Disclosure of Invention
The embodiment of the application provides a path planning method, a path planning device, path planning equipment and a storage medium, which are used for improving the safety and the comfort in the running process of a vehicle.
In a first aspect, an embodiment of the present application provides a path planning method, including:
Acquiring first driving information of a first vehicle and second driving information of at least one second vehicle driving around the first vehicle;
Determining a driving strategy of the first vehicle based on the first driving information and each second driving information;
And determining a plurality of path control points based on the first driving information and the current position of the at least one second vehicle under the condition that the driving strategy is a lane changing strategy or an obstacle avoidance strategy, wherein one path control point is positioned in the advancing direction of the first vehicle so that a target track path generated based on the plurality of path control points is tangential to the advancing direction of the first vehicle.
Optionally, the determining a plurality of path control points based on the first driving information and the current position of the at least one second vehicle includes:
Determining a plurality of path control points based on the current position of the first vehicle, the current travel speed, and the current position of the at least one second vehicle, if the travel strategy is a lane change strategy;
And determining a plurality of path control points based on the current position and the current running speed of the first vehicle under the condition that the running strategy is an obstacle avoidance strategy.
Optionally, the determining a plurality of path control points based on the current position of the first vehicle, the current running speed and the current position of the at least one second vehicle includes:
Determining two path control points based on the current position of the first vehicle, wherein a first path control point is a start point of the target track path, a second path control point is located in the advancing direction of the first vehicle so that the target track path is tangential to the advancing direction of the first vehicle, and
Determining two path control points based on the current position of the at least one second vehicle, wherein a third path control point and a fourth path control point are used for ensuring that the target track path does not overlap with the current track path of the at least one second vehicle, and
And determining two path control points based on the current running speed of the first vehicle and the safe lane change time, wherein a fifth path control point is used for ensuring that the target track path and the current track path of the at least one second vehicle are not overlapped, and a sixth path control point is the end point of the target track path.
Optionally, the determining two path control points based on the position points of the at least one second vehicle includes:
The second vehicle running in front of the current running lane is taken as a starting point, the safe lane changing distance is displaced backwards along the central line of the current running lane, and the current position of the third path control point is determined;
A second vehicle running in front of the target changed lane is taken as a starting point, the safe lane changing distance is displaced backwards along the central line of the target changed lane, one boundary point is determined, the second vehicle running behind the target changed lane is taken as a starting point, the safe lane changing distance is displaced forwards along the central line of the target changed lane, and the other boundary point is determined;
and determining a candidate channel change area based on the two boundary points, and determining the current position of the fourth path control point from the candidate channel change area.
Optionally, the determining a plurality of path control points based on the current position and the current running speed of the first vehicle includes:
determining two path control points based on the current position of the first vehicle, wherein a first path control point is the starting point of the target track path, and a second path control point is positioned in the advancing direction of the first vehicle to ensure that the generated target track path is tangential to the advancing direction of the first vehicle, and
And determining four path control points based on the current running speed of the first vehicle, wherein a sixth path control point is an end point of the target track path, and the other three path control points are used for ensuring that the target track path is not overlapped with the current track path of the at least one second vehicle.
Optionally, the determining four path control points based on the current running speed of the first vehicle includes:
determining a longitudinal cut-in distance of the first vehicle based on the current running speed of the first vehicle and a safe cut-in time, and determining the sixth path control point on the current running lane based on the obtained longitudinal cut-in distance;
The sixth path control point is taken as a starting point, the safe overtaking distance is displaced backwards along the advancing direction of the center line of the current driving lane, and the fifth path control point is determined;
the third path control point is determined based on the current position of the second path control point, and the fourth path control point is determined based on the current position of the fifth path control point.
Optionally, the determining the third path control point based on the current position of the second path control point, and the determining the fourth path control point based on the current position of the fifth path control point include:
Determining the third path control point by vertically shifting the safe overtaking distance along the perpendicular direction between the center line of the current driving lane and the center line of the target changed lane by taking the second path control point as a starting point, and
And taking the current position of the fifth path control point as a starting point, vertically shifting a safe overtaking distance along the perpendicular line direction between the central line of the current driving lane and the central line of the target changed lane, and determining the fourth path control point.
In a second aspect, an embodiment of the present application further provides a path planning apparatus, including:
The information acquisition module is used for acquiring first running information of a first vehicle and second running information of at least one second vehicle running around the first vehicle;
the path planning module is used for determining a driving strategy of the first vehicle based on the first driving information and the second driving information;
And determining a plurality of path control points based on the first driving information and the current position of the at least one second vehicle under the condition that the driving strategy comprises a lane change strategy or an obstacle avoidance strategy, wherein one path control point is positioned in the heading direction advancing direction of the first vehicle so as to ensure that a target track path generated based on the plurality of path control points is tangential to the heading direction advancing direction of the first vehicle.
Optionally, the path planning module is configured to:
Determining a plurality of path control points based on the current position of the first vehicle, the current travel speed, and the current position of the at least one second vehicle, if the travel strategy is a lane change strategy;
And determining a plurality of path control points based on the current position and the current running speed of the first vehicle under the condition that the running strategy is an obstacle avoidance strategy.
Optionally, the path planning module is configured to:
Determining two path control points based on the current position of the first vehicle, wherein a first path control point is a start point of the target track path, a second path control point is located in the advancing direction of the first vehicle so that the target track path is tangential to the advancing direction of the first vehicle, and
Determining two path control points based on the current position of the at least one second vehicle, wherein a third path control point and a fourth path control point are used for ensuring that the target track path does not overlap with the current track path of the at least one second vehicle, and
And determining two path control points based on the current running speed of the first vehicle and the safe lane change time, wherein a fifth path control point is used for ensuring that the target track path and the current track path of the at least one second vehicle are not overlapped, and a sixth path control point is the end point of the target track path.
Optionally, the path planning module is configured to:
The second vehicle running in front of the current running lane is taken as a starting point, the safe lane changing distance is displaced backwards along the central line of the current running lane, and the current position of the third path control point is determined;
A second vehicle running in front of the target changed lane is taken as a starting point, the safe lane changing distance is displaced backwards along the central line of the target changed lane, one boundary point is determined, the second vehicle running behind the target changed lane is taken as a starting point, the safe lane changing distance is displaced forwards along the central line of the target changed lane, and the other boundary point is determined;
and determining a candidate channel change area based on the two boundary points, and determining the current position of the fourth path control point from the candidate channel change area.
Optionally, the path planning module is configured to:
determining two path control points based on the current position of the first vehicle, wherein a first path control point is the starting point of the target track path, and a second path control point is positioned in the advancing direction of the first vehicle to ensure that the generated target track path is tangential to the advancing direction of the first vehicle, and
And determining four path control points based on the current running speed of the first vehicle, wherein a sixth path control point is an end point of the target track path, and the other three path control points are used for ensuring that the target track path is not overlapped with the current track path of the at least one second vehicle.
Optionally, the path planning module is configured to:
determining a longitudinal cut-in distance of the first vehicle based on the current running speed of the first vehicle and a safe cut-in time, and determining the sixth path control point on the current running lane based on the obtained longitudinal cut-in distance;
The sixth path control point is taken as a starting point, the safe overtaking distance is displaced backwards along the advancing direction of the center line of the current driving lane, and the fifth path control point is determined;
the third path control point is determined based on the current position of the second path control point, and the fourth path control point is determined based on the current position of the fifth path control point.
Optionally, the path planning module is configured to:
Determining the third path control point by vertically shifting the safe overtaking distance along the perpendicular direction between the center line of the current driving lane and the center line of the target changed lane by taking the second path control point as a starting point, and
And taking the current position of the fifth path control point as a starting point, vertically shifting a safe overtaking distance along the perpendicular line direction between the central line of the current driving lane and the central line of the target changed lane, and determining the fourth path control point.
In a third aspect, an embodiment of the present application further provides a path planning apparatus, including a processor and a memory, where the memory stores program code, and when the program code is executed by the processor, causes the processor to execute the steps of any one of the path planning methods described above.
In a fourth aspect, embodiments of the present application also provide a computer readable storage medium comprising program code for causing a path planning apparatus to perform the steps of any one of the path planning methods described above, when the program product is run on the path planning apparatus.
The embodiment of the application provides a path planning method, a device, equipment and a storage medium, wherein the method comprises the steps of obtaining first running information of a first vehicle and second running information of at least one second vehicle running around the first vehicle; and determining a driving strategy of the first vehicle based on the first driving information and the second driving information, wherein when the driving strategy is a lane changing strategy or an obstacle avoidance strategy, a plurality of path control points are determined based on the first driving information and the current position of at least one second vehicle, and one path control point is positioned in the advancing direction of the first vehicle so as to ensure that a target track path generated based on the plurality of path control points is tangential to the advancing direction of the first vehicle.
When the target track path is established for the first vehicle of the automatic driving automobile in the lane changing strategy or the obstacle avoidance strategy, the transverse deviation and the heading deviation of the first vehicle are considered, and the target track path tangential to the advancing direction of the first vehicle is generated, so that the aim of counteracting the heading deviation is fulfilled. Therefore, when the first vehicle runs along the target track path, the steering wheel does not need to be controlled to deflect a larger running angle, the shaking amplitude of the steering wheel is reduced, and the safety and the comfort of the first vehicle are improved.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the technical solutions of the present application, but not all embodiments. Some terms in the embodiments of the present application are explained below to facilitate understanding by those skilled in the art.
1. Lateral deviation the distance between the center point of the rear axle of the automatically driven automobile and the foot of the vertical line, which is perpendicular to the center line of the lane to be changed, is called lateral deviation.
Heading deviation refers to the angular difference between the heading direction of the autonomous car and the tangential direction of the centerline of the current driving lane.
2. Bezier curve is also called Bezier curve or Bezier curve, is a basic tool for computer graphic image modeling, and is one of the most used basic lines for graphic modeling.
The Bezier curve is composed of line segments and nodes, the nodes are draggable fulcra, the line segments are like telescopic rubber bands, and patterns with different shapes are created and edited by controlling the nodes on the curve.
The following briefly describes the design concept of the embodiment of the present application:
The automatic driving automobile detects road obstacles and recognizes road conditions by means of various sensor devices arranged on the automobile body, and then a built-in path planning module is used for generating a target track path matched with the current road conditions. When the automatic driving automobile is in the lane change mode, the process of generating the target track path for the automatic driving automobile is as follows:
And performing polynomial curve fitting on the lateral deviation and the longitudinal lane change distance to obtain a function L=F(s) of the lateral deviation relative to the longitudinal lane change distance, wherein L is the lateral deviation, and s is the longitudinal lane change distance. Discretizing the center line of the target changed lane to obtain a plurality of discrete points, determining the transverse displacement of each discrete point according to the function, and obtaining the target track path shown in fig. 1a based on the transverse displacement of each discrete point.
When the automatic driving automobile has lateral deviation and course deviation in the normal driving process, the conventional path planning method usually only considers the lateral deviation between the automatic driving automobile and the target changed lane when generating the lane changing path or the obstacle avoidance path of the automatic driving automobile, but ignores the course deviation between the automatic driving automobile and the current driving lane, so that the course deviation exists in the target track path shown in fig. 1 b. When the automatic driving automobile runs along the target track path, the steering wheel is controlled to deflect a larger running angle so as to achieve the purpose of correcting course deviation, but the steering wheel is subjected to step jitter caused by the way, and the safety and the comfort of the automatic driving automobile are affected.
In view of this, the embodiment of the application provides a self-path planning method. The method specifically comprises the steps of obtaining first running information of a first vehicle and second running information of at least one second vehicle running around the first vehicle, and determining a running strategy of the first vehicle based on the first running information and the second running information, wherein when the running strategy is a lane change strategy or an obstacle avoidance strategy, a plurality of path control points are determined based on the first running information and the current position of the at least one second vehicle, and one of the path control points is located in the advancing direction of the first vehicle so as to ensure that a target track path generated based on the plurality of path control points is tangential to the advancing direction of the first vehicle.
When the target track path is formulated for the first vehicle in the lane change strategy or the obstacle avoidance strategy, the transverse deviation and the heading deviation of the first vehicle are considered, and the target track path tangential to the advancing direction of the first vehicle is generated, so that the aim of counteracting the heading deviation is fulfilled. Therefore, when the first vehicle runs along the target track path, the steering wheel does not need to be controlled to deflect a larger running angle, the shaking amplitude of the steering wheel is reduced, and the safety and the comfort of the first vehicle are improved.
The embodiments of the present application will be described below with reference to the drawings of the specification, it should be understood that the preferred embodiments described herein are for illustration and explanation of the present application only, and are not intended to limit the present application, and embodiments of the present application and features of the embodiments may be combined with each other without conflict.
As shown in fig. 2, the automatic driving automobile at least comprises an information acquisition module composed of various sensors and a path planning module respectively connected with the steering wheel and the information acquisition module. The present application is not limited herein, as the sensor may be placed inside the autonomous vehicle (e.g., the speed sensor is mounted beside the transmission output shaft for collecting the current running speed of the autonomous vehicle) or the sensor may be placed outside the autonomous vehicle (e.g., the image collecting sensor is mounted around the sun visor of the main driver seat for collecting image information around the autonomous vehicle). The path planning module can be placed in the automatic driving automobile or can be deployed in a server to communicate with the automatic driving automobile through an established communication network.
The servers mentioned herein may be independent physical servers, may be server clusters or distributed systems formed by a plurality of physical servers, and may also be cloud servers that provide cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.
The automatic driving automobile acquires first driving information of the automatic driving automobile and second driving information of at least one second vehicle driving around the automatic driving automobile through various sensors arranged around and in the automobile body, and sends the first driving information and the second driving information to the path planning module.
The path planning module determines a driving strategy of the first vehicle based on the first driving information and the second driving information. And determining a plurality of path control points based on the first driving information and the current position of at least one second vehicle under the condition that the driving strategy is a lane changing strategy or an obstacle avoidance strategy, wherein one path control point is positioned in the advancing direction of the first vehicle so that a target track path generated based on the plurality of path control points is tangential to the advancing direction of the first vehicle. The path planning module sends the generated target track path to a processor of the automatic driving automobile so that the processor controls the steering wheel to run along the target track path.
Referring to the flow chart shown in fig. 3a, a process of generating a target track path for an automatic driving automobile by using the path planning method provided by the embodiment of the application is specifically described.
S301, acquiring first driving information of a first vehicle and second driving information of at least one second vehicle driving around the first vehicle.
First travel information of the first vehicle itself and second travel information of at least one second vehicle traveling around the first vehicle are collected by various sensors disposed inside and around the vehicle body of the first vehicle.
The first traveling information includes, but is not limited to, a current traveling speed, a current position, and a traveling direction of the first vehicle. And the current position and heading of the first vehicle, also referred to as pose information of the first vehicle.
The second travel information includes, but is not limited to, a current travel speed, a current position, and a forward direction of the second vehicle. Likewise, the current position and heading of the second vehicle is also referred to as pose information of the second vehicle.
As shown in fig. 3b, a plurality of vehicles are traveling around the first vehicle, but when the first vehicle performs the lane change strategy or the obstacle avoidance strategy, the degree of influence on whether the first vehicle can normally travel is considered in the vehicle a traveling ahead of the current traveling lane, the vehicle c traveling ahead of the target changed lane, and the vehicle d traveling behind the target changed lane. Therefore, the first vehicle needs to acquire the second traveling information of the vehicles a, c to d.
S302, determining a driving strategy of the first vehicle based on the first driving information and the second driving information.
If only one second vehicle runs around the first vehicle, a running strategy is formulated for the first vehicle based on the first running information of the first vehicle and the second running information of the second vehicle;
If a plurality of second vehicles run around the first vehicle, the road conditions of the current running lane and the target changed lane are comprehensively researched and judged based on the first running information of the first vehicle and the second running information of each second vehicle, and a final running strategy is formulated for the first vehicle.
Taking a first vehicle and a second vehicle traveling in front of the current driving lane as an example, a method for making a driving strategy for the first vehicle is described with reference to a flow chart shown in fig. 3c and a logic diagram shown in fig. 3 d.
S3021, determining a relative distance between the first vehicle and the second vehicle traveling in front of the current traveling lane, a collision time of the two vehicles, and respective current traveling speeds based on the first traveling information and the second traveling information.
The relative distance refers to the absolute value of the difference between the current positions of the two vehicles. And the respective current positions of the two vehicles are obtained from the respective travel information.
As shown in equation 1, the collision time of two vehicles is determined based on the relative distance of the two vehicles and the respective current traveling speeds.
Ttc=s/(v 1-v 0) equation 1;
where ttc represents the time of collision of the two vehicles, s represents the relative distance, v1 represents the current travel speed of the vehicle traveling ahead of the current travel lane, and v0 represents the current travel speed of the vehicle traveling behind the current travel lane.
In this example, the second vehicle travels in front and the first vehicle travels in rear, and therefore, the current travel speed of the second vehicle should be substituted for v1 in equation 1 and the current travel speed of the first vehicle should be substituted for v0 in equation 1.
And S3022, determining that the driving strategy of the first vehicle is a following strategy under the condition that a first decision condition is met, wherein the first decision condition is that the relative distance is smaller than the safe lane change distance or the current driving speed of the second vehicle driving in front of the current driving lane is larger than the current driving speed of the first vehicle.
In case the first decision condition is fulfilled, the following strategy is formulated for the first vehicle for the following reasons:
(1) In the case where the relative distance is smaller than the safe lane change distance (safe_distance_for_change), if a lane change policy is formulated for the first vehicle, the first vehicle may collide with the second vehicle traveling ahead of the current traveling lane during the lane change. Therefore, in order to ensure the safety of the first vehicle, it is not recommended to let the first vehicle execute the lane change strategy.
In the process of avoiding the obstacle overtaking, the first vehicle also needs to keep a certain safe overtaking distance with the second vehicle running in front of the current running lane so as to ensure that the first vehicle smoothly and safely completes overtaking. However, if the relative distance is smaller than the safe lane change distance, the first vehicle may collide with the second vehicle traveling in front of the current driving lane during the obstacle avoidance passing if the obstacle avoidance strategy is formulated for the first vehicle. Therefore, in order to ensure the safety of the first vehicle, it is not recommended to let the first vehicle execute the obstacle avoidance strategy.
(2) If the current running speed of the second vehicle running in front of the current running lane is greater than the current running speed of the first vehicle, the first vehicle cannot complete the overtaking operation if an obstacle avoidance strategy is formulated for the first vehicle. Therefore, it is not recommended to have the first vehicle execute the obstacle avoidance strategy.
In this example, there are only two vehicles on the road, a first vehicle and a second vehicle, and the second vehicle is traveling in front of the first vehicle, then the first vehicle may select a following or lane changing strategy when the current traveling speed of the second vehicle is greater than the current traveling speed of the first vehicle.
However, if there are a plurality of second vehicles around the first vehicle, one of the second vehicles is traveling behind the target lane change, and the current traveling speed of the second vehicle is greater than the current traveling speed of the first vehicle, the first vehicle cannot complete the lane change operation. Therefore, in order to secure the safety of the first vehicle in various complicated road situations, it is not recommended to let the first vehicle execute a lane change strategy.
S3023, judging whether the second vehicle running in front of the current running lane is in a stationary state, if so, executing step 3024, otherwise, jumping to step 3025.
S3024, determining that the driving strategy of the first vehicle is a following strategy when the second vehicle driving in front of the current driving lane is in a static state and does not meet the first decision condition and the second decision condition, and determining that the driving strategy of the first vehicle is an obstacle avoidance strategy when the second vehicle driving in front of the current driving lane is in a static state and does not meet the first decision condition but meets the second decision condition, wherein the second decision condition is that the target lane is changed to be a safe lane.
When the second vehicle running in front of the current driving lane is in a stationary state and the first decision condition and the second decision condition are not satisfied, the following strategy is formulated for the first vehicle for the following reasons:
When the second vehicle running in front of the current running lane is in a stationary state and the first decision condition is not satisfied, the running strategy of the first vehicle is most preferably a lane changing strategy or an obstacle avoidance strategy. However, the second decision condition is not satisfied, and the lane change condition or the overtaking condition is not satisfied, so that the safety of the first vehicle in the lane change or obstacle avoidance process cannot be ensured. In this case, therefore, the travel strategy established for the first vehicle is a following strategy.
When the second vehicle running in front of the current running lane is in a stationary state and does not meet the first decision condition, but meets the second decision condition, the reason for making the obstacle avoidance strategy for the first vehicle is as follows:
When the second vehicle running in front of the current running lane is in a stationary state and the first decision condition is not satisfied, the running strategy of the first vehicle is most preferably a lane changing strategy or an obstacle avoidance strategy. Under the condition that the second decision condition is met, the first vehicle can go beyond the second vehicle in the stationary state in front by executing the obstacle avoidance strategy, and the first vehicle can continue to run forwards. In this case, therefore, the travel strategy established for the first vehicle is an obstacle avoidance strategy.
In the embodiment of the application, when at least one of the following conditions is satisfied, the target changed lane is determined to be a safe lane:
(1) A second vehicle that does not travel on the target changed lane around the first vehicle;
(2) A second vehicle which runs around the first vehicle and is on the target changed lane, wherein the relative distance between the second vehicle and the first vehicle exceeds the safe lane change distance;
(3) The relative distance between the second vehicle which runs around the first vehicle and the first vehicle on the target changed lane exceeds the safe lane change time, and the collision time between the second vehicle which runs around the first vehicle and the first vehicle also exceeds the safe overtaking time (safe_change_ttc).
S3025, determining that the driving strategy of the first vehicle is a following strategy when the second vehicle driving in front of the current driving lane is in a driving state and does not meet the first decision condition and the third decision condition, and determining that the driving strategy of the first vehicle is a lane changing strategy when the second vehicle driving in front of the current driving lane is in a driving state and does not meet the first decision condition but meets the third decision condition, wherein the third decision condition is that the collision time of the two vehicles exceeds the safe overtaking time and the target lane changing is a safe lane.
When the second vehicle running in front of the current driving lane is in a driving state and the first decision condition and the third decision condition are not satisfied, the following strategy is formulated for the first vehicle for the following reasons:
When the second vehicle running in front of the current running lane is in a running state and the first decision condition is not satisfied, the running strategy of the first vehicle is most preferably a lane changing strategy or an obstacle avoidance strategy. However, the third decision condition is not satisfied, and the lane change condition or the overtaking condition is not satisfied, so that the safety of the first vehicle in the lane change or obstacle avoidance process cannot be ensured. In this case, therefore, the travel strategy established for the first vehicle is a following strategy.
And S303, determining a plurality of path control points based on the first driving information and the current position of at least one second vehicle under the condition that the driving strategy is a lane changing strategy or an obstacle avoidance strategy, wherein one path control point is positioned in the advancing direction of the first vehicle so that a target track path generated based on the plurality of path control points is tangential to the advancing direction of the first vehicle.
The embodiment of the application provides a vehicle following strategy, a lane changing strategy and an obstacle avoidance strategy, and the process of generating target track paths of different driving strategies is respectively described below.
As shown in fig. 3e to 3f, when the driving strategy is lane change driving, the process of generating the target track path is as follows:
first, a plurality of path control points are determined based on a current position of a first vehicle, a current travel speed, and a current position of at least one second vehicle.
(1) Two path control points are determined based on the current position of the first vehicle, wherein the first path control point P0 is the start point of the target trajectory path, and the second path control point P1 is located in the advancing direction of the first vehicle so that the target trajectory path is tangential to the advancing direction of the first vehicle.
In the embodiment of the present application, the current position of the first vehicle is determined as the current position of the first path control point P0. And then, taking the first vehicle as a starting point, forward displacing the safety channel distance along the forward direction of the first vehicle, and determining the current position of the second path control point P1.
When the second path control point P1 is located in the forward direction of the first vehicle, it may be ensured that the generated target track path is tangential to the forward direction of the first vehicle, so as to counteract the heading deviation of the first vehicle and reduce the steering wheel shake amplitude.
(2) Two path control points are determined based on the current position of the at least one second vehicle, wherein the third path control point P2 and the fourth path control point P3 are used for ensuring that the target track path does not overlap with the current track path of the at least one second vehicle.
Specifically, the current position of the third path control point P2 is determined by displacing the safe lane change distance backward along the center line of the current travel lane with the second vehicle traveling ahead of the current travel lane as a starting point. Thus, the third path control point P2 is located on the center line of the current driving lane regardless of whether the current driving lane is a straight road or a curve.
A boundary point is determined by displacing the safe lane change distance backward along the center line of the target lane change with the second vehicle traveling in front of the target lane change as a starting point. And taking a second vehicle running behind the target changed lane as a starting point, shifting forward along the central line of the target changed lane by a safe lane changing distance, and determining the other boundary point. And determining a candidate channel change area based on the two boundary points, and determining the current position of the fourth path control point P3 from the candidate channel change area. In this way, the fourth path control point P3 is positioned on the center line of the target lane change.
(3) Two path control points are determined based on the current running speed of the first vehicle and the safe lane change time, wherein the fifth path control point P4 is used for ensuring that the target track path does not overlap with the current track path of at least one second vehicle, and the sixth path control point P5 is the end point of the target track path.
As shown in equation 2, the longitudinal lane change distance of the first vehicle is determined based on the current running speed of the first vehicle and the safe lane change time. And then taking the current position of the first vehicle as a starting point, making a vertical line to the central line of the lane to be changed, taking the foot as a new starting point, and shifting forward by a longitudinal lane changing distance along the advancing direction of the first vehicle to determine the current position of the sixth path control point P5.
Change_distance Lane changing＝v Self-vehicle*change_time Lane changing formula 2;
Wherein change_distance Lane changing represents a longitudinal lane change distance, v Self-vehicle represents a current running speed of the first vehicle, and change_time Lane changing represents a safe lane change time.
And then the sixth path control point P5 is taken as a starting point, the safe lane change distance is shifted backwards along the advancing direction of the center line of the target lane change, and the current position of the fifth path control point P4 is determined.
As shown in fig. 3g, when the target lane change is a straight road, the center line of the target lane change overlaps with the advancing direction of the center line, and therefore, the fifth path control point P4 obtained by displacement along the advancing direction of the center line is fixed on the center line of the target lane change;
When the target lane change is a curve, there is a deviation angle between the center line of the target lane change and the advancing direction of the center line, and therefore, the fifth path control point P4 obtained by displacement along the advancing direction of the center line may not be on the center line of the target lane change.
Next, a target trajectory path tangential to the advancing direction of the first vehicle is generated by performing bezier curve processing on the plurality of path control points.
As shown in equation 3, bezier curve processing is performed on the plurality of path control points to generate a target track path of the first vehicle. Wherein, Pi represents the current position of the ith path control point, Bi,n (t) represents the bezier curve coefficient of the ith path control point when the control variable value is t, P (t) represents the current position of each point distributed on the bezier curve when the control variable value is t, n represents the order of the bezier curve, t represents the control variable of the bezier curve, and a series of position points can be obtained by discretely increasing the control variable t from 0 to 1, and further a discrete bezier curve can be obtained.
And each time a target track path is generated, judging whether a first vehicle collides with a second vehicle running in front of the current running lane when the first vehicle runs along the target track path by using a collision algorithm and other modes. If the two vehicles are judged to collide, the safe lane change distance is increased, and the current positions of the second path control point P1 and the fifth path control point P4 are readjusted based on the adjusted safe lane change distance until the target track path position which cannot collide is generated.
In the collision test, only the reason that whether the first vehicle collides with the second vehicle traveling in front of the current traveling lane is considered is that if the first vehicle collides with the second vehicle traveling in front of the target lane change, a following strategy is initially formulated for the first vehicle, instead of the lane change strategy.
As shown in fig. 3h to 3i, when the driving strategy is obstacle avoidance driving, the process of generating the target track path is as follows:
And then performing Bezier curve processing on the plurality of path control points by using the Bezier curve expression shown in the formula 3 to generate a target track path tangent to the advancing direction of the first vehicle.
The process of determining the plurality of path control points is as follows:
(1) Two path control points are determined based on the current position of the first vehicle, wherein the first path control point P0 is the start point of the target trajectory path, and the second path control point P1 is located in the forward direction of the first vehicle to ensure that the generated target trajectory path is tangential to the forward direction of the first vehicle.
In the embodiment of the present application, the current position of the first vehicle is determined as the current position of the first path control point P0. The current position of the second path control point P1 is then determined based on the current position of the first vehicle and the current position of the second vehicle traveling in front of the current traveling lane.
Specifically, a boundary point is determined by displacing the safe overtaking distance forward in the advancing direction of the first vehicle with the first vehicle as a starting point. Another boundary point is determined by displacing the safe overtaking distance backward along the advancing direction of the center line of the current traveling lane with the current position of the second vehicle traveling ahead of the current traveling lane as a starting point. And determining a candidate obstacle avoidance area based on the two boundary points, and determining the current position of the second path control point P1 from the candidate obstacle avoidance area.
(2) Four path control points are determined based on the current travel speed of the first vehicle, wherein the sixth path control point is the end point of the target track path, and the other three path control points are used for ensuring that the target track path does not overlap with the current track path of the at least one second vehicle.
As shown in equation 3, a longitudinal cut-in distance of the first vehicle is determined based on the current traveling speed of the first vehicle and the safe cut-in time, and a sixth control point P5 is determined on the current traveling lane based on the obtained longitudinal cut-in distance.
Specifically, the current position of the sixth path control point P5 is determined by taking the current position of the first vehicle as a starting point, making a vertical line to the center line of the lane to be changed, and taking the foot drop as a new starting point, and shifting forward by the longitudinal overtaking distance along the advancing direction of the first vehicle.
Change_distance Overtaking vehicle＝v Self-vehicle*change_time Overtaking vehicle formula 3;
Wherein change_distance Overtaking vehicle represents a longitudinal cut-in distance, v Self-vehicle represents a current running speed of the first vehicle, and change_time Overtaking vehicle represents a safe cut-in time.
And then, the sixth path control point P5 is taken as a starting point, the safe overtaking distance is shifted backwards along the advancing direction of the center line of the current driving lane, and the fifth path control point P4 is determined.
The fifth path control point P4 must be on the center line of the current driving lane when the current driving lane is a straight road, and the fifth path control point P4 may not be on the center line of the current driving lane when the current driving lane is a curve.
After the current positions of the second path control point P1 and the fifth path control point P4 are determined, a third path control point P2 is determined based on the current position of the second path control point P1, and a fourth path control point P3 is determined based on the current position of the fifth path control point P4.
Specifically, the second path control point P1 is used as a starting point, the safe overtaking distance is vertically offset along the perpendicular line direction between the center line of the current driving lane and the center line of the target changed lane, and the third path control point P2 is determined. The fourth path control point P3 is determined by vertically shifting the safe overtaking distance along the perpendicular direction between the center line of the current traveling lane and the center line of the target changed lane with the fifth path control point P4 as the starting point.
And each time a target track path is generated, judging whether a first vehicle collides with a second vehicle running in front of the current running lane when the first vehicle runs along the target track path by using a collision algorithm and other modes. If the two vehicles are judged to collide, the safe overtaking distance is increased, and the current positions of the second path control point P1 and the fifth path control point P4 are readjusted based on the adjusted safe overtaking distance until the target track path position which cannot collide is generated. Therefore, the third path control point P2 and the fourth path control point P3 are not necessarily located on the target change lane.
As shown in fig. 3j to 3k, when the driving strategy is the following strategy, the method for generating the target track path is as follows:
If the relative distance between the first vehicle and the second vehicle traveling in front of the current traveling lane does not exceed the safe following distance, the first vehicle proceeds at the current traveling speed of the second vehicle traveling in front of the current traveling lane as shown in equation 4;
If the relative distance is greater than the safe following distance, the first vehicle proceeds at its own target travel speed, wherein the target travel speed of the first vehicle is determined based on the relative distance and a current travel speed of the second vehicle traveling in front of the current travel lane.
Where vtarget denotes a target running speed of the first vehicle, vobj denotes a current running speed of the second vehicle running ahead of the current running lane, s denotes a relative distance between the two vehicles, a denotes a preset deceleration of the first vehicle, and safe_distance_for_following denotes a safe following distance.
And equation 5 shows a calculation equation of the preset safe following distance. Where min_follow_distance represents the shortest following distance of the first vehicle, v Self-vehicle represents the current travel speed of the first vehicle, and followtime represents the following reaction time of the first vehicle.
As shown in fig. 4, in the case that the first vehicle has a heading deviation, the target track path obtained by using polynomial curve fitting also has a heading deviation, and the target track path generated by the embodiment of the application is tangential to the advancing direction of the first vehicle, so that the heading deviation of the first vehicle is counteracted. Therefore, when the first vehicle runs along the target track path, the steering wheel does not need to be controlled to deflect a larger running angle, the shaking amplitude of the steering wheel is reduced, and the safety and the comfort of the first vehicle are improved.
In addition, when the lateral deviation and the current running speed of the automatic driving automobile are fixed values, a plurality of identical target track paths can be generated by using a polynomial curve fitting method, and the method cannot adapt to complex running scenes of the automobile. According to the embodiment of the application, the current positions of the path control points on the five-order Bessel curves can be dynamically adjusted according to the current road conditions of the first vehicle, so that a smoother target track path is generated, the safety and the comfort of the first vehicle are ensured, and the capability of the first vehicle for adapting to complex road conditions is improved.
In various embodiments of the application, where no special description or logic conflict exists, terms and/or descriptions between the various embodiments are consistent and may reference each other, technical features in the various embodiments may be combined to form new embodiments based on their inherent logic relationships.
The term "and/or" in the present application is merely an association relationship describing the association object, indicating that three relationships may exist. For example, A and/or B may mean that A alone, both A and B, and B alone are present. In addition, the term "at least one" in the present application means any one of a plurality or any combination of at least two of a plurality. For example, including at least one of A, B, C may mean including selecting any one or more elements from the set consisting of A, B and C.
The embodiment of the application also provides a path planning device based on the same conception as the embodiment of the method. Referring to the schematic structure shown in fig. 5, the path planning apparatus 500 may include:
an information acquisition module 501, configured to acquire first driving information of a first vehicle and second driving information of at least one second vehicle driving around the first vehicle;
a path planning module 502, configured to determine a driving policy of the first vehicle based on the first driving information and each second driving information;
and determining a plurality of path control points based on the first driving information and the current position of at least one second vehicle under the condition that the driving strategy comprises a lane changing strategy or an obstacle avoidance strategy, wherein one path control point is positioned in the heading direction advancing direction of the first vehicle so as to ensure that a target track path generated based on the plurality of path control points is tangential to the heading direction advancing direction of the first vehicle.
Optionally, the path planning module 502 is configured to:
Determining a plurality of path control points based on the current position of the first vehicle, the current travel speed, and the current position of the at least one second vehicle, if the travel strategy is a lane change strategy;
In the case where the travel strategy is an obstacle avoidance strategy, a plurality of path control points are determined based on the current position and the current travel speed of the first vehicle.
Optionally, the path planning module 502 is configured to:
Determining two path control points based on the current position of the first vehicle, wherein the first path control point is the start point of the target track path, the second path control point is located in the advancing direction of the first vehicle so that the target track path is tangential to the advancing direction of the first vehicle, and
Determining two path control points based on the current position of the at least one second vehicle, wherein the third path control point and the fourth path control point are used for ensuring that the target track path does not overlap with the current track path of the at least one second vehicle, and
And determining two path control points based on the current running speed of the first vehicle and the safe lane change time, wherein a fifth path control point is used for ensuring that the target track path does not overlap with the current track path of at least one second vehicle, and a sixth path control point is the end point of the target track path.
Optionally, the path planning module 502 is configured to:
the second vehicle running in front of the current running lane is taken as a starting point, the safe lane changing distance is displaced backwards along the center line of the current running lane, and the current position of the third path control point is determined;
A second vehicle running in front of the target changed lane is taken as a starting point, the safe lane changing distance is displaced backwards along the central line of the target changed lane, one boundary point is determined, the safe lane changing distance is displaced forwards along the central line of the target changed lane, and the other boundary point is determined;
and determining a candidate channel change area based on the two boundary points, and determining the current position of a fourth path control point from the candidate channel change area.
Optionally, the path planning module 502 is configured to:
Determining two path control points based on the current position of the first vehicle, wherein the first path control point is the start point of the target track path, the second path control point is located in the advancing direction of the first vehicle to ensure that the generated target track path is tangential to the advancing direction of the first vehicle, and
Four path control points are determined based on the current travel speed of the first vehicle, wherein the sixth path control point is the end point of the target track path, and the other three path control points are used for ensuring that the target track path does not overlap with the current track path of the at least one second vehicle.
Optionally, the path planning module 502 is configured to:
Determining a longitudinal overtaking distance of the first vehicle based on the current running speed and the safe overtaking time of the first vehicle, and determining a sixth path control point on the current running lane based on the obtained longitudinal overtaking distance;
The sixth path control point is taken as a starting point, the safe overtaking distance is displaced backwards along the advancing direction of the center line of the current driving lane, and a fifth path control point is determined;
A third path control point is determined based on the current position of the second path control point, and a fourth path control point is determined based on the current position of the fifth path control point.
Optionally, the path planning module 502 is configured to:
determining a third path control point by vertically shifting the safe overtaking distance along the perpendicular direction between the center line of the current driving lane and the center line of the target changed lane by taking the second path control point as a starting point, and
And taking the current position of the fifth path control point as a starting point, vertically shifting the safe overtaking distance along the perpendicular line direction between the central line of the current driving lane and the central line of the target changed lane, and determining the fourth path control point.
In some embodiments, the functions or modules included in the path planning apparatus provided by the embodiments of the present application may be used to perform the methods described in the foregoing method embodiments, and specific implementation of the path planning apparatus may refer to the descriptions in the foregoing method embodiments, which are not repeated herein for brevity.
For convenience of description, the above parts are described as being functionally divided into modules (or units) respectively. Of course, the functions of each module (or unit) may be implemented in the same piece or pieces of software or hardware when implementing the present application.
Having described the path planning method and apparatus of an exemplary embodiment of the present application, next, a path planning apparatus according to another exemplary embodiment of the present application is described.
Those skilled in the art will appreciate that the various aspects of the application may be implemented as a system, method, or program product. Accordingly, aspects of the present application may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, micro-code, etc.) or an embodiment combining hardware and software aspects that may be referred to herein collectively as a "circuit," module "or" system.
Based on the same inventive concept as the above-mentioned method embodiment, a path planning apparatus is further provided in the embodiment of the present application, and referring to fig. 6, the path planning apparatus 600 may at least include a processor 601 and a memory 602. The memory 602 stores program code that, when executed by the processor 601, causes the processor 601 to perform the steps of any one of the path planning methods described above.
In some possible implementations, a computing device according to the application may include at least one processor, and at least one memory. Wherein the memory stores program code which, when executed by the processor, causes the processor to perform the method described in the method embodiments above. For example, the processor may perform the steps as shown in fig. 3 a.
A computing device 700 according to such an embodiment of the application is described below with reference to fig. 7. The computing device 700 of fig. 7 is only one example and should not be taken as limiting the functionality and scope of use of embodiments of the present application.
As shown in fig. 7, computing device 700 is in the form of a general purpose computing device. The components of computing device 700 may include, but are not limited to, at least one processing unit 701 described above, at least one memory unit 702 described above, and a bus 703 that connects the various system components, including memory unit 702 and processing unit 701.
Bus 703 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a processor, and a local bus using any of a variety of bus architectures.
The storage unit 702 may include readable media in the form of volatile memory, such as Random Access Memory (RAM) 7021 and/or cache memory 7022, and may further include Read Only Memory (ROM) 7023.
The storage unit 702 may also include a program/utility 7025 having a set (at least one) of program modules 7024, such program modules 7024 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment.
The computing device 700 may also communicate with one or more external devices 704 (e.g., keyboard, pointing device, etc.), one or more devices that enable a user to interact with the computing device 700, and/or any devices (e.g., routers, modems, etc.) that enable the computing device 700 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 705. Moreover, the computing device 700 may also communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet, through the network adapter 706. As shown, the network adapter 706 communicates with other modules for the computing device 700 over the bus 703. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with computing apparatus 700, including, but not limited to, microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.
Aspects of the path planning method provided by the application may also be implemented in the form of a program product comprising program code for causing a path planning device to carry out the method described in the method embodiments above, when the program product is run on the path planning device, e.g. the path planning device may carry out the steps as shown in fig. 3 a.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of a readable storage medium include an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
While preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the application.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the scope of the application.