In some embodiments, localization system 406 generates data associated with the position of the vehicle. In some examples, localization system 406 generates data associated with the position of the vehicle based on localization system 406 determining the position of the vehicle. In such an example, the data associated with the position of the vehicle includes data associated with one or more semantic properties corresponding to the position of the vehicle.
[69] In some embodiments, control system 408 receives data associated with at least one trajectory from planning system 404 and control system 408 controls operation of the vehicle. In some examples, control system 408 receives data associated with at least one trajectory from planning system 404 and control system 408 controls operation of the vehicle by generating and transmitting control signals to cause a powertrain control system (e.g., DBW system 202h, powertrain control system 204, and/or the like), a steering control system (e.g., steering control system 206), and/or a brake system (e.g., brake system 208) to operate. For example, control system 408 is configured to perform operational functions such as a lateral vehicle motion control or a longitudinal vehicle motion control. The lateral vehicle motion control causes activities necessary for the regulation of the y-axis component of vehicle motion. The longitudinal vehicle motion control causes activities necessary for the regulation of the x-axis component of vehicle motion. In an example, where a trajectory includes a left turn, control system 408 transmits a control signal to cause steering control system 206 to adjust a steering angle of vehicle 200, thereby causing vehicle 200 to turn left. Additionally, or alternatively, control system 408 generates and transmits control signals to cause other devices (e.g., headlights, turn signal, door locks, windshield wipers, and/or the like) of vehicle 200 to change states.
[70] In some embodiments, perception system 402, planning system 404, localization system 406, and/or control system 408 implement at least one machine learning model (e.g., at least one multilayer perceptron (MLP), at least one convolutional neural network (CNN), at least one recurrent neural network (RNN), at least one autoencoder, at least one transformer, and/or the like). In some examples, perception system 402, planning system 404, localization system 406, and/or control system 408 implement at least one machine learning model alone or in combination with one or more of the above-noted systems. In some examples, perception system 402, planning system 404, localization system 406, and/or control system 408 implement at least one machine learning model as part of a pipeline (e.g., a pipeline for identifying one or more objects located in an environment and/or the like).
[71] Database 410 stores data that is transmitted to, received from, and/or updated by perception system 402, planning system 404, localization system 406 and/or control system 408. In some examples, database 410 includes a storage component (e.g., a storage component that is the same as or similar to storage component 308 of FIG. 3) that stores data and/or software related to the operation and uses at least one system of autonomous vehicle compute 400. In some embodiments, database 410 stores data associated with 2D and/or 3D maps of at least one area. In some examples, database 410 stores data associated with 2D and/or 3D maps of a portion of a city, multiple portions of multiple cities, multiple cities, a county, a state, a State (e.g., a country), and/or the like). In such an example, a vehicle (e.g., a vehicle that is the same as or similar to vehicles 102 and/or vehicle 200) can drive along one or more drivable regions (e.g., single-lane roads, multi-lane roads, highways, back roads, off road trails, and/or the like) and cause at least one LiDAR sensor (e.g., a LiDAR sensor that is the same as or similar to LiDAR sensors 202b) to generate data associated with an image representing the objects included in a field of view of the at least one LiDAR sensor.
[72] In some embodiments, database 410 can be implemented across a plurality of devices. In some examples, database 410 is included in a vehicle (e.g., a vehicle that is the same as or similar to vehicles 102 and/or vehicle 200), an autonomous vehicle system (e.g., an autonomous vehicle system that is the same as or similar to remote AV system 114, a fleet management system (e.g., a fleet management system that is the same as or similar to fleet management system 116 of FIG. 1 , a V2I system (e.g., a V2I system that is the same as or similar to V2I system 118 of FIG. 1 ) and/or the like.
[73] Referring now to FIG. 5, illustrated is a flowchart of a process 500 for addressing drivable artifacts for motion planning. In some embodiments, one or more of the steps described with respect to process 500 are performed (e.g., completely, partially, and/or the like) by a system of an autonomous or semi-autonomous vehicle (e.g., by autonomous vehicle compute 400 or 202f and/or using sensors 202a, 202b, 202c), by one or more systems remote to a vehicle (e.g., fleet management system 116 and/or vehicle-to- infrastructure system 118), or a combination thereof. For example, the process 500 can be performed by system 600 illustrated in FIG. 6, which can be implemented by an autonomous vehicle compute 400 or 202f, a fleet management system 116, and/or one or more other systems.
[74] The process 500 includes obtaining perception data characterizing an environment (502) and detecting, using the perception data, the presence of a drivable artifact in a portion of the environment that a vehicle is to traverse (504). For example, as shown in FIG. 7, an environment 700 includes a roadway 714 having two lanes 708, 710. The environment 700 further includes one or more drivable artifacts 712 in a portion of the environment 700 through which a vehicle 702 is to traverse, e.g., based on an originally- selected trajectory 704 of the vehicle 702.
[75] The vehicle 702 can be an autonomous or semi-autonomous vehicle, such as a vehicle 102 or 200, and can have at least the characteristics described for vehicles 102 and/or 200, such as the inclusion of autonomous system 202.
[76] The drivable artifacts 712 are roadway features over which the vehicle 702 can travel, at the cost of passenger experience. For example, the drivable artifacts 712 can include features of road surfaces, such as rough/bumpy road surfaces, construction debris such as metal plates or damaged road surfaces, potholes, manholes, and/or potentially-sharp objects. The vehicle 702 is able to travel over the drivable artifacts 712, but the drivable artifacts 712 would cause a negative user experience of traversal, e.g., by causing jostling of passenger(s) in the vehicle. In some embodiments, the drivable artifacts 712 are associated with safety hazards. For example, open manholes and sharp objects (e.g., glass) may damage the vehicle 702. Drivable artifacts 712 can be differentiated from “obstacles,” which include, for example, large debris that would block navigation of the vehicle 702, closed roads along which the vehicle 702 is not permitted to travel, barriers placed in road lanes, other vehicles stopped in the roadway, etc. [77] The perception data can include, and/or be derived from, for example, sensor data, such as vision data (e.g., data from cameras 202a), LiDAR data (e.g., data from LiDAR sensors 202b), radar data (e.g., data from radar sensors 202c), and/or inertial data (e.g., from an IMU of the vehicle). For example, the perception data can include raw and/or pre- processed sensor data, and/or can include a list of objects in the environment (including drivable artifacts) and the objects’ locations, the list derived from sensor data. In some embodiments, the perception data includes map data or other location data and previously-generated labels of the map data or other location data, the labels indicating drivable artifacts at certain locations. Examples of generation of and/or use of labels indicating drivable artifacts are provided below with respect to the drivable artifact database 604.
[78] In the example of the system 600, an active road surface labeling system 602 (sometimes referred to as an active road surface labeling module) is configured to identify drivable artifacts based on sensor data. For example, the active road surface labeling system 602 can obtain vision data, LiDAR data, radar data, and/or inertial data and process the data using one or more computational methods, such as computer vision methods and/or object detection methods. For example, the active road surface labeling system 602 can be configured to execute one or more trained convolutional neural networks (CNN) on vision data to identify imaged drivable artifacts. As another example, sensor data can be processed by a trained classifier, e.g., to identify specific object types, associated with drivable artifacts, in vision, LiDAR, and/or radar data (e.g., imaging radar data). As another example, inertial data from an IMU of the vehicle can be analyzed to identify a rough surface that the vehicle is driving on, e.g., based on bouncing by the vehicle. Further, non-limiting examples of methods that can be applied by the active road surface labeling system 602 include optical polarization analysis (e.g., for roughness detection) and Kalman-filter based object tracking and dimension estimation (e.g., for application to LiDAR and/or radar data).
[79] In some embodiments, the radar sensors 202c include a ground-facing radar and/or a forward-facing radar. A ground-facing radar is configured to sense the road surface, e.g., below and/or in front of the vehicle. A forward-facing radar is configured to sense non-road-surface objects in the environment. Data from the ground-facing radar can indicate the presence of, for example, rough road surfaces and potholes. Data from the forward-facing radar can indicate the presence of, for example, debris in the roadway.
[80] The active road surface labeling system 602 can be included in a vehicle and/or a remote system. For example, in some embodiments, the active road surface labeling system 602 is wholly or partially included in the perception system 402. For example, the perception system 402 can obtain data from on-board sensors (an example of obtaining perception data characterizing an environment (502)) and perform on-board detection (504) of the presence of a drivable artifact based on the sensor data.
[81] In some embodiments, the active road surface labeling system 602 is at least partially included in a computer system remote from the vehicle, e.g., distinct from the vehicle compute 400. For example, in some embodiments, the active road surface labeling system 602 is wholly or partially included in the fleet management system 116, which is configured to obtain sensor data from a vehicle 102 (an example of obtaining perception data characterizing an environment (502)) over network 112 and perform remote identification of drivable artifacts.
[82] In some embodiments, locations of previously-identified artifacts are stored in a database for subsequent retrieval and use in motion planning. For example, as shown in FIG. 6, the active road surface labeling system 602 can be configured to store artifact information, such as information about identified drivable artifacts and their corresponding locations, in a drivable artifact database 604. The drivable artifact database 604 can be, for example, a remote system (e.g., a cloud-based system or a system in a server remote from vehicles) including one or more storage devices. In some embodiments, drivable artifact database 604 is included in the fleet management system 116. In some embodiments, the drivable artifact database 604 is integrated together with another database that stores map data. For example, when the vehicle compute 400 obtains general map data for storage in the database 410 and for use in planning, the map data can include artifact information as labels of the map data. In some embodiments, drivable artifact database 604 is included in the vehicle computer 400, e.g., as part of database 410.
[83] In the example of FIG. 6, the artifact information 610 stored in the drivable artifact database 604 includes a list of drivable artifacts and their corresponding location(s). In the artifact information 610, the drivable artifacts can be identified by, for example, a type of drivable artifact, such as “rough road surface” or “pothole.” Corresponding locations can be stored in one or more suitable forms, such as GPS or other GNSS coordinates. In some embodiments, the location includes a polygon segment on a road, e.g., to indicate a portion of the road as having the drivable artifact. For example, the polygon segment can be defined by a set of coordinates that together bound the drivable artifact. In some embodiments, the location includes a road segment, e.g., to indicate that the road segment generally has the drivable artifact. In some embodiments, the location includes a coordinate of the drivable artifact and a size of the drivable artifact. The artifact information 610 can be referred to as a “label” because it effectively labels locations/map data with the locations’/maps’ corresponding drivable artifacts.
[84] In some embodiments, storing artifact information in the drivable artifact database 604 is dependent on a confidence in detection of the drivable artifact. For example, in some embodiments, a remote system such as the fleet management system 116 is configured to receive, from multiple vehicles, artifact information indicative of detection of drivable artifacts using sensors of the vehicles. When a drivable artifact has been detected by more vehicles, a confidence that the drivable artifact actually exists can be higher, and, in some embodiments, artifact information for the drivable artifact can be stored in the drivable artifact database 604 based on the confidence satisfying a condition, e.g., being at least a threshold. For example, in some embodiments, the fleet management system 116 adds artifact information for a drivable artifact to the drivable artifact database 604 in response to a threshold number of vehicles (such as two or three) reporting the presence of the drivable artifact to the fleet management system 116.
[85] In embodiments in which the active road surface labeling system 602 is included in a vehicle (e.g., as a module of vehicle compute 400, such as perception system 402), storing the artifact information can including uploading the artifact information to the database. For example, after an on-board active road surface labeling system 602 identifies a drivable artifact using on-board-collected sensor data, the active road surface labeling system 602 can send the artifact information to the fleet management system 116 over the network 112 for storage. [86] Artifact information stored in the drivable artifact database 604 can be retrieved by autonomous and semi-autonomous vehicles, so that vehicles in a fleet can be aware of drivable artifacts detected by other vehicles and/or detected using sensor data collected by other vehicles. As result, passenger comfort and safety can be improved throughout the fleet. For example, obtaining perception data characterizing an environment (502) can include obtaining (e.g., downloading) the artifact information, including labels indicating the presence of the drivable artifact, at a vehicle from the drivable artifact database 604, e.g., for storage in database 410 of the vehicle compute 400. In some embodiments, obtaining the artifact information from the drivable artifact database 604 (an example of obtaining perception data characterizing an environment (502)) is performed by the planning system 404.
[87] Detecting, using the perception data, the presence of a drivable artifact in a portion of the environment that a vehicle is to traverse (504) can be based at least partially on knowledge of the vehicle’s traversal. For example, the environment may include drivable artifacts in a portion of the environment that the vehicle is not planning to traverse. Accordingly, the process of element 504 can, in some embodiments, be performed by at least two modules/systems. For example, the perception system 402 can be configured to detect the presence of the drivable artifact based on sensor data, and the planning system 404 can be configured to recognize that the drivable artifact is in a portion of the environment that a vehicle is to traverse.
[88] Detection of the drivable artifact can be reactive or predictive, in various cases. Reactive detection includes, for example, an IMU-based and/or ground-facing radarbased determination that the vehicle is currently traversing rough ground. Predictive detection includes, for example, vision-based, LiDAR-based, forward-facing radar-based, imaging radar-based, and/or label-based (from labeled map data) determinations that a drivable artifact is in the environment, e.g., in a portion of the environment that the vehicle is to traverse.
[89] At least some of the process of element 504 can be performed by a trajectory modification system 608 (sometimes referred to as a trajectory modification module). The trajectory modification system 608 can be included in a vehicle and/or a remote system. For example, in some embodiments, the trajectory modification system 608 is wholly or partially included in the planning system 404. For example, the planning system 404 can obtain, from the perception system 402, data indicative of one or more drivable artifacts in the environment, based on the perception system 402 identifying the drivable artifacts using sensor data. As another example, the planning system 404 can obtain, from the database 410, map labels indicating locations of drivable artifacts, e.g., after the map labels have been obtained at the vehicle compute 400 from a remote drivable artifact database 604, and detect the presence of the drivable artifact based on the label.
[90] As discussed above, the drivable artifact includes a roadway feature over which the vehicle can travel and which is associated with a negative user experience of traversal. For example, as shown in FIG. 7, drivable artifacts 712 are in a portion of the environment (e.g., a portion of the road lane 708) traversed by the originally-selected trajectory 704, such that continuing on the originally-selected trajectory 704 would result in the vehicle 702 passing over/on the drivable artifacts 712.
[91] The originally-selected trajectory 704 is a trajectory that may be adjusted based on the presence of the drivable artifacts 712. In some embodiments, the originally- selected trajectory 704 is a trajectory determined by the planning system 404 without consideration of the presence of the drivable artifacts. As shown in FIG. 6, a trajectory generation system 606 (which can be included, for example, in the planning system 404 and/or in the fleet management system 116, and which is sometimes referred to as a trajectory generation module) is configured to determine the originally-selected trajectory, e.g., in an optimization process. For example, the trajectory generation system 606 can be configured to compute costs associated with multiple candidate trajectories and select, as the originally-selected trajectory 704, the candidate trajectory having the lowest cost. The originally-selected trajectory can be associated with a path (e.g., defined by one or more waypoints or nodes, such as Dubins nodes) and velocities defining the speeds of the vehicle along the path. The cost function based on which the costs are computed can be independent of the presence of the drivable artifacts 712, e.g., can result in costs whose values are not based on the presence or non-presence of the drivable artifacts 712. In some embodiments, the cost function depends on obstacles (as distinguished from drivable artifacts); for example, the cost function utilized by the trajectory generation system 606 can consider large debris, road closures, and other environment elements that the vehicle cannot traverse. The originally-selected trajectory can be a trajectory along which the vehicle is currently traveling, or can be a future, planned trajectory.
[92] In some embodiments, the trajectory modification system 608 is configured to obtain the originally-selected trajectory and determine whether the originally-selected trajectory traverses a portion of the environment having drivable artifacts. For example, the trajectory modification system 608 can be configured to compare locations of the originally-selected trajectory (e.g., a set of coordinates and/or segments defining the originally-selected trajectory) to location(s) of identified drivable artifacts, and detect, based on the comparison of locations, the presence of the drivable artifacts in the portion of the environment through which the originally-selected trajectory traverses.
[93] In response to detection of the presence of the drivable artifact, the trajectory modification system 608 is configured to determine adjustments to the trajectory of the vehicle (506). For example, the trajectory modification system 608 can modify the originally-selected trajectory to obtain an adapted trajectory. Modification of the originally- selected trajectory can include one or both of path adjustment (e.g., modification of waypoints that define the trajectory, compared to waypoints defining the originally- selected trajectory) and velocity adjustment (e.g., modification of the speed of the vehicle along the path, compared to the speeds of the originally-selected trajectory). Velocity adjustment can include adjustment of the velocity profile of the vehicle, as described with respect to FIGS. 8-10.
[94] The adapted trajectory can be determined so as to generally follow the same route as the original trajectory, but to avoid the drivable artifacts entirely or reduce an amount of time and/or distance during which the vehicle traverses the drivable artifacts. In the example of FIG. 7, an adapted trajectory 706 remains in the same lane 708 as the originally-selected trajectory 704, but deviates to the left to avoid the drivable artifacts 712. In various cases, the adapted trajectory may, for example, avoid the drivable artifact, traverse less of the drivable artifact than the originally-selected trajectory (e.g., avoid some but not all of the drivable artifact), and/or traverse the drivable artifact at a different speed than the originally-selected trajectory (e.g., slower, which may reduce passenger jostling when traversing the drivable artifact). [95] In some embodiments, the adapted trajectory is not based on a wholesale recalculation of the route of the vehicle, e.g., does not include a de novo trajectory optimization. Rather, the adapted trajectory is constrained by a predetermined degree of difference with the originally-selected trajectory, in one or more ways. For example, the adapted trajectory can be constrained to within one or more of: a maximum lateral deviation from the originally-selected trajectory (e.g., lateral deviation 716 illustrated in FIG. 714); a maximum length difference between the adapted trajectory and the originally- selected trajectory; a maximum difference in travel time between the adapted trajectory and the originally-selected trajectory; a maximum number of additional turns compared to the originally-selected trajectory; a maximum difference in speed between the originally-selected trajectory and the adapted trajectory; a maximum difference in acceleration between the originally-selected trajectory and the adapted trajectory; and/or a predetermined limitation on overall route differences between the adapted trajectory and the originally-selected trajectory, e.g., the adapted trajectory may be limited to the same roadway(s) as the originally-selected trajectory, may be limited to starting and ending at or within a predetermined distance from the start and end of the originally- selected trajectory, etc.
[96] The predetermined degree of difference is applied by the trajectory modification system 608 in a trajectory recalculation process, e.g., an optimization process. The trajectory recalculation process can include, for example, calculation of respective costs for one or more candidate adapted trajectories, where the costs are calculated using cost functions that take into account the presence of the drivable artifacts. For example, the costs can be based on one or more of: whether the vehicle traverses the drivable artifact (e.g., in a binary determination); a length of the vehicle’s traversal of the drivable artifact; a speed of the vehicle’s traversal of the drivable artifact; an acceleration of the vehicle during traversal of the drivable artifact; and/or a time duration of the vehicle’s traversal of the drivable artifact. Traversal of the drivable artifact increases the cost compared to entirely avoiding the drivable artifact, and longer traversal of the drivable artifact increases the cost compared to shorter traversals. In some embodiments, faster or slower traversal of the drivable artifact increases the cost. Any or all of the costs associated with these factors can depend on a type of the drivable artifact, e.g., some types of drivable artifacts can be associated with higher costs of traversal, based on those types of drivable artifacts being comparatively worse for passenger comfort and/or safety. The cost function can, in some embodiments, further take into account aspects of the candidate adapted trajectories that are not directly related to the presence of drivable artifacts, such as overall length, overall travel duration, trajectory curvature, acceleration, speed (e.g., minimum/maximum speed), and/or trajectory distance from road boundaries, to provide several non-limiting examples. The candidate adapted trajectory that satisfies one or more conditions based on the cost function (e.g., that has the lowest corresponding cost) can be selected as the adapted trajectory.
[97] The trajectory recalculation process is subject to the above-discussed and/or other constraint(s) on the adapted trajectory to remain within the predetermined degree of difference with the originally-selected trajectory. As such, trajectory recalculation can be performed with significantly reduced computational costs, and/or with significantly reduced computation time, compared to a trajectory calculation that did not include those constraints. As a non-limiting example, the trajectory modification system 608, in some embodiments, does not consider many disparate overall routes, complex alternative sequences of turns, etc., to determine the adapted trajectory. Rather, for certain examples of the constraint(s), the trajectory modification system 608 can be limited to considering, for example, various small adjustments to the originally-selected trajectory, such as small lateral deviations, temporary lane switches, etc. This recalculation can be performed rapidly and on-the-fly by an on-board system such as the vehicle compute 400, in some cases without compromising other operations of the on-board system.
[98] Accordingly, by separation of the determination of an original trajectory (which may be computationally intensive and involve relatively few constraints) and modification of the original trajectory to account for the presence of a drivable artifact (which may be constrained in one or more ways in reference to the original trajectory), the computational resources and/or time consumed in accounting for the presence of the drivable artifact can be reduced, permitting real-time, on-board, efficient trajectory determination and corresponding vehicle navigation. Moreover, because the adapted trajectory, in some cases, reduces passenger exposure to the drivable artifact (e.g., by causing the vehicle to entirely avoid the drivable artifact, by causing the vehicle to traverse less of the drivable artifact, and/or by causing the vehicle to traverse the drivable artifact at a slower speed), passenger comfort is increased.
[99] The adapted trajectory, once determined, can be implemented, e.g., by an actuation system 612 (sometimes referred to as an actuation module). The actuation system 612 can be included, for example, in the control system 408. In some embodiments, the control system 408 obtains the adapted trajectory from the planning system 404 (the planning system 404 implementing the trajectory modification system 608), and the control system 408 controls operation of the vehicle by generating and transmitting control signals to cause a powertrain control system, a steering control system, a brake system, and/or another vehicle system, to operate, as discussed above in reference to FIG. 4. Accordingly, the vehicle is caused to navigate along the adapted trajectory, e.g., along a modified path and/or with a modified speed compared to the originally-selected trajectory.
[100] FIG. 8 illustrates another example of a process 800 for modifying vehicle navigation based on the presence of a drivable artifact. As described for the process 500, one or more of the steps described with respect to process 800 are performed (e.g., completely, partially, and/or the like) by a system of an autonomous or semi-autonomous vehicle (e.g., by autonomous vehicle compute 400 or 202f and/or using sensors 202a, 202b, 202c), by one or more systems remote to a vehicle (e.g., fleet management system 116 and/or vehicle-to-infrastructure system 118), or a combination thereof.
[101] The process 800 can be performed by system 900 illustrated in FIG. 9. In the system 900, an active road surface labeling system 902, a drivable artifact database 904, and a trajectory generation system 906 can have characteristics as described for, and can perform functions that are described as being performed by, the active road surface labeling system 602, the drivable artifact database 604, and the trajectory generation system 606, respectively. For example, the active road surface labeling system 902 can be included in the perception system 402 and/or the fleet management system 116; the trajectory generation system 906 can be included in the planning system 404 and/or in the fleet management system 116; and the drivable artifact database 904 can be included in the database 410 and/or in a remote database, such as a database of the fleet management system 116. The trajectory generation system 906 generates an originally- selected trajectory, in some embodiments without taking into account the presence of the drivable artifact.
[102] The process 800 includes obtaining perception data characterizing an environment (802) and detecting, using the perception data, a presence of a drivable artifact in a portion of the environment that a vehicle is to traverse (804). These processes can be performed as described for processes 502 and 504, respectively. For example, processes 802 and 804 can include obtaining sensor data and detecting the presence of the drivable artifact based on the sensor data, and/or obtaining, from the drivable artifact database 904, labeled data indicating the presence of the drivable artifact, and detecting the presence of the drivable artifact based on the labeled data.
[103] The process 800 further including determining adjustments to a velocity of the vehicle in the portion of the environment in response to detecting the presence of the drivable artifact (806). For example, a velocity profile modification system 908 (which is sometimes referred to as a velocity profile modification module, and which can be included, for example, in the planning system 404, as described for the trajectory modification system 608) can be configured to obtain, from the trajectory generation system 906, an originally-selected trajectory as described with respect to FIGS. 5-7. For example, the originally-selected trajectory can be generated in an optimization process that does not account for the presence of the drivable artifact. The originally-selected trajectory is associated with a corresponding velocity profile defining the speed of the vehicle along the path of the originally-selected trajectory. The velocity profile modification system 908 is configured to adjust the speed along at least a portion of the path of the originally-selected trajectory, e.g., without modifying the path itself.
[104] For example, as shown in FIG. 10, a portion of a roadway 1014 in an environment 1000 includes a drivable artifact 1012, e.g., an area have a rough road surface. An originally-selected trajectory 1004 traverses the drivable artifact 1012. In addition, the originally-selected trajectory 1004 is associated with an original velocity profile 1008, which is, in this non-limiting example, a constant velocity profile, e.g., the vehicle 1002 is to traverse the roadway 1014, including the drivable artifact 1012, at a constant speed. Based on the presence of the drivable artifact 1012, the velocity along a portion of the originally-selected path of the originally-selected trajectory 1004 is adjusted, to obtain a modified velocity profile 1010 according to which the vehicle 1002 is controlled to traverse the originally-selected path. For example, the velocity can be adjusted at least at position(s) at which the originally-selected path traverses the drivable artifact 1012, such that the vehicle 1002 traverses the drivable artifact 1012 slower or faster than indicated by the original velocity profile 1008. In this example, the modified velocity profile 1010, includes a deceleration portion 1016, a constant-velocity portion 1020 that is slower than the corresponding portion of the original velocity profile 1008, and an acceleration portion 1018 that returns the modified velocity profile 1010 to match the original velocity profile 1008.
[105] The velocity profile modification system 908 can be configured to determine the modified velocity profile as described for the trajectory modification system’s 608 determination of the adapted trajectory. For example, the velocity profile modification system 908 can be configured to compute respective costs for multiple adapted trajectories that share a common path (the path of the originally-selected trajectory) but that have different velocity profiles. The computation, in some embodiments, can be subject to constraint(s) on the modified velocity profile to remain within a predetermined degree of difference with the originally-selected velocity profile. For example, the modified velocity profile can be constrained to within a maximum difference in speed from the originally-selected velocity profile (e.g., at matching locations); to within a maximum difference in acceleration from the originally-selected velocity profile (e.g., at matching locations); and/or to within a maximum difference in travel time between the originally- selected trajectory and the adapted trajectory having the modified velocity profile. The cost function can take into account at least the speed of the vehicle as it traverses the drivable artifact, and/or an acceleration of the vehicle as it traverses the drivable artifact. For example, in some embodiments, faster or slower traversal of the drivable artifact can be associated with higher costs, in situations in which passenger comfort is decreased by faster or slower traversal, respectively. As another example, in some embodiments, higher acceleration during traversal of the drivable artifact can be associated with higher costs, in situations in which passenger comfort is decreased by higher acceleration during traversal. Any or all of the costs associated with these factors can depend on a type of the drivable artifact, e.g., some types of drivable artifacts can be associated with higher costs of higher-speed travel, based on those types of drivable artifacts being comparatively worse for passenger comfort and/or safety when traversed at higher speeds. The cost function can, in some embodiments, further take into account aspects of the candidate adapted trajectories that are not directly related to the presence of drivable artifacts, such as overall length, overall travel duration, trajectory curvature, acceleration, speed (e.g., minimum/maximum speed), and/or trajectory distance from road boundaries, to provide several non-limiting examples. The candidate adapted trajectory that satisfies one or more conditions based on the cost function (e.g., that has the lowest corresponding cost based on its modified velocity profile) can be selected as the adapted trajectory.
[106] An actuation system 910 (sometimes referred to as an actuation module) causes the vehicle to navigate along the adapted trajectory, e.g., with modified speed(s) compared to speeds of the originally-selected trajectory. The actuation system 910 can have characteristics as described for the actuation system 612.
[107] In some cases, determination of specifically a modified velocity profile based on the presence of a drivable artifact, as described with respect to FIGS. 8-10, can be advantageous compared to some alternative methods. For example, determining adjustments to a velocity of the vehicle (806) can be less computationally taxing than determining adjustments to a path of the vehicle, e.g., can be performed faster and/or using fewer computational resources. For example, the search space for candidate adapted trajectories may be smaller when the candidate adapted trajectories vary only in their velocity profiles, compared to when the candidate adapted trajectories can vary in either or both of velocity profiles and path, and the smaller search space can facilitate faster determination of an optimal candidate adapted trajectory by the velocity profile modification system 908. As a result, vehicles can be controlled using on-the-fly velocity adjustments in response to drivable artifacts, increasing passenger comfort without overly burdening on-board computer systems.
[108] In addition, the process described with respect to FIGS. 8-10, like the process described with respect to FIGS. 5-7, may, in some embodiments, be performed relatively quickly and/or with relatively few computational resources based on the use of a two-step process of (i) generation of an originally-selected trajectory and (ii) modification of the originally-selected trajectory to obtain an adapted trajectory. The modification can be performed at relatively low computational cost so as to allow for rapid and efficient adaptation to drivable artifacts.
[109] In some embodiments, the presence of a drivable artifact is accounted for in a trajectory optimization process. For example, the presence of the drivable artifact can be accounted for in an initial trajectory optimization process, e.g., not necessarily by modifying an originally-selected trajectory.
[110] For example, FIG. 11 illustrates an example of a process 1100 for trajectory determination. As described for the processes 500 and 800, one or more of the steps described with respect to process 1100 are performed (e.g., completely, partially, and/or the like) by a system of an autonomous or semi-autonomous vehicle (e.g., by autonomous vehicle compute 400 or 202f and/or using sensors 202a, 202b, 202c), by one or more systems remote to a vehicle (e.g., fleet management system 116 and/or vehicle-to- infrastructure system 118), or a combination thereof.
[111] The process 1100 can be performed by system 1200 illustrated in FIG. 12. In the system 1200, an active road surface labeling system 1202 and a drivable artifact database 1204, can have characteristics as described for, and can perform functions that are described as being performed by, the active road surface labeling system 602 and the drivable artifact database 604, respectively. For example, the active road surface labeling system 1202 can be included in the perception system 402 and/or the fleet management system 116, and the drivable artifact database 1204 can be included in the database 410 and/or in a remote database, such as a database of the fleet management system 116.
[112] The process 1100 includes obtaining perception data characterizing an environment (1102) and detecting, using the perception data, a presence of a drivable artifact in the environment (1104). These processes can be performed at least partially as described for processes 502 and 504, respectively. For example, processes 1102 and 1104 can include obtaining sensor data and detecting the presence of the drivable artifact based on the sensor data, and/or obtaining, from the drivable artifact database 1204, labeled data indicating the presence of the drivable artifact, and detecting the presence of the drivable artifact based on the labeled data. In some embodiments, when the presence of the drivable artifact is detected (1104), the vehicle does not yet have a determined trajectory in the environment, such that detecting the presence of the drivable artifact, in some embodiments, does not include detecting that the vehicle is to traverse the drivable artifact. For example, the presence of the drivable artifact in the environment can be detected by obtaining map data of the environment that includes a label indicating the presence of the drivable artifact, even if the vehicle’s path through the environment has not been determined.
[113] Based on information about the drivable artifact, a trajectory generation system 1206 (sometimes referred to as a trajectory generation module) is configured to: determine candidate trajectories of the vehicle to traverse through the environment (1106); compute respective costs associated with the candidate trajectories, the respective costs based at least on distances between the candidate trajectories and the drivable artifact (1108); and select one of the candidate trajectories based on the costs (1110), e.g., by selecting the candidate trajectory having the lowest cost. The trajectory generation system 1206 can be included in an on-board computing system (e.g., in the vehicle compute 400, such as in the planning system 404), and/or in a remote computing system, such as the fleet management system 116.
[114] In this example, the process of accounting for the drivable artifact is folded into overall trajectory determination (optimization). The candidate trajectories can differ from one another in path and/or velocity profile, and costs can be computed for each using a cost function. The cost function depends at least on distances between the candidate trajectories and the drivable artifact. “Distances between the candidate trajectory and the drivable artifact” can include, for example, a binary determination of whether the candidate trajectories traverse the drivable artifact, and/or a continuous metric such as a distance between the trajectory and a center of the drivable artifact and/or a degree of overlap between the vehicle navigating on the trajectory and the drivable artifact. For example, traversal of the drivable artifact, navigation closer to the center of the drivable artifact, and higher overlap between the vehicle and the drivable artifact, can be associated with higher costs than non-traversal, further navigation, and less overlap, respectively. [115] In some embodiments, the cost function depends on the drivable artifact in one or more further ways, such as a length of the vehicle’s traversal of the drivable artifact; a speed of the vehicle’s traversal of the drivable artifact; an acceleration of the vehicle during traversal of the drivable artifact; and/or a time duration of the vehicle’s traversal of the drivable artifact. The cost function can, in some embodiments, further take into account aspects of the candidate trajectories that are not directly related to the presence of drivable artifacts, such as overall length, overall travel duration, trajectory curvature, acceleration, speed (e.g., minimum/maximum speed), and/or trajectory distance from road boundaries, to provide several non-limiting examples. The candidate trajectory that satisfies one or more conditions based on the cost function (e.g., that has the lowest corresponding cost) can be selected as the particular trajectory to be used for navigation.
[116] The candidate trajectories evaluated by the trajectory generation system 1206 are not limited by a predetermined difference with a previously-determined trajectory. Accordingly, the search space for selection of the particular trajectory to be used for navigation may be relatively large. In some cases, this can allow for the selection of a trajectory that provides improved passenger comfort and/or other positive characteristics. For example, limiting the search space to within a predetermined difference with a previously-determined trajectory may result in the selection of a trajectory having a local cost function minimum, while a larger search space may result in the selection of a trajectory having a global cost function minimum. As such, passenger comfort and/or other navigation characteristics (such as total navigation time, acceleration, etc.) can be improved.
[117] Referring to FIG. 13, illustrated in an example of an environment 1300 to which the process 1100 can be applied. The environment 1300 includes a roadway 1314 having two lanes 1308, 1310. Drivable artifacts 1312 are positioned in lane 1308. A vehicle 1302 is navigating in lane 1308. An on-board computing system of the vehicle 1302 obtains perception data characterizing the environment 1300 (1102) and detects the presence of the drivable artifacts 1312 (1104), e.g., based on data from sensor(s) of the vehicle 1302 and/or by downloading data that includes labels indicating the presence of the drivable artifacts 1312. The on-board computing system determines candidate trajectories 1306, 1316, 1318 through the environment 1300 (1106) and computes respective costs associated with each candidate trajectory 1306, 1316, 1318 (1108), the costs based at least on distances between each candidate trajectory 1306, 1316, 1318 and the drivable artifacts 1312. In some embodiments, the candidate trajectories 1306, 1316, 1318 are not restricted to within a predetermined degree of difference from a previously-determined trajectory. For example, the evaluation of the candidate trajectories 1306, 1316, 1318 can be an initial optim ization process for traversal through the portion of the environment 1300 having the drivable artifacts 1312.
[118] In this example, trajectory 1306 has the lowest cost from among the set of evaluated candidate trajectories 1306, 1316, 1318, and, accordingly, the on-board computing system selects trajectory 1306 to use for navigation. Trajectory 1306 includes a lane change from lane 1308 to lane 1310, representing a significant departure from the vehicle 1302 simply continuing in lane 1308. In some cases, this and other navigation re- routings are facilitated by the trajectory generation system 1206 accounting for the presence of drivable artifacts when performing overall trajectory optimization (e.g., as an initial optimization process). However, the example of FIG. 13 should not be understood to indicate that a lane change can only be performed based on the process of FIGS. 11- 13. For example, in some embodiments, a trajectory modification as described with respect to FIGS. 5-7 can result in an adapted trajectory that includes a lane change.
[119] An actuation system 1210 (sometimes referred to as an actuation module) causes the vehicle to navigate along the selected trajectory. The actuation system 1210 can have characteristics as described for the actuation systems 612, 910.
[120] In some embodiments, trajectory determination based on the presence of a drivable artifact is performed in an iterative process in which less computationally- intensive adaptations are attempted first, and more computationally-intensive adaptations are performed if the less computationally-intensive adaptations fail to provide satisfactory results. Referring to FIG. 14, illustrated is a process 1400 for determining an adapted trajectory. In some embodiments, one or more of the steps described with respect to process 1400 are performed (e.g., completely, partially, and/or the like) by a system of an autonomous or semi-autonomous vehicle (e.g., by autonomous vehicle compute 400 or 202f), by one or more systems remote to a vehicle (e.g., fleet management system 116 and/or vehicle-to-infrastructure system 118), or a combination thereof. The process 1400 can be performed, for example, by a system/module similar to trajectory modification system 608, velocity profile modification system 908, and/or trajectory generation system 1206. For example, the process 1400 can be performed by vehicle compute 400, e.g., by the planning system 404 or a module thereof.
[121] In some embodiments, the process 1400 is performed in response to detecting the presence of a drivable artifact in an environment, e.g., in a portion of an environment that the vehicle is to traverse. For example, the process 1400 can be performed in response to performance of process 504, 804, or 1104.
[122] With continued reference to FIG. 14, the process 1400 includes obtaining an originally-selected trajectory that traverses a portion of an environment having a drivable artifact (1402). For example, the originally-selected trajectory can be obtained from a trajectory generation system such as trajectory generation system 606 or trajectory generation system 906. In some embodiments, as discussed in reference to the systems 606, 906, the originally-selected trajectory is determined in an optimization process that does not account for the presence of the drivable artifact.
[123] A velocity profile of the originally-selected trajectory is adjusted, to obtain a first adapted trajectory having the path of the originally-selected trajectory with a different velocity profile (1404). Process 1404 can be performed, for example, as described with respect to process 806. For example, multiple candidate adapted trajectories can be evaluated using cost functions, where the candidate adapted trajectories can share a common path with the originally-selected trajectory and can have different respective velocity profiles. In some embodiments, the velocity profiles of the candidate adapted trajectories are limited to within a predetermined degree of difference with the velocity profile of the originally-selected trajectory. The candidate adapted trajectory associated with the lowest cost can be selected as the first adapted trajectory.
[124] With continued reference to FIG. 14, it is determined whether the first adapted trajectory satisfies one or more conditions (1406). The conditions can be based at least on characteristics of the first adapted trajectory, such as any of the characteristics described in this disclosure as being used in a cost function, e.g., length, navigation time, and/or speed of traversal of the drivable artifact, and/or characteristics not directly related to the presence of the drivable artifact, such as overall length, overall navigation time, curvature, etc. In some embodiments, the condition is based on the cost associated with the adapted trajectory. For example, the condition can be that the cost is less than a predetermined maximum value representing the cost-limit of an acceptable trajectory.
[125] If the first adapted trajectory satisfies the condition(s), the first adapted trajectory can be used for navigation (1414), e.g., as described in reference to the actuation system 910. If the first adapted trajectory does not satisfy the condition(s), the first adapted trajectory is determined to be unsatisfactory, and more extensive trajectory modification can be performed. In the example of FIG. 14, a path of the originally-selected trajectory is adjusted, to obtain a second adapted trajectory (1408). Process 1408 can be performed, for example, as described with respect to process 506. For example, multiple candidate adapted trajectories having different paths can be evaluated using a cost function, and the candidate adapted trajectory having the lowest cost can be selected as the second adapted trajectory. The multiple candidate adapted trajectories can be limited to within a predetermined degree of difference from the originally-selected trajectory, e.g., a maximum lateral deviation.
[126] In some embodiments, in addition to adjustment of the path of the originally- selected trajectory, a velocity profile of the originally-selected trajectory is also modified for the second adapted trajectory, as is also the case for process 506. For example, the trajectory search space for process 1404 (velocity modification only) can be a strict subset of the trajectory search space for process 1408 (path modification and optional velocity modification).
[127] With continued reference to FIG. 14, it is determined whether the second adapted trajectory satisfies one or more conditions (1410), which can be, for example, the same one or more conditions as in process 1406. Because the adjustment to obtain the first adapted trajectory (1404) is restricted to velocity modification, while the adjustment to obtain the second adapted trajectory (1408) can include path modification and velocity modification, in some cases the second adapted trajectory is expected to be better (e.g., for passenger comfort and/or in other respects) than the first adapted trajectory, e.g., to have a lower cost based on the same cost function. As such, even if the first adapted trajectory fails to satisfy the conditions (e.g., by having a cost that is greater than a maximum cost), the second adapted trajectory may satisfy the conditions (e.g., by having a cost that is less than or equal to the maximum cost).
[128] If the second adapted trajectory satisfies the condition(s), the second adapted trajectory can be used for navigation (1414), e.g., as described in reference to the actuation system 510. If the second adapted trajectory does not satisfy the condition(s), the second adapted trajectory is determined to be unsatisfactory. In response, an optimization process can be performed (1412) with fewer constraints than applied to determination of the second adapted trajectory (1408), to obtain a third adapted trajectory. For example, when determination of the second adapted trajectory is constrained to within a predetermined difference from the originally-selected trajectory, those constraints can be loosened (e.g., the maximum allowable lateral deviation can be increased) or removed entirely. In some embodiments, determination of the third adapted trajectory (1412) can effectively be performed as an initial optimization process without reference to the originally-selected trajectory. In some embodiments, determination of the third adapted trajectory (1412) can be performed as described in reference to processes 1106, 1108, 1110, e.g., corresponding to the operations of the trajectory generation system 1206.
[129] In some embodiments, the third adapted trajectory is directly used for navigation (1414), e.g., as described in reference to the actuation system 1210. In some embodiments, the third adapted trajectory is tested against one or more conditions in a decision process (not shown in FIG. 14), and the third adapted trajectory is used for navigation if the conditions are satisfied; if not, an alternative planning process can be used.
[130] The process of FIG. 14 can be understood as a process of using increasingly computationally-demanding processes (e.g., 1404, 1408, 1412) to determine an adapted trajectory in response to detecting the presence of a drivable artifact. Each successive process effectively has a larger search space for selection of the adapted trajectory from among candidate trajectories, and the larger-search-space (more computationally demanding) processes are applied only if the smaller-search-space (less computationally demanding) processes have failed to satisfy one or more conditions. Accordingly, computational resources consumed in trajectory determination can be reduced, and/or the computation can be performed faster, compared to always applying process 1412. [131] The techniques and processes described herein can enhance passenger experience and safety by accounting for the presence of drivable artifacts when planning motion. Drivable artifacts, distinct from obstacles that, for example, entirely block vehicle motion, can be traversed at the cost of comfort and/or safety. Adjustment of vehicle trajectories (path and/or velocity) in response to the drivable artifacts, and/or incorporation of the drivable artifacts into an optimization process such as an initial optimization process, can facilitate vehicle motion that avoids the drivable artifacts, traverses the drivable artifacts less, and/or traverses the drivable artifacts at comfortable and/or safer speeds.
[132] Moreover, the techniques and processes described herein can be computationally advantageous. For example, in some embodiments, trajectory adjustments are constrained to within a predetermined degree of difference (in path and/or velocity) from a previously-determined trajectory, which may reduce the computational resources used for addressing the drivable artifacts compared to an adjustment that is not constrained with respect to a previously-determined trajectory. In some embodiments, restriction of trajectory adaptation to velocity adjustment can result in fewer computational resources being consumed compared to more extensive adaptation processes (e.g., path adjustment).
[133] Addressing drivable artifacts as a distinct class of environmental feature (e.g., as distinct from obstacles that block vehicle motion) can be computationally advantageous, e.g., by allowing adaptation to drivable artifacts to be performed separately from an optimization process in which the obstacles are accounted for. Moreover, addressing drivable artifacts as a distinct class of environmental feature can result in improved motion planning. For example, treating drivable artifacts identically to obstacles may result in poor route planning (e.g., adding significant travel time to avoid a rough road segment), while ignoring drivable artifacts may result in negative user experience when vehicles traverse drivable artifacts that could be avoided with a minor trajectory adaptation.
[134] Non-limiting aspects and embodiments of the present disclosure include the following.
[135] Clause 1 : A method includes: obtaining, by at least one processor, perception data characterizing an environment; detecting, by the at least one processor using the perception data, a presence of a drivable artifact in a portion of the environment that a vehicle is to traverse, wherein the drivable artifact includes a roadway feature over which the vehicle can travel and which is associated with a negative user experience of traversal; and determining, by the at least one processor, adjustments to one or more parameters of movement of the vehicle in the portion of the environment in response to detecting the presence of the drivable artifact.
[136] Clause 2: the method of clause 1 , wherein determining the adjustments to the one or more parameters of movement includes adjusting a previously-determined trajectory of the vehicle in the environment in response to detecting the presence of the drivable artifact, to obtain an adjusted trajectory.
[137] Clause 3: the method of clause 2, wherein the adjustment of the previously- determined trajectory is constrained by a predetermined degree of difference between the previously-determined trajectory and the adjusted trajectory.
[138] Clause 4: the method of clause 3, wherein the adjustment of the previously- determined trajectory is constrained by a predetermined lateral deviation between the previously-determined trajectory and the adjusted trajectory.
[139] Clause 5: the method of any of clauses 2-4, wherein the previously-determined trajectory traverses the drivable artifact, and wherein the adjusted trajectory does not traverse the drivable artifact.
[140] Clause 6: the method of any of clauses 1 -5, wherein determining the adjustments to the one or more parameters of movement includes adjusting a speed of the vehicle in the environment in response to detecting the presence of the drivable artifact, to obtain an adjusted speed.
[141] Clause 7: the method of clause 6, wherein the adjusted speed includes a speed of the vehicle during traversal of the drivable artifact.
[142] Clause 8: the method of any of clauses 1 -7, wherein the drivable artifact includes at least one of a rough road surface, debris over which the vehicle can travel, a pothole, or a manhole.
[143] Clause 9: the method of any of clauses 1 -8, wherein obtaining the perception data includes obtaining sensor data captured by at least one sensor of the vehicle; and wherein detecting the presence of the drivable artifact includes detecting the presence of the drivable artifact in the sensor data.
[144] Clause 10: the method of clause 9, wherein the sensor data includes at least one of data from an inertial measurement unit of the vehicle or data from a ground-facing radar of the vehicle.
[145] Clause 11 : the method of clause 9, including: generating, by the at least one processor, the perception data at the vehicle based at least on the sensor data; labeling, by the at least one processor, the drivable artifact in the perception data; and sending, by the at least one processor, the perception data, including the label, from the vehicle to a remote computing system.
[146] Clause 12: the method of any of clauses 1-8, wherein obtaining the perception data includes obtaining the perception data at the vehicle from a remote computing system, the perception data including a label indicating the presence of the drivable artifact.
[147] Clause 13: a system, including: at least one processor; and at least one memory storing instructions thereon that, when executed by the at least one processor, cause the at least one processor to: obtain perception data characterizing an environment; detect, using the perception data, a presence of a drivable artifact in a portion of the environment that a vehicle is to traverse, wherein the drivable artifact includes a roadway feature over which the vehicle can travel and which is associated with a negative user experience of traversal; and determine, by the at least one processor, adjustments to one or more parameters of movement of the vehicle in the portion of the environment in response to detecting the presence of the drivable artifact.
[148] Clause 14: the system of clause 13, wherein determining the adjustments to the one or more parameters of movement includes adjusting a previously-determined trajectory of the vehicle in the environment in response to detecting the presence of the drivable artifact, to obtain an adjusted trajectory.
[149] Clause 15: the system of clause 14, wherein the adjustment of the previously- determined trajectory is constrained by a predetermined degree of difference between the previously-determined trajectory and the adjusted trajectory. [150] Clause 16: the system of any of clauses 13-15, wherein determining the adjustments to the one or more parameters of movement includes adjusting a speed of the vehicle in the environment in response to detecting the presence of the drivable artifact, to obtain an adjusted speed.
[151] Clause 17: a non-transitory computer readable medium including instructions stored thereon that, when executed by at least one processor, cause the at least one processor to carry out operations including: obtaining perception data characterizing an environment; detecting, using the perception data, a presence of a drivable artifact in a portion of the environment that a vehicle is to traverse, wherein the drivable artifact includes a roadway feature over which the vehicle can travel and which is associated with a negative user experience of traversal; and determining adjustments to one or more parameters of movement of the vehicle in the portion of the environment in response to detecting the presence of the drivable artifact.
[152] Clause 18: a method, including: obtaining, by at least one processor, perception data characterizing an environment; detecting, by the at least one processor using the perception data, a presence of a drivable artifact the environment, wherein the drivable artifact includes a roadway feature over which the vehicle can travel and which is associated with a negative user experience of traversal, determining, by the at least one processor, a plurality of candidate trajectories of the vehicle to traverse through the environment; computing respective costs associated with each of the plurality of candidate trajectories, the respective costs based at least on distances between the plurality of candidate trajectories and the drivable artifact; and selecting a particular trajectory from the plurality of candidate trajectories based on respective costs.
[153] Clause 19: the method of clause 18, wherein determining the respective costs is performed during an initial optimization process for traversal through the portion of the environment.
[154] Clause 20: the method of clause 18, wherein the respective costs are based at least on whether the plurality of candidate trajectories intersect the drivable artifact.
[155] Clause 21 : a method, including: obtaining, by at least one processor, perception data characterizing an environment, detecting, by the at least one processor using the perception data, a presence of a drivable artifact in a portion of the environment that a vehicle is to traverse, wherein the drivable artifact includes a roadway feature over which the vehicle can travel and which is associated with a negative user experience of traversal; determining, by the at least one processor, first adjustments to one or more parameters of movement of the vehicle in the portion of the environment in response to detecting the presence of the drivable artifact, to obtain a first adjusted trajectory; determining that the first adjusted trajectory does not satisfy a condition; and, in response to determining that the first adjusted trajectory does not satisfy the condition, determining second adjustments to the one or more parameters of movement, to obtain a second adjusted trajectory, wherein the second adjustments are constrained by fewer or no constraints compared to the first adjustments.
[156] In the foregoing description, aspects and embodiments of the present disclosure have been described with reference to numerous specific details that can vary from implementation to implementation. Accordingly, the description and drawings are to be regarded in an illustrative rather than a restrictive sense. The sole and exclusive indicator of the scope of the invention, and what is intended by the applicants to be the scope of the invention, is the literal and equivalent scope of the set of claims that issue from this application, in the specific form in which such claims issue, including any subsequent correction. Any definitions expressly set forth herein for terms contained in such claims shall govern the meaning of such terms as used in the claims. In addition, when we use the term “further comprising,” in the foregoing description or following claims, what follows this phrase can be an additional step or entity, or a sub-step/sub-entity of a previously- recited step or entity.