相关申请的交叉引用Cross-references to related applications
本申请要求如下的美国申请的权益：2016年6月14日提交的美国申请序列号15/182,281、2016年6月14日提交的美国申请序列号15/182,313、2016年6月14日提交的美国申请序列号15/182,360、2016年6月14日提交的美国申请序列号15/182,400、以及2016年6月14日提交的美国申请序列号15/182,365，上述申请中的每一个申请的公开内容通过引用以其整体结合于此。This application claims the benefit of the following U.S. Applications: U.S. Application Serial No. 15/182,281 filed on June 14, 2016, U.S. Application Serial No. 15/182,313 filed on June 14, 2016, Disclosures of U.S. Application Serial No. 15/182,360, U.S. Application Serial No. 15/182,400 filed on June 14, 2016, and U.S. Application Serial No. 15/182,365 filed on June 14, 2016, each of which The content is incorporated herein by reference in its entirety.
技术领域Technical field
本申请涉及用于自主车辆的路线规划。This application relates to route planning for autonomous vehicles.
背景技术Background technique
本说明书涉及用于自主车辆的路线规划。This specification relates to route planning for autonomous vehicles.
在旅程中的部分期间或在整个旅程期间，自主车辆可以安全驾驶而无需人为干预。Autonomous vehicles can drive safely without human intervention during part of the journey or throughout the entire journey.
自主车辆包括传感器、致动器、计算机、和通信设备，以实现对通过环境的路线的自动生成和跟踪。一些自主车辆具有无线双向通信能力，该无线双向通信能力用于：与可由人类监测器操纵的远程定位的命令中心通信、访问存储在云服务中的数据和信息、以及与紧急服务通信。Autonomous vehicles include sensors, actuators, computers, and communications equipment to enable automatic generation and tracking of routes through the environment. Some autonomous vehicles have wireless two-way communication capabilities that are used to: communicate with remotely located command centers that can be operated by human monitors, access data and information stored in cloud services, and communicate with emergency services.
如图1中所示的，在自主车辆10的典型使用中，可以以各种方式标识期望的目标位置12(例如，目的地地址或街道交叉路口)。可以由乘坐者(例如，可以是车辆的所有者或者移动即服务(mobility-as-a-service)“智能出租车(robo-taxi)”应用中的乘客)指定目标位置。目标位置可以由算法(例如，该算法可以在云中的中央服务器上运行，并且被委以优化自主车辆车队的位置的任务，目的是在乘坐者招呼智能出租车时最小化乘坐者的等待时间)提供。在一些情况下，目标位置可以由过程(例如，由于车辆上检测到的医疗紧急情况而将最近的医院标识为目标位置的紧急过程)提供。As shown in FIG. 1 , in typical use of autonomous vehicle 10 , desired target location 12 (eg, a destination address or a street intersection) may be identified in various ways. The target location may be specified by the occupant, who may be, for example, the owner of the vehicle or a passenger in a mobility-as-a-service "robo-taxi" application. The target location can be determined by an algorithm (for example, the algorithm can run on a central server in the cloud and be tasked with optimizing the location of a fleet of autonomous vehicles with the goal of minimizing the rider's waiting time when hailing a smart taxi. )supply. In some cases, the target location may be provided by a process (eg, an emergency process that identifies the nearest hospital as the target location due to a medical emergency detected on the vehicle).
在给定期望的目标位置的情况下，选路算法20确定通过环境的从车辆的当前位置16到目标位置12的路线14。我们有时称这个过程为“路线规划”。在一些实施方式中，路线是道路、街道、和公路(highway)的一系列经连接的段(我们有时将其称为道路段或简称段)。Given a desired target location, the routing algorithm 20 determines a route 14 through the environment from the vehicle's current location 16 to the target location 12 . We sometimes call this process "route planning." In some embodiments, a route is a series of connected segments of roads, streets, and highways (which we sometimes refer to as road segments or simply segments).
选路算法通常通过分析道路网络信息来操作。道路网络信息通常是关于道路网络的结构、类型、连接性、和其他相关信息的数字表示。道路网络通常被表示为一系列经连接的道路段。道路网络信息除了标识道路段之间的连接性之外，还可以包含关于每个道路段的物理和概念属性的附加信息，该附近信息包括但不限于地理位置、道路名称或数量、道路长度和宽度、速度限制、行驶方向、车道边缘边界类型、以及关于道路段的任何特殊信息，所述任何特殊信息诸如是否为公交车道、是仅右转弯车道还是仅左转弯车道、是否是公路、小道路或土道路的部分、该道路段是否允许停车或站立、以及其他属性。Routing algorithms typically operate by analyzing road network information. Road network information is usually a digital representation of the structure, type, connectivity, and other related information about the road network. Road networks are usually represented as a series of connected road segments. In addition to identifying connectivity between road segments, road network information may also contain additional information about the physical and conceptual properties of each road segment. This proximity information includes, but is not limited to, geographic location, road name or number, road length, and Width, speed limit, direction of travel, lane edge boundary type, and any special information about the road segment such as whether it is a bus lane, whether it is a right turn lane only or a left turn lane only, whether it is a highway, a small The portion of a road or dirt road, whether parking or standing is allowed on that road segment, and other attributes.
选路算法通常标识从当前位置到目标位置的一个或多个候选路线22。通常通过采用标识最小化指定成本的路线的算法(诸如，A*、D*、Dijkstra算法等)来完成从候选路线中标识最好或最佳的路线14。该成本通常根据一个或多个标准，所述一个或多个标准通常包括沿着候选路线行驶的距离、在考虑速度限制时沿候选路线行驶的预期时间、交通状况、以及其他因素。选路算法可以标识要被呈现给乘坐者(或其他人，例如，在远程位置处的操作员)的一个或多个良好路线，以供选择或批准。在一些情况下，可以简单地将一个最佳路线提供给车辆轨迹规划和控制模块28，车辆轨迹规划和控制模块28具有引导车辆沿着最佳路线朝向目标(我们有时称为目标位置或仅仅称为目标)的功能。The routing algorithm typically identifies one or more candidate routes 22 from the current location to the target location. Identifying the best or optimal route 14 from the candidate routes is typically accomplished by employing an algorithm that identifies a route that minimizes a specified cost, such as A*, D*, Dijkstra's algorithm, etc. The cost is typically based on one or more criteria, which typically include the distance traveled along the candidate route, the expected time to travel along the candidate route when speed limits are taken into account, traffic conditions, and other factors. The routing algorithm may identify one or more good routes to be presented to the rider (or others, such as an operator at a remote location) for selection or approval. In some cases, an optimal route may simply be provided to the vehicle trajectory planning and control module 28, which has the function of guiding the vehicle along the optimal route toward the target (which we sometimes refer to as the target location or just as the target) function.
如图2中所示的，道路网络信息通常被存储在数据库30中，数据库30被维持在集中式可访问服务器32上，并且可以以高频率(例如，1Hz或更高)更新数据库30。可以按需访问(例如，由车辆34请求)网络信息，或者由服务器将网络信息推送给车辆。As shown in Figure 2, road network information is typically stored in a database 30, which is maintained on a centralized accessible server 32 and which can be updated at a high frequency (eg, 1 Hz or higher). Network information may be accessed on demand (eg, requested by vehicle 34) or pushed to the vehicle by a server.
道路网络信息可以具有与道路网络信息相关联的时间信息，所述时间信息用于实现对交通规则、停车规则或与时间有关的其他影响(例如，例如在标准营业时间期间或在周末期间不允许停车的道路段)的描述，或所述时间信息用于包括关于在一天中的特定时间(例如，在高峰时间段期间)沿着道路段的预期行驶时间的信息。The road network information may have time information associated with the road network information used to implement traffic rules, parking rules or other time-related effects (e.g. not allowed during standard business hours or during weekends) A description of the road segment where the vehicle is parked), or the time information is used to include information about the expected travel time along the road segment at a specific time of day (eg, during peak hours).
发明内容Contents of the invention
通常，在一方面中，确定路线的可行性。该路线包括将由自主车辆从开始位置行驶到目标位置的经连接的道路段的序列。该路线符合所存储的道路网络信息。Typically, in one aspect, the feasibility of a route is determined. The route includes a sequence of connected road segments that will be traveled by the autonomous vehicle from a starting location to a target location. The route conforms to the stored road network information.
实施方式可包括以下特征中的一项或者以下特征中的两项或更多项的组合。该路线的可行性包括自主车辆安全地行驶该路线的能力。可行性包括自主车辆不能安全地行驶该路线。该路线的可行性状态包括自主车辆稳健地行驶该路线的能力。可行性状态包括自主车辆不能稳健地行驶该路线。计算机确定路线组中的每一条路线的可行性。计算机确定到给定时间为止的可行性。该路线是由路线规划过程确定的两条或更多条候选路线中的一条。将该路线排除在作为候选路线的考虑之外。可行性状态取决于车辆上的传感器的特性。特性包括根据当前状况或预测的未来状况的实际性能水平或估计性能水平。Implementations may include one or a combination of two or more of the following features. The feasibility of the route includes the ability of the autonomous vehicle to travel the route safely. Feasibility includes the inability for autonomous vehicles to travel the route safely. The route's feasibility status includes the autonomous vehicle's ability to travel the route robustly. The feasibility state includes the autonomous vehicle being unable to travel the route robustly. The computer determines the feasibility of each route in the route group. The computer determines feasibility up to a given time. The route is one of two or more candidate routes identified by the route planning process. Exclude this route from consideration as a candidate route. The feasibility status depends on the characteristics of the sensors on the vehicle. Characteristics include actual or estimated performance levels based on current conditions or predicted future conditions.
可行性状态取决于软件过程的特性。软件过程包括对来自车辆上的传感器的数据进行处理。软件过程包括运动规划。软件过程包括决策制定。软件过程包括车辆运动控制。特性包括根据当前状况或预测的未来状况的实际性能水平或估计性能水平。The feasibility status depends on the characteristics of the software process. The software process involves processing data from sensors on the vehicle. The software process includes motion planning. Software processes include decision making. The software process includes vehicle motion control. Characteristics include actual or estimated performance levels based on current conditions or predicted future conditions.
可行性状态取决于道路特征的特性。道路特征的特性包括交叉路口、环岛(roundabout)或高速公路出入口的空间特性。道路特征的特性包括交叉路口、环岛或高速公路出入口的连接性特性。道路特征的特性包括空间定向。道路特征的特性包括道路施工或交通事故。道路特征的特性包括粗糙度。道路特征的特性包括由于弯曲和坡度导致的差的能见度。道路特征的特性包括自主车辆的差的先前驾驶性能。道路特征的特性包括模型自主车辆的差的先前模拟性能。道路特征的特性包括恶劣天气中的物理导航挑战。The feasibility status depends on the characteristics of the road features. Characteristics of road features include spatial characteristics of intersections, roundabouts, or highway entrances and exits. Properties of road features include connectivity properties of intersections, roundabouts, or highway entrances and exits. Properties of road features include spatial orientation. Characteristics of road features include road construction or traffic accidents. Characteristics of road features include roughness. Characteristics of road features include poor visibility due to curves and slopes. Characteristics of the road characteristics include poor previous driving performance of the autonomous vehicle. Characteristics of the road features include poor prior simulation performance of the model autonomous vehicle. Characteristics of road features include physical navigation challenges in inclement weather.
通常，在一方面中，确定属于道路网络信息体的一个或多个道路段对于自主车辆的行驶的可行性。使道路段的可行性状态可用于与道路网络信息相连接。Generally, in one aspect, the feasibility of one or more road segments belonging to a body of road network information for travel by an autonomous vehicle is determined. Makes the feasibility status of road segments available for connection with road network information.
实施方式可包括以下特征中的一项或者以下特征中的两项或更多项的组合。道路段的可行性包括自主车辆安全地行驶该道路段的能力。可行性包括自主车辆不能安全地行驶该道路段。该路线的可行性包括自主车辆稳健地行驶该道路段的能力。可行性包括自主车辆不能稳健地行驶该道路段。计算机确定到给定时间为止的可行性。可行性取决于车辆上的传感器的特性。特性包括根据当前状况或预测的未来状况的实际性能水平或估计性能水平。Implementations may include one or a combination of two or more of the following features. The feasibility of a road segment includes the ability of an autonomous vehicle to travel that road segment safely. Feasibility includes the road segment being unsafe for autonomous vehicles to travel. The feasibility of the route includes the ability of autonomous vehicles to robustly travel this road segment. Feasibility includes the road segment being unable to be driven robustly by an autonomous vehicle. The computer determines feasibility up to a given time. Feasibility depends on the characteristics of the sensors on the vehicle. Characteristics include actual or estimated performance levels based on current conditions or predicted future conditions.
可行性取决于软件过程的特性。软件过程包括对来自车辆上的传感器的数据进行处理。软件过程包括运动规划。软件过程包括决策制定。软件过程包括车辆运动控制。特性包括根据当前状况或预测的未来状况的实际性能水平或估计性能水平。Feasibility depends on the characteristics of the software process. The software process involves processing data from sensors on the vehicle. The software process includes motion planning. Software processes include decision making. The software process includes vehicle motion control. Characteristics include actual or estimated performance levels based on current conditions or predicted future conditions.
可行性状态取决于道路段的特性。道路段的特性包括交叉路口、环岛或高速公路出入口的空间特性。道路段的特性包括交叉路口、环岛或高速公路出入口的连接性特性。道路段的特性包括空间定向。道路段的特性包括道路施工或交通事故。道路段的特性包括粗糙度。道路段的特性包括由于弯曲和坡度导致的差的能见度。道路段的特性包括自主车辆的差的先前驾驶性能。道路段的特性包括模型自主车辆的差的先前模拟性能。道路段的特性包括在恶劣天气中的物理导航挑战。当自主车辆正行驶该路线时，路线的可行性状态被更新。The feasibility status depends on the characteristics of the road segment. Properties of road segments include the spatial properties of intersections, roundabouts, or highway entrances and exits. Road segment properties include the connectivity properties of intersections, roundabouts, or highway entrances and exits. Characteristics of road segments include spatial orientation. Characteristics of road segments include road construction or traffic accidents. Characteristics of road segments include roughness. Characteristics of road segments include poor visibility due to curves and slopes. Characteristics of the road segment include poor previous driving performance of the autonomous vehicle. The characteristics of the road segment include poor previous simulation performance of the model autonomous vehicle. Characteristics of road segments include physical navigation challenges in inclement weather. The route's feasibility status is updated while the autonomous vehicle is traveling the route.
通常，在一方面中，作出关于如下的确定：到一时间或时间范围为止，自主车辆安全地或稳健地行驶正被考虑用于该自主车辆的道路特征或道路段或路线的能力。该路线符合所存储的道路网络信息的属性。如果计算机已经确定道路特征或道路段或路线不能由自主车辆安全地或稳健地行驶，则将该道路特征或道路段或路线排除在考虑之外。计算机的确定是基于自主车辆的属性的。Generally, in one aspect, a determination is made regarding an autonomous vehicle's ability to safely or robustly travel a road feature or road segment or route for which the autonomous vehicle is being considered, up to a time or range of time. The route conforms to the properties of the stored road network information. If the computer has determined that a road feature or road segment or route cannot be driven safely or robustly by an autonomous vehicle, that road feature or road segment or route is excluded from consideration. The computer's determination is based on the properties of the autonomous vehicle.
实施方式可包括以下特征中的一项或以下特征中的两项或更多项的组合。属性包括自主车辆在自主行驶期间所使用的传感器的特性。自主车辆安全或稳健地行驶的能力的确定基于处理表示自主车辆的属性的数据的软件过程。属性包括传感器的性能水平，所述性能水平包括根据当前状况或预测的未来状况的实际性能水平或估计性能水平。自主车辆的属性包括一个或多个传感器在特定性能水平下产生感兴趣的数据产品的能力。自主车辆的属性包括一个或多个传感器的故障模式。自主车辆的属性包括由自主车辆所使用的软件过程的特性。软件过程的特性包括软件过程在特定性能水平下产生感兴趣的数据产品的能力。软件过程的特性包括数据融合网络在特定性能水平下产生感兴趣的数据产品的能力。软件过程包括运动规划过程。软件过程包括决策制定过程。软件过程包括运动控制过程。Implementations may include one or a combination of two or more of the following features. The attributes include the characteristics of the sensors used by the autonomous vehicle during autonomous driving. Determination of an autonomous vehicle's ability to travel safely or robustly is based on a software process that processes data representing attributes of the autonomous vehicle. Attributes include performance levels of sensors, including actual or estimated performance levels based on current conditions or predicted future conditions. The attributes of an autonomous vehicle include the ability of one or more sensors to produce data products of interest at a specific performance level. Properties of autonomous vehicles include failure modes of one or more sensors. Properties of autonomous vehicles include characteristics of software processes used by autonomous vehicles. The characteristics of a software process include the ability of the software process to produce the data product of interest at a specific performance level. Characteristics of a software process include the ability of the data fusion network to produce the data products of interest at a specific performance level. The software process includes the motion planning process. Software processes include decision-making processes. Software processes include motion control processes.
通常，在一方面中，作出关于如下的确定：到一时间或时间范围为止，自主车辆安全地或稳健地行驶正被考虑用于该自主车辆的道路特征或道路段或路线的能力。路线符合所存储的道路网络信息的属性。如果计算机已经确定道路特征或道路段或路线不能由自主车辆安全地或稳健地行驶，则将该道路特征或道路段或路线排除在考虑之外。计算机的确定基于自主车辆行驶的环境的属性。Generally, in one aspect, a determination is made regarding an autonomous vehicle's ability to safely or robustly travel a road feature or road segment or route for which the autonomous vehicle is being considered, up to a time or range of time. The route conforms to the properties of the stored road network information. If the computer has determined that a road feature or road segment or route cannot be driven safely or robustly by an autonomous vehicle, that road feature or road segment or route is excluded from consideration. The computer's determination is based on properties of the environment in which the autonomous vehicle is traveling.
实施方式可包括以下特征中的一项或者以下特征中的两项或更多项的组合。环境包括道路特征。环境的属性包括自主车辆的可导航性。环境的属性包括道路特征的空间特性。环境的属性包括道路特征的连接性特性。环境的属性包括道路特征的空间定向。环境的属性包括道路施工或交通事故的位置。环境的属性包括道路特征的道路表面粗糙度。环境的属性包括影响能见度的弯曲坡度。环境的属性包括道路特征的标记的特性。环境的属性包括与恶劣天气相关联的道路特征的物理导航挑战。计算机确定自主车辆安全或稳健地行驶道路特征组中的每一个道路特征或道路段组中的每一个道路段或路线组中的每一个路线的能力。Implementations may include one or a combination of two or more of the following features. The environment includes road features. Properties of the environment include the navigability of autonomous vehicles. Properties of the environment include the spatial properties of road features. Properties of the environment include the connectivity properties of road features. Properties of the environment include the spatial orientation of road features. Properties of the environment include the location of road construction or traffic accidents. Properties of the environment include road surface roughness of road features. Properties of the environment include curved slopes that affect visibility. Properties of the environment include characteristics of markers of road features. Properties of the environment include the physical navigation challenges of road features associated with severe weather. The computer determines the ability of the autonomous vehicle to safely or robustly travel each road feature in the group of road features or each road segment in the group of road segments or each route in the group of routes.
自主车辆安全或稳健地行驶道路特征或道路段或路线的能力取决于车辆上的传感器的特性。特性包括根据当前状况或预测的未来状况的实际性能水平或估计性能水平。计算机确定自主车辆到给定时间为止的能力。该路线是由路线规划过程确定的两条或更多条候选路线中的一条。自主车辆安全或稳健地行驶道路特征或道路段或路线的能力取决于软件过程的特性。软件过程包括对来自车辆上的传感器的数据进行处理。软件过程包括运动规划。软件过程包括决策制定。软件过程包括车辆运动控制。特性包括根据当前状况或预测的未来状况的实际性能水平或估计性能水平。The ability of an autonomous vehicle to safely or robustly navigate road features or road segments or routes depends on the characteristics of the sensors on the vehicle. Characteristics include actual or estimated performance levels based on current conditions or predicted future conditions. The computer determines the capabilities of the autonomous vehicle by a given time. The route is one of two or more candidate routes identified by the route planning process. The ability of an autonomous vehicle to safely or robustly navigate road features or road segments or routes depends on the characteristics of the software process. The software process involves processing data from sensors on the vehicle. The software process includes motion planning. Software processes include decision making. The software process includes vehicle motion control. Characteristics include actual or estimated performance levels based on current conditions or predicted future conditions.
通常，在一方面中，作出关于如下的确定：到一时间或时间范围为止，自主车辆安全地或稳健地行驶正被考虑用于该自主车辆的道路特征或道路段或路线的能力。该路线符合所存储的道路网络信息的属性。如果计算机已经确定道路特征或道路段或路线不能由自主车辆安全地或稳健地行驶，则将该道路特征或道路段或路线排除在考虑之外。该确定是基于对自主车辆的性能的分析的。Generally, in one aspect, a determination is made regarding an autonomous vehicle's ability to safely or robustly travel a road feature or road segment or route for which the autonomous vehicle is being considered, up to a time or range of time. The route conforms to the properties of the stored road network information. If the computer has determined that a road feature or road segment or route cannot be driven safely or robustly by an autonomous vehicle, that road feature or road segment or route is excluded from consideration. This determination is based on an analysis of the performance of autonomous vehicles.
实施方式可包括以下特征中的一项或者以下特征中的两项或更多项的组合。对自主车辆的性能的分析包括与道路特征相关联的先前驾驶性能。对自主车辆的性能的分析包括与道路特征相关联的先前模拟性能。Implementations may include one or a combination of two or more of the following features. Analysis of autonomous vehicle performance includes previous driving performance associated with road characteristics. Analysis of autonomous vehicle performance includes previously simulated performance associated with road characteristics.
通常，在一方面中，从两条或更多条候选路线的组中选择到一时间或时间范围为止由自主车辆行驶的路线，该组中的所有候选路线具有超过可行性阈值的可行性状态。Typically, in one aspect, a route traveled by an autonomous vehicle up to a time or time range is selected from a group of two or more candidate routes, all candidate routes in the group having a feasibility status exceeding a feasibility threshold .
实施方式可包括以下特征中的一项或者以下特征中的两项或更多项的组合。可行性状态包括如下的指示：该候选路线可以由自主车辆安全地或稳健地行驶或者由自主车辆安全地并且稳健地行驶。从源接收作为数据产品或数据的馈送的关于候选路线的信息。所接收的关于候选路线的信息是道路网络信息的部分。候选路线包括包含尚未验证的至少一个道路段的路线。Implementations may include one or a combination of two or more of the following features. The feasibility status includes an indication that the candidate route can be traveled safely or robustly by an autonomous vehicle or both safely and robustly by an autonomous vehicle. Information about candidate routes is received from a source as a data product or feed of data. The information received about candidate routes is part of the road network information. Candidate routes include routes that contain at least one road segment that has not yet been verified.
这些和其他的方面、特征、实施方式、以及优势、以及它们的组合可以被表达为方法、系统、部件、装置、程序产品、经营商业的方法、用于执行功能的装置或步骤、以及以其他方式被表达。These and other aspects, features, embodiments, and advantages, and combinations thereof, may be expressed as methods, systems, components, devices, program products, methods of doing business, means or steps for performing functions, and otherwise way is expressed.
根据以下描述和权利要求，其他方面、特征、实施方式和优势将变得显而易见。Other aspects, features, embodiments, and advantages will become apparent from the following description and claims.
附图说明Description of the drawings
图1示出了在自主车辆的典型使用中对期望的目标位置的标识。Figure 1 shows the identification of desired target locations in a typical use of an autonomous vehicle.
图2示出了用于维持存储有道路网络信息的数据库的集中式可访问服务器。Figure 2 shows a centrally accessible server for maintaining a database storing road network information.
图3示出了传感器和软件过程的物理位置的示例。Figure 3 shows an example of the physical location of sensors and software processes.
图4至图9是道路场景的示意图。Figures 4 to 9 are schematic diagrams of road scenes.
图10是车辆和远程定位的数据库的示意图。Figure 10 is a schematic diagram of a vehicle and remote location database.
具体实施方式Detailed ways
对于涉及人类驾驶车辆的路线规划，通常假设由选路算法标识的从当前位置到目标位置的路线是可由驾驶员安全驾驶的路线，其中所述路线是由经连接的道路段组成的。然而，由于各种原因，对于由该选路算法为自主车辆标识的路线，该假设可能无效。由于道路特征的特定属性和车辆相对于这些道路特征的能力，自主车辆可能不能安全地导航某些道路段、交叉路口、或其他地理区域(我们将广泛地称其为道路特征)。而且，自主车辆可能在一天中的某些时段期间、一年中的某些时段期间、或在某些天气状况下不能安全地导航某些道路特征。For route planning involving human-driven vehicles, it is generally assumed that the route identified by the routing algorithm from the current location to the target location is a route that can be driven safely by the driver, where the route is composed of connected road segments. However, for various reasons, this assumption may not be valid for the routes identified by this routing algorithm for autonomous vehicles. Autonomous vehicles may not be able to safely navigate certain road segments, intersections, or other geographic areas (which we will refer to broadly as road features) due to the specific properties of road features and the vehicle's capabilities relative to those road features. Furthermore, autonomous vehicles may not be able to safely navigate certain road features during certain times of the day, during certain times of the year, or under certain weather conditions.
图3和图10中示出了车辆中的传感器和在基于云的服务器和数据库处的软件过程的物理位置的示例。Examples of the physical location of sensors in a vehicle and software processes at cloud-based servers and databases are shown in Figures 3 and 10.
传感器和软件过程Sensors and software processes
在许多情况下，这种无法安全地导航道路特征涉及传感器和软件过程的特性，自主车辆使用所述传感器和软件过程来感知环境、处理来自传感器的数据、了解当前由感知的环境所呈现的状况以及可能将来由感知的环境所呈现的状况、执行运动规划、执行运动控制、以及基于这些感知和了解作出决策。除其他事物外，在某些状况下以及在某些时间处，传感器和过程的如下能力可能劣化(degrade)或丢失，或者受到不可接受的改变：感知环境、了解状况、执行运动规划和运动控制、以及作出决策。In many cases, this inability to safely navigate road features involves characteristics of the sensors and software processes used by autonomous vehicles to sense the environment, process data from the sensors, and understand the current conditions presented by the sensed environment. and possible future situations presented by sensing the environment, performing motor planning, performing motor control, and making decisions based on these perceptions and understandings. Under certain conditions and at certain times, the ability of sensors and processes to, among other things, sense the environment, understand the situation, and perform motion planning and motion control may be degraded or lost, or otherwise unacceptably altered. , and make decisions.
传感器和软件过程输出的这种劣化或不可接受的改变的示例如下：Examples of such degradation or unacceptable changes in sensor and software process output are as follows:
用于感知车辆的环境的传感器Sensors for sensing the vehicle’s environment
如图3上所示的，以下类型的传感器40通常可用于具有驾驶员辅助能力或高度自动驾驶能力的车辆(例如，自主车辆)：能够测量车辆的环境的属性的传感器，包括但不限于，例如，激光雷达(LIDAR)、雷达(RADAR)、可见光、红外或热光谱中的单目视频相机或立体视频相机、超声波传感器、飞行时间(TOF)深度传感器、以及温度和雨水传感器、以及它们的组合。来自这些传感器的数据42可被处理44以产生“数据产品”46，例如，关于其他车辆、行人、骑自行车者、滑板车、车厢、推车、动物和其他移动物体的类型、位置、速度和估计的未来运动的信息。数据产品还包括相关的物体和特征、道路标记以及道路标志的位置、类型和内容，其中所述相关的物体和特征诸如是静态阻挡物(例如，杆、标志、路缘、交通标记锥和桶、交通信号、交通标志、道路分隔物和树木)As shown on Figure 3, the following types of sensors 40 may generally be used in vehicles with driver assistance capabilities or highly automated driving capabilities (eg, autonomous vehicles): Sensors capable of measuring properties of the vehicle's environment, including, but not limited to, For example, lidar (LIDAR), radar (RADAR), monocular or stereo video cameras in the visible, infrared or thermal spectrum, ultrasonic sensors, time of flight (TOF) depth sensors, and temperature and rain sensors, and their combination. Data 42 from these sensors may be processed 44 to produce "data products" 46 , for example, regarding the type, location, speed, and Estimated future movement information. Data products also include associated objects and features, road markings, and the location, type, and content of road signs, such as static obstructions (e.g., poles, signs, curbs, traffic sign cones, and barrels). , traffic signals, traffic signs, road dividers and trees)
软件过程44使用这种传感器数据以在特定性能水平下计算这种数据产品的能力取决于传感器的属性，诸如，检测范围、分辨率、噪声特性、温度依赖性、和其他因素。在特定性能水平下计算这些数据产品的能力还可能取决于环境状况，诸如，环境光照的属性(例如，是否存在直射阳光、漫射阳光、日出或日落状况、黄昏或黑暗)，雾、霭、烟雾或空气污染的存在，是否正在下雨或下雪或者最近是否已经下雨或下雪，以及其他因素。The ability of the software process 44 to use such sensor data to calculate such data products at a particular performance level depends on the properties of the sensor, such as detection range, resolution, noise characteristics, temperature dependence, and other factors. The ability to calculate these data products at a specific performance level may also depend on environmental conditions, such as the properties of the ambient lighting (e.g., presence of direct sunlight, diffuse sunlight, sunrise or sunset conditions, dusk or darkness), fog, haze , the presence of smog or air pollution, whether it is raining or snowing or has recently rained or snowed, and other factors.
通常，表征特定的传感器(以及相关联的处理软件)在特定性能水平(例如，特定水平的检测准确度、检测范围、真肯定或假肯定的比率、或其他度量)下产生感兴趣的数据产品的能力是可能的，其中所述特定性能水平根据与环境状况相关的可测量的度量。例如，表征特定单目相机传感器可以在特定性能水平下检测移动车辆的范围通常是可能的，其中所述特定性能水平根据与白天和夜晚状况相关联的环境照明水平。Typically, a data product of interest is characterized as producing a particular sensor (and associated processing software) at a particular performance level (e.g., a particular level of detection accuracy, detection range, rate of true positives or false positives, or other metric) Capabilities are possible where the specific performance level is based on measurable metrics related to environmental conditions. For example, it is often possible to characterize the extent to which a particular monocular camera sensor can detect moving vehicles at a specific performance level based on ambient lighting levels associated with day and night conditions.
此外，标识传感器的特定故障模式，以及标识传感器未被设计成能够生成的数据产品通常是可能的，其中所述传感器的特定故障模式即传感器将确切地劣化或无法生成感兴趣的数据产品的状况或环境。Furthermore, it is often possible to identify specific failure modes of a sensor, i.e. conditions under which the sensor will degrade or be unable to generate the data product of interest, and to identify data products that the sensor was not designed to be able to generate. or environment.
图9示出了自主车辆传感器配置的示例。Figure 9 shows an example of an autonomous vehicle sensor configuration.
用于处理来自传感器的数据的软件Software for processing data from sensors
如上所述，可以由软件过程44使用来自传感器的数据以产生感兴趣的各种数据产品。软件过程中的每一个的生成符合指定性能水平的数据产品的能力取决于传感器软件过程(例如，算法)的属性，这可能会限制它们在具有某些属性的场景中的性能，其中所述具有某些属性的场景诸如，与手头上的感测任务相关的数据特征的密度非常高或非常低。As discussed above, data from sensors may be used by software process 44 to generate various data products of interest. The ability of each of the software processes to generate data products that meet specified performance levels depends on the properties of the sensor software processes (e.g., algorithms), which may limit their performance in scenarios with certain properties, including Scenarios for certain attributes include very high or very low density of data features relevant to the sensing task at hand.
例如，用于依赖于来自单目视觉传感器的数据来进行行人检测的算法(我们有时可互换地使用术语软件过程和算法)可能在其以指定的性能水平(例如，指定的处理速率)检测超过一定数量的行人的能力方面劣化或失败，并且可能因此在具有大量的行人的场景中劣化或失败(在指定的性能水平下的情景中没有检测到所有行人的意义上)。此外，在几乎不具有诸如平坦的停车场之类的几何地势的场景中，用于基于从车辆安装的传感器收集的激光雷达数据与存储在地图数据库中的数据的比较来确定自我(ego)车辆的位置(称为“定位”)的算法可能以其能力无法在指定的性能水平下(例如，在指定的位置准确度程度下)确定车辆的当前位置。For example, an algorithm (we sometimes use the terms software process and algorithm interchangeably) for pedestrian detection that relies on data from a monocular vision sensor may perform detection at a specified performance level (e.g., a specified processing rate) Capabilities degrade or fail above a certain number of pedestrians, and may therefore degrade or fail in scenarios with large numbers of pedestrians (in the sense that not all pedestrians are detected in the scenario at a specified performance level). Furthermore, in a scene with little geometric terrain such as a flat parking lot, it is used to determine the ego vehicle based on comparison of lidar data collected from sensors mounted on the vehicle with data stored in a map database Algorithms for positioning (referred to as "localization") may not be able to determine the vehicle's current location at a specified level of performance (e.g., at a specified degree of location accuracy).
通常，表征特定传感器软件过程的如下的能力是可能的：在根据可测量的场景属性的特定性能水平下产生感兴趣的数据产品。Typically, it is possible to characterize a particular sensor software process's ability to produce data products of interest at specific performance levels based on measurable scene attributes.
通常，由一个以上传感器提供的数据被组合在由一个或多个软件过程实施的数据融合框架中，目的是改进计算一个或多个数据产品的整体性能。例如，来自视频相机的数据可以与来自激光雷达传感器的数据组合，以实现在被设计为超过通过单独使用视频相机或激光雷达传感器可实现的性能水平的性能水平下检测行人。在诸如此类的数据融合场景中，上述情况仍然如此：表征特定数据融合框架在特定性能水平下产生感兴趣的数据产品的能力通常是可能的。Typically, data provided by more than one sensor are combined in a data fusion framework implemented by one or more software processes with the goal of improving the overall performance of computing one or more data products. For example, data from a video camera may be combined with data from a lidar sensor to achieve detection of pedestrians at a performance level designed to exceed performance levels achievable by using the video camera or lidar sensor alone. In data fusion scenarios such as this, the above remains true: it is often possible to characterize the ability of a specific data fusion framework to produce the data product of interest at a specific performance level.
用于运动规划的软件过程Software process for motion planning
能够高度自动驾驶的车辆(例如，自主车辆)依赖于运动规划过程，即，自动生成和执行通过环境朝向指定的短期目标的轨迹的算法过程。我们广义地使用术语轨迹来包括例如从一个地方到另一个地方的路径。为了区分由运动规划过程产生的轨迹与由路线规划过程产生的路线，我们注意到轨迹是通过车辆最近周围环境(例如，距离标度通常在几米到几百米的量级)的路径，这些路径被专门设计成不与阻挡物碰撞，并且通常具有与如下的相关的理想特性：路径长度、乘坐质量、所需行驶时间、不违反道路规则、遵守驾驶习惯、或其他因素。Vehicles capable of highly automated driving (e.g., autonomous vehicles) rely on motion planning processes, that is, algorithmic processes that automatically generate and execute trajectories through the environment toward specified short-term goals. We use the term trajectory broadly to include, for example, a path from one place to another. To distinguish trajectories produced by a motion planning process from routes produced by a route planning process, we note that trajectories are paths through the vehicle's nearest surroundings (i.e., the distance scale is typically on the order of a few meters to a few hundred meters). Are specifically designed not to collide with obstructions and typically have desirable characteristics related to path length, ride quality, required travel time, non-violation of road rules, compliance with driving habits, or other factors.
在自主车辆上采用的一些运动规划过程表现出已知的限制。例如，在假设车辆仅在向前方向上移动但不在向后方向上移动的情况下，某个运动规划过程可能能够计算用于车辆的从其当前位置到目标的路径。或者，某个运动计划过程可能能够仅在车辆以小于指定速度限制的速度行驶时计算用于车辆的路径。Some motion planning processes employed on autonomous vehicles exhibit known limitations. For example, a motion planning process might be able to calculate a path for the vehicle from its current position to the target, assuming that the vehicle only moves in the forward direction but not in the backward direction. Alternatively, a motion planning process might be able to calculate a path for a vehicle only when the vehicle is traveling less than a specified speed limit.
基于对过程的算法设计或其在模拟或实验测试中观察到的性能的了解来标识运动规划过程上的这些和类似的性能特性(例如，限制)通常是可能的。根据特定运动规划过程的限制，可能难以或不可能在特定区域中安全地导航，所述特定区域例如，需要以高速度行驶的公路，或需要涉及向前和后退操纵两者的复杂多点转弯的多级停车结构。It is often possible to identify these and similar performance characteristics (eg, limitations) on a motion planning process based on knowledge of the algorithmic design of the process or its observed performance in simulations or experimental tests. Depending on the constraints of the specific motion planning process, it may be difficult or impossible to safely navigate in certain areas, such as highways that require traveling at high speeds, or complex multi-point turns that require both forward and reverse maneuvers. multi-level parking structure.
用于决策制定的软件过程software process for decision making
能够高度自动驾驶的车辆依赖于决策制定过程，即算法过程，该决策制定过程用于自动决定用于车辆在给定时间的适当短期行动进程，例如，是否超过停止的车辆或在其后面等待；是否行进通过四向停止交叉路口或避让(yield)已先前到达该交叉路口的车辆。Vehicles capable of highly autonomous driving rely on decision-making processes, i.e. algorithmic processes, that are used to automatically decide on the appropriate short-term course of action for the vehicle at a given time, for example, whether to pass a stopped vehicle or wait behind it; Whether to proceed through a four-way stop intersection or to yield to vehicles that have previously arrived at the intersection.
在自主车辆上采用的一些决策制定过程表现出已知的限制。例如，某个决策制定过程可能无法确定用于在高复杂度的某些场景中(例如，在包括交通灯的环岛中)或在多层停车结构中的车辆的适当的行动进程。Some decision-making processes employed on autonomous vehicles exhibit known limitations. For example, a certain decision-making process may not determine an appropriate course of action for a vehicle in certain scenarios of high complexity (eg, in a roundabout including traffic lights) or in a multi-story parking structure.
如在运动规划过程的情况下，基于对过程的算法设计或其在模拟或实验测试中观察到的性能的了解来标识决策制定过程上的这些和类似的性能特性(例如，限制)通常是可能的。根据对特定决策制定过程的限制，可能难以或不可能在特定区域中安全地导航。As in the case of motion planning processes, it is often possible to identify these and similar performance characteristics (e.g., limitations) on the decision-making process based on knowledge of the process's algorithmic design or its observed performance in simulations or experimental tests. of. Depending on the constraints placed on a particular decision-making process, it may be difficult or impossible to safely navigate certain areas.
用于车辆运动控制的软件过程Software process for vehicle motion control
自主车辆通常旨在通过采用运动控制过程以高精确程度遵循由运动规划过程提供的轨迹。运动控制过程基于对从期望轨迹的当前偏离和预测偏离的分析和其他因素来计算控制输入(即，转向、制动和油门输入)组。Autonomous vehicles are typically designed to follow a trajectory provided by a motion planning process with a high degree of accuracy by employing motion control processes. The motion control process calculates sets of control inputs (ie, steering, braking, and throttle inputs) based on analysis of current and predicted deviations from the desired trajectory and other factors.
这些运动控制过程表现出已知的限制。例如，某个运动控制过程可以允许仅在向前方向上的稳定操作，而不允许在向后方向上操作。或者，某个运动控制过程可能具有仅在车辆以小于指定速度限制的速度行驶时跟踪期望的轨迹(达指定的精度)的能力。或者，某个运动控制过程可能具有如下的能力：仅在道路表面摩擦系数超过某个特定水平时执行需要某个水平的横向或纵向加速度的转向或制动输入。These motor control processes exhibit known limitations. For example, a certain motion control process may allow stable operation only in the forward direction, but not in the backward direction. Alternatively, a motion control process might have the ability to track a desired trajectory (to a specified accuracy) only when the vehicle is traveling less than a specified speed limit. Alternatively, a motion control process might have the ability to perform steering or braking inputs that require a certain level of lateral or longitudinal acceleration only when the road surface friction coefficient exceeds a certain level.
如在运动规划和决策制定过程的情况下，基于对过程的算法设计或其在模拟或实验测试中观察到的性能的了解来标识运动控制过程上的这些和类似的限制通常是可能的。根据对特定运动控制过程的限制，可能难以或不可能在特定区域中安全地导航。As in the case of motion planning and decision-making processes, it is often possible to identify these and similar limitations on a motion control process based on knowledge of the algorithmic design of the process or its observed performance in simulations or experimental tests. Depending on the limitations on specific motor control processes, it may be difficult or impossible to navigate safely in certain areas.
可以基于根据当前状况和未来状况的传感器和软件过程的特定性能水平来确定自主车辆的安全或稳健操作。Safe or robust operation of an autonomous vehicle can be determined based on specific performance levels of sensors and software processes based on current and future conditions.
道路特征的特性Characteristics of road features
路线规划过程旨在排除如下的候选路线：包括可被确定为自主车辆无法安全地导航的道路特征。为此目的，路线规划过程可以有用地考虑与自主车辆特别相关的信息的源，所述信息包括关于道路特征的特性的信息，诸如空间特性、定向、表面特性等。通常，这种信息将用于避开为自主车辆选择如下路线：通过对车辆来说难以或不可能在所需的性能或安全水平下进行导航的道路网络的区域。这里描述了信息的源的示例，以及它们对自主车辆性能或安全性的影响的解释。The route planning process is designed to eliminate candidate routes that include road features that can be determined to be unsafe for autonomous vehicles to navigate. To this end, the route planning process may usefully take into account sources of information particularly relevant to autonomous vehicles, including information about the properties of road features, such as spatial properties, orientation, surface properties, etc. Typically, this information will be used to avoid routing for autonomous vehicles through areas of the road network that are difficult or impossible for the vehicle to navigate at the required level of performance or safety. Examples of sources of information are described here, along with explanations of their impact on autonomous vehicle performance or safety.
交叉路口、环岛、高速公路出入口或其他道路特征的空间特性Spatial properties ofintersections, roundabouts, highway entrances, or other road features
如图5中所示的示例所示，道路网络信息可以包含或允许通过单独的过程计算与道路交叉路口、环岛、高速公路出入口或包括多车道表面道路和公路的其他道路特征的空间特性有关的信息。这样的信息可以包括例如道路的宽度、交叉路口两端的距离(即，从交叉路口的边缘处的行驶车道上的点到交叉路口的相对边缘处的相对车道上的点的距离)、以及环岛两端的距离(即，环岛的直径)As shown in the example shown in Figure 5, road network information may contain or allow calculation by a separate process related to the spatial characteristics of road intersections, roundabouts, highway entrances and exits, or other road features including multi-lane surface roads and highways. information. Such information may include, for example, the width of the road, the distance between the two ends of the intersection (i.e. the distance from a point on the driving lane at the edge of the intersection to a point on the opposite lane at the opposite edge of the intersection), and the distance between the two ends of the roundabout. The distance between the ends (i.e., the diameter of the roundabout)
鉴于对自主车辆的传感器系统的检测属性的了解，对这种空间特性的分析可以允许在不考虑或者鉴于某个时间或一天中的时间或时间范围(例如，在日落之后和日出之前)的情况下，确定某些道路段不能由自主车辆在指定的安全水平或稳健水平下导航。考虑到对自主车辆的感测能力的实际限制和道路的可允许行驶速度，这可以允许自主车辆避开(例如)某些交叉路口，这些交叉路口例如“在日落之后，太大而不能看到两端”。这些限制可能使得自主车辆传感器不可能以足够的用于对即将发生的交通作出反应的时间来向运动规划过程提供数据产品。Given an understanding of the detection properties of an autonomous vehicle's sensor system, analysis of such spatial characteristics may allow detection of such spatial characteristics regardless of or in view of a certain time or time of day or time range (e.g., after sunset and before sunrise). situations where it is determined that certain road segments cannot be navigated by autonomous vehicles at a specified level of safety or robustness. Given practical limitations on the sensing capabilities of autonomous vehicles and the permissible travel speeds of roads, this could allow autonomous vehicles to avoid (for example) certain intersections that are too large to see, such as "after sunset" Both ends". These limitations may make it impossible for autonomous vehicle sensors to provide data products to the motion planning process with sufficient time to react to impending traffic.
交叉路口、环岛、高速公路出入口或其他道路特征的连接性特性Connectivity properties ofintersections, roundabouts, highway entrances, or other road features
如图4中所示的示例所示，道路网络信息可以包含或允许通过单独的过程来计算与特定道路段或各个道路段车道或其他道路特征的连接性特性有关的信息。例如，这种信息可以包括相交的道路段相对于彼此的定向。它还可以包括对专门的行驶车道的指定，诸如，仅右转弯和仅左转弯车道指定，或对公路入口坡道和出口坡道的标识。As shown in the example shown in Figure 4, road network information may contain or allow calculation by a separate process of information related to connectivity characteristics of lanes or other road features for a specific road segment or individual road segments. Such information may include, for example, the orientation of intersecting road segments relative to each other. It may also include the designation of special travel lanes, such as right-turn-only and left-turn-only lane designations, or markings of highway entrance and exit ramps.
鉴于对自主车辆传感器系统的检测属性、运动规划过程的能力以及决策制定过程的能力的了解，对这种连接性特性的分析可以允许确定某些道路段或高速公路出入口潜在地在一天中的某个(某些)时间处或时间范围内不能由自主车辆在指定的安全水平或稳健水平下导航。这可以允许自主车辆避开例如具有如下的几何属性的交叉路口：使得自主车辆传感器不可能以足够的用于对即将发生的交通作出反应的时间向运动规划过程提供数据产品。考虑到对车辆的决策制定能力的已知限制，它还可以允许自主车辆避开太复杂而不能安全地导航(例如，由于复杂的所需的合并，或者无法推出在专门的行驶车道中的行驶)的交叉路口。Given the understanding of the detection properties of autonomous vehicle sensor systems, the capabilities of motion planning processes, and the capabilities of decision-making processes, analysis of this connectivity characteristic could allow the identification of certain road segments or highway entrances and exits that are potentially open at certain times of the day. A (certain) time or time range that cannot be navigated by an autonomous vehicle at a specified level of safety or robustness. This may allow the autonomous vehicle to avoid, for example, intersections with geometric properties that make it impossible for the autonomous vehicle sensors to provide data products to the motion planning process with sufficient time to react to oncoming traffic. It could also allow autonomous vehicles to avoid maneuvers that are too complex to navigate safely (e.g. due to complex required merging, or the inability to push out of a dedicated driving lane), given the known limitations on the vehicle's decision-making capabilities. ) intersection.
道路特征的空间定向Spatial Orientation of Road Features
如图6中所示的示例所示，道路网络信息可以包含或允许通过单独的过程来计算与特定道路段或各个道路段车道或其他道路特征的空间定向(例如，在惯性坐标系中的定向)有关的信息。As shown in the example shown in Figure 6, road network information may contain or allow calculation by a separate process of spatial orientation (e.g., orientation in an inertial coordinate system) with respect to a specific road segment or individual road segment lanes or other road features. ) related information.
鉴于对自主车辆传感器系统的检测属性的了解，对道路特征的定向的分析可以允许确定某些道路段或高速公路出入口潜在地在一天中的某个(某些)时间处或时间范围内不能由自主车辆在指定的安全水平或稳健水平下导航。这可以允许自主车辆避免(例如)被“太阳致盲(sunblinded)”(即，由于以低倾斜入射角暴露于直射阳光而经历视频相机和/或激光雷达传感器的严重劣化的性能)。Given knowledge of the detection properties of autonomous vehicle sensor systems, analysis of the orientation of road features can allow the determination of certain road segments or highway entrances that are potentially incapable of being accessed by the vehicle at certain times of day or time ranges. Autonomous vehicles navigate within a specified level of safety or robustness. This may allow autonomous vehicles to avoid, for example, being "sunblinded" (ie, experiencing severely degraded performance of video cameras and/or lidar sensors due to exposure to direct sunlight at low oblique angles of incidence).
道路施工和交通事故的位置Location of road construction and traffic accidents
道路网络信息可以包含或经由实时地图绘制服务提供商或另一输入而被增加以包括，关于潜在地导致某些道路段的关闭的道路施工或事故的位置的信息。鉴于对自主车辆的传感器系统的检测属性的了解，对这种信息的分析可以允许确定由于车辆不能检测到临时标牌、障碍物或者由与道路施工或事故相关联的人员交通指导呈现的手势信号而导致某些道路段或高速公路出入口不能由自主车辆导航。Road network information may contain or be augmented via a real-time mapping service provider or another input to include information regarding the location of road construction or accidents that could potentially result in the closure of certain road segments. Given the knowledge of the detection properties of autonomous vehicles' sensor systems, analysis of this information can allow the determination of errors due to the vehicle's inability to detect temporary signage, obstacles or hand signals presented by human traffic guidance associated with road construction or accidents. As a result, certain road segments or highway entrances and exits cannot be navigated by autonomous vehicles.
粗糙道路特征的位置Location of rough road features
道路网络信息可以包含或经由实时地图绘制服务提供商或类似输入而被增加以包括，关于粗糙的、劣化的、坑坑洼洼的、损坏的、洗涤板式的(washboarded)或部分构造的道路(包括未准备好的道路和次要道路、以及故意以减速带或振动带(rumblestrips)构造的道路)的区域的位置的信息。该信息可以是二元指定的形式(例如，“粗糙道路”或“光滑道路”)或者是以量化道路表面粗糙度的连续数字或语义度量的形式。Road network information may include or be augmented via a real-time mapping service provider or similar input to include information regarding rough, degraded, potholed, damaged, washboarded or partially constructed roads (including unprepared roads). Information on the location of areas of good and secondary roads, as well as roads intentionally constructed with speed bumps or rumblestrips. This information may be in the form of a binary specification (eg, "rough road" or "smooth road") or in the form of a continuous number or semantic measure that quantifies the roughness of the road surface.
鉴于对自主车辆的传感器系统的检测属性的了解，对道路表面粗糙度的分析可以允许确定某些道路段或高速公路出入口潜在地在一天中的某个(某些)时间处或时间范围内不能由自主车辆在指定的安全水平或稳健水平下导航。这可以允许自主车辆避开(例如)在物理传感器安装件中引起振动从而导致差的传感器系统性能的严重洗涤板式的道路，或者具有可能被感知过程意外地分类为不可通过的阻挡物的减速带的道路区域。Given knowledge of the detection properties of autonomous vehicles' sensor systems, analysis of road surface roughness could allow determination of certain road segments or highway entrances that are potentially unavailable at certain times of day or time ranges. Navigation by an autonomous vehicle at a specified level of safety or robustness. This could allow the autonomous vehicle to avoid, for example, heavily scrubbed roads that induce vibrations in the physical sensor mounts resulting in poor sensor system performance, or speed bumps with obstructions that may be accidentally classified as impassable by the sensing process. road area.
由于弯曲和坡度而具有差的能见度的道路特征的位置Locations of road features with poor visibility due to curves and slopes
如图7和图8中所示的，道路网络信息可以包含或允许通过单独的过程来计算与道路特征的弯曲和坡度(沿着车辆俯仰或滚动轴线)有关的信息。As shown in Figures 7 and 8, the road network information may contain or allow calculation by a separate process of information regarding the curvature and slope of road features (along the vehicle pitch or roll axis).
鉴于对自主车辆的传感器系统的检测属性的了解，对道路特征的弯曲和坡度的分析可以允许确定某些道路段或高速公路出入口潜在地在一天中的某个(某些)时间处或时间范围内不能由自主车辆在指定的安全水平或稳健水平下导航。这可以允许自主车辆避开如下的道路段：陡峭倾斜的并且因此使得车辆传感器系统不可能“越过山坡观看(seeoverthehill)”(即，由于传感器的有限的垂直视野，而不能检测周围环境中的交通的存在)，以及不可能“看到拐角周围(seearoundthecorner)”(即，由于传感器的有限的水平视野，而不能检测周围环境中的交通的存在)。Given knowledge of the detection properties of autonomous vehicles' sensor systems, analysis of the curves and slopes of road features could allow determining where certain road segments or highway entrances and exits are potentially active at a certain time(s) of day or time range. cannot be navigated by autonomous vehicles at specified levels of safety or robustness. This may allow autonomous vehicles to avoid road segments that are steeply sloping and therefore make it impossible for the vehicle sensor system to "see over the hill" (i.e., be unable to detect traffic in the surrounding environment due to the sensor's limited vertical field of view) presence), and the impossibility of "seeing around the corner" (i.e. the inability to detect the presence of traffic in the surrounding environment due to the sensor's limited horizontal field of view).
具有难以辨认的、被侵蚀的、难以理解的、维护或定位不良的标记、标牌或信号的Having illegible, eroded, incomprehensible, poorly maintained or positioned markings, signage or signals道路特征的位置location of road features
道路网络信息可以包含或经由实时地图绘制服务提供商或其他输入而被增加以包括，关于具有如下的道路区域的位置的信息：难以辨认的、被侵蚀的、难以理解的、或维护或定位不良的车道标记和其他道路标记、标牌或信号。Road network information may contain, or be augmented via a real-time mapping service provider or other input to include, information about locations with road areas that are: illegible, eroded, difficult to understand, or poorly maintained or positioned lane markings and other road markings, signs or signals.
鉴于对自主车辆的传感器系统的检测属性、以及(潜在地)运动规划或决策制定过程的能力的了解，对这种信息的分析可以允许确定某些道路段或高速公路出入口潜在地在一天中的某个(某些)时间处或时间范围内不能由自主车辆在指定的安全水平或稳健水平下导航。这可以允许自主车辆避开(例如)标记不良的道路区域，以考虑车辆无法在具有如下的交通标志或信号的车道、交叉路口内安全地导航：部分被遮挡(例如，通过叶子)或以其他方式难以从公称的行驶车道(多条)中检测。它还可以允许自主车辆避开(例如)具有如下的信号或标牌的道路区域：区域特定的或国家特定的并且不能通过车辆感知过程(多个)可靠地检测到的。Given knowledge of the detection properties of autonomous vehicles' sensor systems, and (potentially) the capabilities of motion planning or decision-making processes, analysis of this information could allow the identification of certain road segments or highway entrances and exits that potentially occur during the day. A certain time(s) or time range that cannot be navigated by an autonomous vehicle at a specified level of safety or robustness. This could allow autonomous vehicles to avoid, for example, poorly marked road areas, considering that the vehicle cannot safely navigate within lanes, intersections with traffic signs or signals that are: partially obscured (e.g., by foliage) or otherwise The mode is difficult to detect from the nominal driving lanes (multiple lanes). It may also allow autonomous vehicles to avoid, for example, road areas that have signals or signage that are region-specific or country-specific and cannot be reliably detected by the vehicle sensing process(es).
具有自主车辆或其他自主车辆的差的先前驾驶性能的道路特征的位置Locations of road features with poor prior drivability of autonomous vehicles or other autonomous vehicles
道路网络信息可以包含、或者经由实时地图绘制服务提供商或另一输入或通过自主车辆车队中的感兴趣的自主车辆或任何其他车辆而被增加以包括，关于如下的道路特征的位置的信息：在其中，潜在地由于高场景交通或行人密度、静止物体的遮挡、交通路口复杂性、或其他因素，感兴趣的自主车辆或另一自主车辆已经经历危险、劣化、不安全、或以其他方式的不期望的驾驶性能。可以在地图数据库中“标出”车辆性能差的区域的标识，并且当经标出的事件的数量超过指定的阈值时将该区域标记为避开。这可以允许自主车辆避开车辆或其他车辆已经经历导航困难的道路特征。Road network information may contain, or be augmented via a real-time mapping service provider or another input or by an autonomous vehicle of interest or any other vehicle in a fleet of autonomous vehicles, to include, information regarding the location of road features such as: in which the autonomous vehicle of interest or another autonomous vehicle has experienced hazards, degradation, unsafety, or otherwise, potentially due to high scene traffic or pedestrian density, occlusion by stationary objects, intersection complexity, or other factors Undesirable driving performance. Identification of areas of poor vehicle performance may be "marked" in the map database and marked for avoidance when the number of marked events exceeds a specified threshold. This can allow autonomous vehicles to avoid road features where vehicles or other vehicles already experience navigation difficulties.
具有模型自主车辆的差的先前模拟性能的道路特征的位置Location of road features with poor previous simulation performance of model autonomous vehicles
道路网络信息可以包含或者被增加以包括，关于如下的道路区域的位置的信息：在其中，在模拟环境中已经观察到感兴趣的自主车辆的模型潜在地由于场景交通或行人密度、静态物体的遮挡、交通路口的复杂性、或其他因素，而经历危险的、劣化的、不安全的或者以其他方式的不期望的驾驶性能。可以在地图数据库中“标出”车辆性能差的区域的标识，并标记该区域以供避开。这可以允许自主车辆避开如下的道路区域：在其中，车辆的模型在模拟环境中已经经历难以安全地导航，从而表明实验车辆可能面临现实世界环境中的导航挑战。Road network information may contain, or be augmented to include, information about the location of road areas in which models of autonomous vehicles of interest have been observed in the simulation environment, potentially due to scene traffic or pedestrian density, static objects, etc. occlusion, traffic intersection complexity, or other factors, and experience hazardous, degraded, unsafe, or otherwise undesirable drivability. Areas of poor vehicle performance can be "highlighted" in a map database and marked for avoidance. This could allow autonomous vehicles to avoid areas of the road where models of the vehicle have experienced difficulty safely navigating in simulated environments, demonstrating that experimental vehicles may face navigation challenges in real-world environments.
可能在恶劣天气中呈现物理导航挑战的道路特征的位置Locations of road features that may present physical navigation challenges in inclement weather
道路网络信息可以包含、或允许通过单独的过程来计算、或经由实时地图绘制服务提供商或另一输入而被增加以包括与可能在恶劣天气中或在指定的环境状况下呈现导航挑战的道路特征的位置有关的信息。Road network information may be included, or allowed to be calculated by a separate process, or augmented via a real-time mapping service provider or another input to include roads related to roads that may present navigation challenges in inclement weather or under specified environmental conditions. Information about the location of features.
鉴于对自主车辆的传感器系统的检测属性的了解、以及对车辆的运动控制过程的性能特性的了解，对这种信息的分析可以允许确定某些道路段或高速公路出入口潜在地在一天中的某个(某些)时间处或时间范围内不能由自主车辆在指定的安全水平或稳健水平下导航。这可以允许自主车辆避开(例如)包含道路倾斜或弯曲的道路段，当被冰、雪或冻雨覆盖时，不可能安全地导航这些道路段。Given the knowledge of the detection properties of the sensor systems of autonomous vehicles, as well as the knowledge of the performance characteristics of the vehicle's motion control processes, analysis of this information can allow the determination of certain road segments or highway entrances and exits that are potentially vulnerable to changes in the vehicle's motion at certain times of the day. A (certain) time or time range that cannot be navigated by an autonomous vehicle at a specified level of safety or robustness. This could allow autonomous vehicles to avoid, for example, road segments that contain slopes or curves in the road that would be impossible to navigate safely when covered with ice, snow, or freezing rain.
可能导致已知的车辆故障或故障状况的道路特征的位置The location of roadway features that could cause known vehicle malfunctions or malfunction conditions
道路网络信息可以包含、或允许通过单独的过程来计算、或经由实时地图绘制服务提供商或另一输入而被增加以包括与可在各种传感器或软件过程中导致已知车辆故障或故障状况的道路特征的位置有关的信息。Road network information may be included, or allowed to be calculated by a separate process, or augmented via a real-time mapping service provider or another input to include information related to known vehicle malfunctions or malfunction conditions that may result in various sensors or software processes. Information about the location of road features.
鉴于对自主车辆的传感器系统的检测属性的了解、以及对车辆的运动控制过程的性能特性的了解，对这种信息的分析可以允许确定某些道路段或高速公路出入口潜在地在一天中的某个(某些)时间处或时间范围内不能由自主车辆在指定的安全水平或稳健水平下导航。这可以允许自主车辆避开(例如)可能引起来自雷达传感器的错误读数的特定类型的金属桥或立交桥、可能阻挡GPS信号并因此导致差的车辆定位性能的某些隧道、以及可能不能提供可由激光雷达传感器检测到的垂直特征并可因此导致差的车辆定位性能的某些极其平坦的道路区域。Given the knowledge of the detection properties of the sensor systems of autonomous vehicles, as well as the knowledge of the performance characteristics of the vehicle's motion control processes, analysis of this information can allow the determination of certain road segments or highway entrances and exits that are potentially vulnerable to changes in the vehicle's motion at certain times of the day. A (certain) time or time range that cannot be navigated by an autonomous vehicle at a specified level of safety or robustness. This could allow autonomous vehicles to avoid, for example, certain types of metal bridges or overpasses that may cause false readings from radar sensors, certain tunnels that may block GPS signals and therefore result in poor vehicle positioning performance, and may not provide the information available from lasers. Radar sensors detect certain extremely flat road areas as vertical features and can therefore lead to poor vehicle localization performance.
当被冰、雪或冻雨覆盖时不可能安全地导航包含道路倾斜或弯曲的道路段。It is impossible to safely navigate sections of road that contain slopes or curves in the road when covered with ice, snow or freezing rain.
道路网络信息可以包含、或允许通过单独的过程来计算、或通过实时地图绘制服务提供商或另一源而被增加以包括与可能在恶劣天气中或在指定的环境状况下呈现导航挑战的道路特征的位置有关的信息。Road network information may be included, or allowed to be calculated by a separate process, or augmented by a real-time mapping service provider or another source to include roads related to roads that may present navigational challenges in inclement weather or under specified environmental conditions. Information about the location of features.
鉴于对自主车辆的传感器系统的检测属性的了解、以及对车辆的运动控制过程的性能特性的了解，对这种信息的分析可以允许确定某些道路段或高速公路出入口潜在地在一天中的某个(某些)时间处或时间范围内不能由自主车辆在指定的安全水平或稳健水平下导航。这可以允许自主车辆避开(例如)包含道路倾斜或弯曲的道路段，当被冰或冻雨覆盖时，不可能安全地导航这些道路段。Given the knowledge of the detection properties of the sensor systems of autonomous vehicles, as well as the knowledge of the performance characteristics of the vehicle's motion control processes, analysis of this information can allow the determination of certain road segments or highway entrances and exits that are potentially vulnerable to changes in the vehicle's motion at certain times of the day. A (certain) time or time range that cannot be navigated by an autonomous vehicle at a specified level of safety or robustness. This could allow autonomous vehicles to avoid, for example, road segments that contain road slopes or curves that would be impossible to navigate safely when covered with ice or freezing rain.
除了标识不能由自主车辆安全地导航的特定道路段之外，执行相反的操作也是可能的：基于对如以上所描述的相关信息源的分析，来标识能够由自主车辆安全地导航的特定道路段。例如，基于对车辆传感器和软件过程的已知性能特性以及关于道路特征的给定信息的分析，确定给定的道路段是否可以由自主车辆安全且稳健地导航是可能的。In addition to identifying specific road segments that cannot be safely navigated by autonomous vehicles, it is also possible to do the opposite: identify specific road segments that can be safely navigated by autonomous vehicles based on analysis of relevant information sources as described above . For example, it is possible to determine whether a given road segment can be safely and robustly navigated by an autonomous vehicle based on an analysis of the known performance characteristics of the vehicle's sensors and software processes and given information about the road characteristics.
这种分析对于编译将由其他产品或过程使用的地图数据产品或数据的馈送、描述自主车辆的“经验证的自主驾驶路线”将是有用的。在一些实施方式中，数据产品或数据馈送可以描述“不安全的自主驾驶路线”。该数据可以用作作为道路网络信息的部分来被维护的道路段的属性之一。在某些情况下，对道路段和路线的验证(或对无法安全或稳健地行驶的确定)可以基于自主车辆在诸如街道之类的道路特征的水平下或在给定道路特征内的车道水平下的成功的实验行驶(或模拟行驶)。当确定自我车辆的当前位置和目标位置之间的最佳路线时，选路算法可以通过仅考虑经验证的自主驾驶路线来使用这种信息。这种最佳路线可能试图仅包括被认为是“经验证的自主驾驶路线”的道路段，或者它可能试图包括经验证的和未经验证的驾驶路线的组合，其中该组合由考虑各种因素的优化过程确定，所述各种因素诸如是行驶距离、预期行驶时间、以及道路段是经验证的还是未经验证的等因素。通常，路线算法可以仅探索已知具有超过可行性阈值的可行性状态的候选路线，例如，以允许足够稳健或足够安全的行驶或足够稳健且足够安全的行驶。This analysis would be useful in compiling map data products or feeds of data that would be used by other products or processes, describing "validated autonomous driving routes" for autonomous vehicles. In some implementations, the data product or data feed may describe "unsafe autonomous driving routes." This data may be used as one of the attributes of road segments maintained as part of the road network information. In some cases, verification of road segments and routes (or determination of inability to travel safely or robustly) may be based on the autonomous vehicle operating at the level of a road feature such as a street or at the lane level within a given road feature. A successful experimental drive (or simulated drive) under Routing algorithms can use this information by considering only verified autonomous driving routes when determining the best route between the ego vehicle's current location and a target location. This optimal route may attempt to include only road segments that are considered "verified autonomous driving routes," or it may attempt to include a combination of verified and unverified driving routes, where the combination is determined by taking into account various factors The optimization process determines factors such as distance traveled, expected travel time, and whether the road segment is verified or unverified. Typically, a routing algorithm may only explore candidate routes that are known to have a feasibility status that exceeds a feasibility threshold, for example, to allow for a sufficiently robust or sufficiently safe journey or a sufficiently robust and sufficiently safe journey.
在某些实例中，这种信息可用于城市规划目的，以使用户(即，道路网络的人类规划者或自动化道路网络规划软件过程)能够避免设计可能对自主车辆提出导航挑战的道路段或交叉路口在这种使用情况下，本文所描述的分析方法将用于道路设计软件工具或过程的背景中。In some instances, this information may be used for urban planning purposes to enable users (i.e., human planners of road networks or automated road network planning software processes) to avoid designing road segments or intersections that may present navigational challenges for autonomous vehicles. Intersection In this use case, the analysis method described in this article will be used in the context of a road design software tool or process.
这种道路设计软件工具或过程将允许用户使用各种可能的输入设备和用户接口来指定或设计道路段、道路网络、交叉路口、公路、或其他道路特征。当用户采样道路设计软件工具来指定或设计道路段、道路网络、交叉路口、公路、或其他道路特征时，软件过程(即，“可行性状态过程”)将分析多个潜在连接的道路段(例如，高速公路(freeway)或交叉路口)中的道路段或区域的可行性状态。可行性状态过程还可以分析路线的可行性状态。基于以上描述的分析方法来确定可行性状态。Such a road design software tool or process would allow a user to specify or design road segments, road networks, intersections, highways, or other road features using a variety of possible input devices and user interfaces. When a user samples a road design software tool to specify or design a road segment, road network, intersection, highway, or other road feature, the software process (i.e., the "feasibility state process") analyzes multiple potentially connected road segments ( For example, the feasibility status of a road segment or area in a freeway or intersection. The feasibility status process can also analyze the feasibility status of a route. The feasibility status is determined based on the analysis method described above.
可行性状态过程的输出可以是可行性状态评估，即，以二元指定表示对道路段、道路网络、交叉路口、公路、或其他道路特征或路线的可行性的评估(例如，“可行”或“不可行”)，或者可以采取量化可行性的连续数字或语义度量的形式。可行性状态评估可以包括对道路段、道路网络、交叉路口、公路或其他道路特征或路线的安全性或稳健性的独立评估，每个评估以二元指定或以量化安全性或稳健性的连续数字或语义度量的形式表示。可行性状态过程的输出可以包括基于可行性状态评估的值向用户发出的警告。The output of the feasibility status process may be a feasibility status assessment, that is, an evaluation of the feasibility of a road segment, road network, intersection, highway, or other road feature or route expressed as a binary designation (e.g., "feasible" or "not feasible"), or can take the form of a continuous numerical or semantic measure that quantifies feasibility. A feasibility status assessment may include an independent assessment of the safety or soundness of a road segment, road network, intersection, highway, or other road feature or route, with each assessment specified binary or on a continuum that quantifies safety or soundness. A formal representation of a numerical or semantic measure. Output from the viability status process may include warnings to users based on the value of the feasibility status evaluation.
根据可行性状态评估的值，可以自动删除由用户设计的道路段、道路网络、交叉路口、公路或其他道路特征。根据可行性状态评估的值，可以以改进可行性状态评估的方式自动修改道路段、道路网络、交叉路口、公路或其他道路特征。User-designed road segments, road networks, intersections, highways, or other road features can be automatically deleted based on the value of the feasibility status assessment. Depending on the value of the feasibility status assessment, road segments, road networks, intersections, highways, or other road features may be automatically modified in a manner that improves the feasibility status assessment.
以这种方式，道路设计工具或过程可能能够在用户设计危险道路段、交叉路口、或路线时警告用户，并由此阻止这种道路段、交叉路口或路线的构造，并且还潜在地建议对该道路段、交叉路口或路线进行改进的设计In this manner, a road design tool or process may be able to warn the user when designing dangerous road segments, intersections, or routes, and thereby prevent the construction of such road segments, intersections, or routes, and also potentially suggest changes to Improved design of the road section, intersection or route
我们有时使用短语“可行性状态”来广泛地包括例如路线或道路特征或路线段对于自主车辆的行驶的适合性水平的任何确定或指示，所述适合性水平例如，是否不安全、不安全的程度，是否安全、安全的程度，是否可以稳健地行驶、以及稳健性程度，是否有效，以及其他类似的解释。We sometimes use the phrase "feasibility status" broadly to include, for example, any determination or indication of the suitability level of a route or road feature or route segment for travel by autonomous vehicles, e.g., whether it is unsafe, unsafe Degree, whether it is safe, whether it is safe, whether it can drive stably, and the degree of robustness, whether it is effective, and other similar explanations.
其他实施方式也在下述权利要求书的范围内。Other implementations are within the scope of the following claims.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US15/182,360 | 2016-06-14 | ||
| US15/182,313US20170356750A1 (en) | 2016-06-14 | 2016-06-14 | Route Planning for an Autonomous Vehicle |
| US15/182,313 | 2016-06-14 | ||
| US15/182,400US10309792B2 (en) | 2016-06-14 | 2016-06-14 | Route planning for an autonomous vehicle |
| US15/182,365US20170356748A1 (en) | 2016-06-14 | 2016-06-14 | Route Planning for an Autonomous Vehicle |
| US15/182,281US11092446B2 (en) | 2016-06-14 | 2016-06-14 | Route planning for an autonomous vehicle |
| US15/182,360US10126136B2 (en) | 2016-06-14 | 2016-06-14 | Route planning for an autonomous vehicle |
| US15/182,365 | 2016-06-14 | ||
| US15/182,281 | 2016-06-14 | ||
| US15/182,400 | 2016-06-14 | ||
| PCT/US2017/037294WO2017218563A1 (en) | 2016-06-14 | 2017-06-13 | Route planning for an autonomous vehicle |
| Publication Number | Publication Date |
|---|---|
| CN109641589A CN109641589A (en) | 2019-04-16 |
| CN109641589Btrue CN109641589B (en) | 2023-10-13 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201780049995.2AActiveCN109641589B (en) | 2016-06-14 | 2017-06-13 | Route planning for autonomous vehicles |
| Country | Link |
|---|---|
| EP (1) | EP3468850A4 (en) |
| CN (1) | CN109641589B (en) |
| WO (1) | WO2017218563A1 (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10126136B2 (en) | 2016-06-14 | 2018-11-13 | nuTonomy Inc. | Route planning for an autonomous vehicle |
| US11092446B2 (en) | 2016-06-14 | 2021-08-17 | Motional Ad Llc | Route planning for an autonomous vehicle |
| US10309792B2 (en) | 2016-06-14 | 2019-06-04 | nuTonomy Inc. | Route planning for an autonomous vehicle |
| US10829116B2 (en) | 2016-07-01 | 2020-11-10 | nuTonomy Inc. | Affecting functions of a vehicle based on function-related information about its environment |
| US10857994B2 (en) | 2016-10-20 | 2020-12-08 | Motional Ad Llc | Identifying a stopping place for an autonomous vehicle |
| US10473470B2 (en) | 2016-10-20 | 2019-11-12 | nuTonomy Inc. | Identifying a stopping place for an autonomous vehicle |
| US10681513B2 (en) | 2016-10-20 | 2020-06-09 | nuTonomy Inc. | Identifying a stopping place for an autonomous vehicle |
| US10331129B2 (en) | 2016-10-20 | 2019-06-25 | nuTonomy Inc. | Identifying a stopping place for an autonomous vehicle |
| US11073405B2 (en) | 2018-06-29 | 2021-07-27 | International Business Machines Corporation | Comparative priority and target destination based lane assignment of autonomous vehicles |
| US11034361B2 (en) | 2018-11-28 | 2021-06-15 | International Business Machines Corporation | Route determination for switching between autonomous and manual driving modes |
| US11131554B2 (en) | 2018-12-26 | 2021-09-28 | Beijing Voyager Technology Co., Ltd. | Systems and methods for vehicle telemetry |
| JP2020104547A (en)* | 2018-12-26 | 2020-07-09 | 株式会社日立製作所 | External sensor failure detection device and external sensor failure detection method |
| CN113748316B (en)* | 2018-12-26 | 2024-01-02 | 北京航迹科技有限公司 | System and method for vehicle telemetry |
| US11287270B2 (en) | 2018-12-26 | 2022-03-29 | Beijing Voyager Technology Co., Ltd. | Systems and methods for safe route planning for a vehicle |
| GB201912145D0 (en)* | 2019-08-23 | 2019-10-09 | Five Ai Ltd | Performance testing for robotic systems |
| DE102019127541B3 (en)* | 2019-10-14 | 2021-01-14 | Audi Ag | Method for assisted or at least partially automated driving of a motor vehicle |
| CN111337043B (en)* | 2020-03-17 | 2022-08-02 | 北京嘀嘀无限科技发展有限公司 | Path planning method and device, storage medium and electronic equipment |
| US11702111B2 (en)* | 2020-08-19 | 2023-07-18 | Here Global B.V. | Method and apparatus for estimating object reliability |
| CN112598916B (en)* | 2020-12-07 | 2022-03-29 | 腾讯科技（深圳）有限公司 | Navigation reminding method and device, electronic equipment and storage medium |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014139821A1 (en)* | 2013-03-15 | 2014-09-18 | Volkswagen Aktiengesellschaft | Automatic driving route planning application |
| CN104133473A (en)* | 2008-10-24 | 2014-11-05 | 格瑞股份公司 | Control method of autonomously driven vehicle |
| US9188985B1 (en)* | 2012-09-28 | 2015-11-17 | Google Inc. | Suggesting a route based on desired amount of driver interaction |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9373149B2 (en)* | 2006-03-17 | 2016-06-21 | Fatdoor, Inc. | Autonomous neighborhood vehicle commerce network and community |
| US8606506B2 (en)* | 2006-07-26 | 2013-12-10 | General Motors Llc | Route-matching method for use with vehicle navigation systems |
| AU2012243484B2 (en)* | 2011-04-11 | 2014-10-30 | Crown Equipment Corporation | Method and apparatus for efficient scheduling for multiple automated non-holonomic vehicles using a coordinated path planner |
| CN102914312A (en) | 2011-08-01 | 2013-02-06 | 环达电脑(上海)有限公司 | Navigation device having three-dimensional gravity sensor and navigation method thereof |
| US8874360B2 (en)* | 2012-03-09 | 2014-10-28 | Proxy Technologies Inc. | Autonomous vehicle and method for coordinating the paths of multiple autonomous vehicles |
| US9110196B2 (en)* | 2012-09-20 | 2015-08-18 | Google, Inc. | Detecting road weather conditions |
| US20150161894A1 (en)* | 2013-12-05 | 2015-06-11 | Elwha Llc | Systems and methods for reporting characteristics of automatic-driving software |
| US9165477B2 (en)* | 2013-12-06 | 2015-10-20 | Vehicle Data Science Corporation | Systems and methods for building road models, driver models, and vehicle models and making predictions therefrom |
| EP2916190B1 (en)* | 2014-03-04 | 2019-05-08 | Volvo Car Corporation | Apparatus and method for prediction of time available for autonomous driving, in a vehicle having autonomous driving cap |
| US10534370B2 (en)* | 2014-04-04 | 2020-01-14 | Signify Holding B.V. | System and methods to support autonomous vehicles via environmental perception and sensor calibration and verification |
| US9457807B2 (en)* | 2014-06-05 | 2016-10-04 | GM Global Technology Operations LLC | Unified motion planning algorithm for autonomous driving vehicle in obstacle avoidance maneuver |
| US9428187B2 (en)* | 2014-06-05 | 2016-08-30 | GM Global Technology Operations LLC | Lane change path planning algorithm for autonomous driving vehicle |
| FR3022340B1 (en)* | 2014-06-16 | 2016-07-15 | Thales Sa | METHOD AND DEVICE FOR DETERMINING AN AIRCRAFT CONTROL INSTRUCTION, COMPUTER PROGRAM PRODUCT AND ASSOCIATED AIRCRAFT |
| KR20160013713A (en)* | 2014-07-28 | 2016-02-05 | 현대자동차주식회사 | Global path generation apparatus for autonomous vehicle and method thereof |
| JP6591737B2 (en) | 2014-08-25 | 2019-10-16 | クラリオン株式会社 | Automatic operation control device |
| KR101664582B1 (en)* | 2014-11-12 | 2016-10-10 | 현대자동차주식회사 | Path Planning Apparatus and Method for Autonomous Vehicle |
| KR101877553B1 (en)* | 2014-11-14 | 2018-07-11 | 한국전자통신연구원 | System for autonomous driving, method for driving car using the same |
| JP6156333B2 (en)* | 2014-11-19 | 2017-07-05 | トヨタ自動車株式会社 | Automated driving vehicle system |
| US9534910B2 (en)* | 2014-12-09 | 2017-01-03 | Toyota Motor Engineering & Manufacturing North America, Inc. | Autonomous vehicle detection of and response to yield scenarios |
| US9528838B2 (en)* | 2014-12-09 | 2016-12-27 | Toyota Motor Engineering & Manufacturing North America, Inc. | Autonomous vehicle detection of and response to intersection priority |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104133473A (en)* | 2008-10-24 | 2014-11-05 | 格瑞股份公司 | Control method of autonomously driven vehicle |
| US9188985B1 (en)* | 2012-09-28 | 2015-11-17 | Google Inc. | Suggesting a route based on desired amount of driver interaction |
| WO2014139821A1 (en)* | 2013-03-15 | 2014-09-18 | Volkswagen Aktiengesellschaft | Automatic driving route planning application |
| Publication number | Publication date |
|---|---|
| EP3468850A1 (en) | 2019-04-17 |
| CN109641589A (en) | 2019-04-16 |
| EP3468850A4 (en) | 2019-07-24 |
| WO2017218563A1 (en) | 2017-12-21 |
| Publication | Publication Date | Title |
|---|---|---|
| CN109641589B (en) | Route planning for autonomous vehicles | |
| US11022449B2 (en) | Route planning for an autonomous vehicle | |
| US11092446B2 (en) | Route planning for an autonomous vehicle | |
| US10126136B2 (en) | Route planning for an autonomous vehicle | |
| US20170356748A1 (en) | Route Planning for an Autonomous Vehicle | |
| US20170356750A1 (en) | Route Planning for an Autonomous Vehicle | |
| AU2024201126B2 (en) | Systems and methods for anonymizing navigation information | |
| US11685360B2 (en) | Planning for unknown objects by an autonomous vehicle | |
| US20210316751A1 (en) | Systems and methods for autonomous vehicle navigation | |
| US10860019B2 (en) | Planning autonomous motion | |
| US20210406559A1 (en) | Systems and methods for effecting map layer updates based on collected sensor data | |
| US10281920B2 (en) | Planning for unknown objects by an autonomous vehicle | |
| US10234864B2 (en) | Planning for unknown objects by an autonomous vehicle | |
| US12379226B2 (en) | Generating scouting objectives | |
| US12422273B2 (en) | Handling unmapped speed limit signs | |
| CN113692373A (en) | Retention and range analysis for autonomous vehicle services | |
| CN116745187A (en) | Method and system for predicting the trajectory of an uncertain road user by semantic segmentation of the boundary of a travelable region | |
| CN114830202A (en) | Planning for unknown objects by autonomous vehicles | |
| EP3454269A1 (en) | Planning autonomous motion | |
| US20240028035A1 (en) | Planning autonomous motion | |
| CN118189995A (en) | Method and system for handling obstruction in autonomous vehicle operation | |
| JP2024014736A (en) | System and method for determining and providing parking lot entrance characteristics | |
| US12351197B2 (en) | System, method, and computer program product for data-driven optimization of onboard data collection | |
| US20230229826A1 (en) | Method for assigning a lane relationship between an autonomous vehicle and other actors near an intersection |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information | Address after:Massachusetts, USA Applicant after:Dynamic ad Ltd. Address before:Massachusetts, USA Applicant before:NUTONOMY Inc. | |
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right | Effective date of registration:20201231 Address after:Massachusetts, USA Applicant after:Motional AD LLC Address before:Massachusetts, USA Applicant before:Dynamic ad Ltd. | |
| GR01 | Patent grant | ||
| GR01 | Patent grant |