Path planning method, device, equipment and medium

Abstract

The invention relates to the field of intelligent driving, in particular to a path planning method, device and equipment and a medium, and the method comprises the steps: determining a plurality of planning tracks in a target coordinate system according to a first coordinate of a vehicle and a second coordinate corresponding to at least one terminal point; other target object track confidence coefficients, the minimum transverse length and the minimum longitudinal length corresponding to the target planning track are determined; determining a cost value corresponding to the target planning track according to the track information corresponding to the target planning track, the self-vehicle information, and the track confidence coefficient, the minimum transverse length and the minimum longitudinal length of other target objects; and determining an optimal planning trajectory from the plurality of planning trajectories according to the cost values corresponding to the plurality of planning trajectories. According to the method, the minimum transverse length and the minimum longitudinal length are introduced into cost value calculation, it can be ensured that the sufficient safe distance is kept between the vehicle and other target objects, and the potential collision risk is effectively avoided; and determining an accurate and reliable optimal planning trajectory according to the cost values of the plurality of planning trajectories.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving, and in particular to a path planning method, device, equipment and medium. Background Art

[0002] Intelligent driving technology has become an important development direction of the automotive industry. Intelligent driving vehicles can drive autonomously in traffic environments and avoid collisions with other vehicles and pedestrians to ensure driving safety.

[0003] At present, most planning methods for intelligent driving vehicles use algorithms based on path planning and collision detection to avoid the driving routes of other vehicles / pedestrians. This planning or collision risk judgment method can bring a great safety margin, resulting in low planning accuracy. Summary of the invention

[0004] The purpose of this application is to provide a path planning method, device, equipment and medium that can accurately plan the optimal path.

[0005] In a first aspect, a path planning method is provided, comprising:

[0006] Acquire a first coordinate of the vehicle and a second coordinate corresponding to at least one end point in a target coordinate system, wherein the target coordinate system is a coordinate system composed of a speed axis, an S axis, and an L axis, and the speed axis is perpendicular to the S axis and the L axis;

[0007] Determining a plurality of planned trajectories in the target coordinate system according to the first coordinate of the ego vehicle and the second coordinate corresponding to the at least one end point;

[0008] Determine the confidence, minimum lateral length, and minimum longitudinal length of other target object trajectories corresponding to the target planning trajectory, wherein the minimum lateral length is the distance from the shortest distance between the target planning trajectory and the other target object trajectories projected to the lateral danger area of ​​the vehicle in the target coordinate system, and the minimum longitudinal length is the distance from the shortest distance between the target planning trajectory and the other target object trajectories projected to the longitudinal danger area of ​​the vehicle in the target coordinate system; the target planning trajectory is any one of the multiple planned trajectories;

[0009] Determine the cost value corresponding to the target planning trajectory according to the trajectory information corresponding to the target planning trajectory, the vehicle information, and the trajectory confidence, minimum lateral length, and minimum longitudinal length of other target objects;

[0010] According to the cost values ​​corresponding to the multiple planned trajectories, an optimal planned trajectory is determined from the multiple planned trajectories, so as to control the driving of the vehicle in the next time frame based on the optimal planned trajectory.

[0011] In a preferred example, the present application can be further configured to: determine the cost value corresponding to the target planning trajectory according to the trajectory information corresponding to the target planning trajectory, the vehicle information, and the trajectory confidence, minimum lateral length, and minimum longitudinal length of other target objects, including:

[0012] Determine the first child value based on the trajectory information and vehicle information corresponding to the target planning trajectory;

[0013] According to the confidence level and the minimum longitudinal length of the trajectory of other target objects, the longitudinal constraint value of other target objects is determined as the second child value;

[0014] According to the confidence level and minimum lateral length of the trajectories of other targets, the lateral constraint values ​​of other targets are determined as the third child value;

[0015] The cost value corresponding to each planning trajectory is determined according to the first child value, the second child value and the third child value.

[0016] In a preferred example, the present application may be further configured as follows: the trajectory information corresponding to the target planning trajectory includes: time loss, current lateral acceleration, current longitudinal acceleration, end lane information, and lane width;

[0017] The vehicle information includes: a first distance between the vehicle and the center of the lane, a second distance between the vehicle and the nearest line, the vehicle speed, a road speed threshold of the lane, a minimum longitudinal distance between the vehicle and other target vehicles, and a minimum lateral distance between the vehicle and other target vehicles.

[0018] In a preferred example, the present application may be further configured to: determine the confidence of other target object trajectories corresponding to the target planning trajectory, including:

[0019] If the end point corresponding to the target planning trajectory is on the vehicle's own lane, the confidence of the trajectory of other target objects is determined to be 1;

[0020] If the end point corresponding to the target planning trajectory is not on the self-lane of the vehicle, the longitudinal other target trajectory confidence is determined according to the longitudinal other target trajectory initial confidence, target duration and trajectory confidence unit increment; the lateral other target trajectory confidence is determined according to the lateral other target trajectory initial confidence, target duration and trajectory confidence unit increment; the sum of the longitudinal other target trajectory confidence and the lateral other target trajectory confidence is used as the other target trajectory confidence;

[0021] The target duration is the duration between the start planning time and the target time. If the current time is less than the time when the vehicle crosses the line, the target time is the current time. If the current time is greater than the time when the vehicle crosses the line, the target time is the time when the vehicle crosses the line.

[0022] The confidence level of the longitudinal other target object trajectories is not greater than a first threshold, the confidence level of the lateral other target object trajectories is not greater than a second threshold, and the sum of the first threshold and the second threshold is 1.

[0023] In a preferred example, the present application can be further configured as follows:

[0024] At the beginning of planning, determine whether other targets in the adjacent lanes meet preset conditions, which are: the distance between other targets and vehicles in the adjacent lanes is greater than a preset distance, and the collision time of other targets is greater than a preset collision time threshold; or there is no vehicle in the adjacent lanes of other targets;

[0025] If the preset conditions are met, the initial confidence values ​​of the longitudinal other target object trajectories are determined to be 0, and the initial confidence values ​​of the lateral other target object trajectories are determined to be 0;

[0026] If the preset condition is not met, it is determined that the initial confidence value of the lateral other target object trajectories is taken as the second threshold, and the initial confidence value of the longitudinal other target object trajectories is taken as 0.

[0027] In a preferred example, the present application can be further configured to: determine the minimum horizontal length and the minimum vertical length corresponding to the target planning trajectory, including:

[0028] According to the target planning trajectory and the predicted trajectory corresponding to the other target objects, determine the third coordinate of the self-vehicle in the target coordinate system and the fourth coordinate of the other target objects in the target coordinate system at the moment when the distance between the vehicles is the shortest;

[0029] Determine the danger zone corresponding to the third coordinate of the ego vehicle in the target coordinate system;

[0030] Determine a minimum lateral length according to the lateral lateral lateral area of ​​the lateral lateral area and the fourth coordinates of other targets in the target coordinate system;

[0031] The minimum longitudinal length is determined according to the longitudinal length of the dangerous area and fourth coordinates of other targets in the target coordinate system.

[0032] In a preferred example, the present application may be further configured as follows: determining the dangerous area corresponding to the third coordinate of the vehicle in the target coordinate system includes:

[0033] A longitudinal danger zone is constructed according to the braking distance, wherein the braking distance is determined according to the maximum deceleration and the vehicle speed to brake at the maximum deceleration;

[0034] Constructing a lateral danger zone according to a preset width, wherein the preset width is a preset multiple of the body width of the vehicle;

[0035] The longitudinal danger zone and the lateral danger zone are mapped to a target coordinate system to obtain a danger zone corresponding to a third coordinate of the vehicle in the target coordinate system.

[0036] In a second aspect, a path planning device is provided, comprising:

[0037] an acquisition module, used to acquire a first coordinate of the vehicle and a second coordinate corresponding to at least one end point in a target coordinate system, wherein the target coordinate system is a coordinate system composed of a speed axis, an S axis and an L axis, and the speed axis is perpendicular to the S axis and the L axis;

[0038] A first determination module, configured to determine a plurality of planned trajectories in the target coordinate system according to the first coordinate of the ego vehicle and the second coordinate corresponding to the at least one end point;

[0039] The second determination module is used to determine the confidence, minimum lateral length, and minimum longitudinal length of other target object trajectories corresponding to the target planning trajectory, wherein the minimum lateral length is the distance from the shortest distance between the target planning trajectory and the other target object trajectories projected to the lateral danger area of ​​the vehicle in the target coordinate system, and the minimum longitudinal length is the distance from the shortest distance between the target planning trajectory and the other target object trajectories projected to the longitudinal danger area of ​​the vehicle in the target coordinate system; the target planning trajectory is any trajectory among the multiple planning trajectories;

[0040] The third determination module is used to determine the cost value corresponding to the target planning trajectory according to the trajectory information corresponding to the target planning trajectory, the vehicle information, and the trajectory confidence, minimum lateral length, and minimum longitudinal length of other target objects;

[0041] The path screening module is used to determine the optimal planned trajectory from the multiple planned trajectories according to the cost values ​​corresponding to the multiple planned trajectories, so as to control the driving of the vehicle in the next time frame based on the optimal planned trajectory.

[0042] In a third aspect, an electronic device is provided, including:

[0043] one or more processors;

[0044] Memory;

[0045] One or more applications, wherein one or more applications are stored in a memory and configured to be executed by one or more processors, and one or more programs are configured to: perform operations corresponding to the method shown in any possible implementation of the first aspect.

[0046] In a fourth aspect, a computer-readable storage medium is provided, wherein the storage medium stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, at least one program, a code set or an instruction set is loaded by a processor and executes the steps of the method shown in any possible implementation of the first aspect.

[0047] In a fifth aspect, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, operations corresponding to the method shown in any possible implementation manner in the first aspect are implemented.

[0048] In summary, the path planning method provided by this application includes the following beneficial technical effects:

[0049] In the present application, in the target coordinate system composed of the speed axis, the S axis and the L axis, the coordinates of the ego vehicle and at least one end point are obtained; multiple planned trajectories are determined based on these coordinates, so that the ego vehicle has multiple possible driving paths to choose from; then, by evaluating the trajectory confidence, minimum lateral length and minimum longitudinal length of other target objects corresponding to each planned trajectory, the actual impact of other target objects on the ego vehicle during driving is comprehensively considered; according to the trajectory information, ego vehicle information corresponding to the target planned trajectory, and the trajectory confidence, minimum lateral length and minimum longitudinal length of other target objects, the cost value corresponding to the target planned trajectory is determined, and the minimum lateral length and minimum longitudinal length are introduced into the cost value calculation, which can ensure that a sufficient safety distance is maintained between the ego vehicle and other target objects, and effectively avoid potential collision risks; the optimal planned trajectory is determined based on the cost values ​​of multiple planned trajectories, which significantly improves the accuracy and reliability of path planning.

[0050] In addition, the present application also provides a path planning device, equipment and medium, all of which have the above-mentioned beneficial technical effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present application or the technical solutions of the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0052] Figure 1 It is a flowchart of a path planning method provided in an embodiment of the present application;

[0053] Figure 2 A schematic diagram of a target coordinate system provided in an embodiment of the present application;

[0054] Figure 3A schematic diagram of planning S-axis motion on a VS plane in a target coordinate system provided in an embodiment of the present application;

[0055] Figure 4 A schematic diagram of planning L-axis motion on the SL plane in the target coordinate system provided in an embodiment of the present application;

[0056] Figure 5 A schematic diagram of a planning of longitudinal movement of a vehicle provided in an embodiment of the present application;

[0057] Figure 6 A schematic diagram of a vehicle lateral movement planning provided in an embodiment of the present application;

[0058] Figure 7 A schematic diagram of a motion surface corresponding to each position point provided in an embodiment of the present application;

[0059] Figure 8 A schematic diagram of a vertical risk provided in an embodiment of the present application;

[0060] Fig. 9 A schematic diagram of vertical and horizontal risks provided in an embodiment of the present application;

[0061] Fig.10 A schematic diagram of a comprehensive risk area provided in an embodiment of the present application;

[0062] Fig.11 A schematic diagram of calculating the minimum longitudinal length provided in an embodiment of the present application;

[0063] Fig.12 A schematic diagram of dynamic adjustment of cconf provided in an embodiment of the present application;

[0064] Fig.13 A schematic diagram of a specific lane-changing scenario provided in an embodiment of the present application;

[0065] Fig.14 is a structural schematic diagram of a path planning device provided in an embodiment of the present application;

[0066] Fig.15 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0067] This specific embodiment is merely an explanation of the present application and is not a limitation of the present application. After reading this specification, a person skilled in the art may make non-creative modifications to the present embodiment as needed, but such modifications are protected by the patent law as long as they are within the scope of the present application.

[0068] It should be noted that in the optional embodiments of the present application, the object information and other related data involved, when the embodiments in the present application are applied to specific products or technologies, need to obtain the permission or consent of the object, and the collection, use and processing of the relevant data need to comply with the relevant laws, regulations and standards of the relevant countries and regions. In other words, if the embodiments of the present application involve data related to the object, it needs to be obtained with the authorization and consent of the object, the authorization and consent of the relevant departments, and in compliance with the relevant laws, regulations and standards of the country and region. If personal information is involved in the embodiments, the acquisition of all personal information needs to obtain the consent of the individual. If sensitive information is involved, the separate consent of the information subject needs to be obtained. The embodiments also need to be implemented with the authorization and consent of the object.

[0069] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0070] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0071] Generally, current planning methods are all aimed at avoiding the driving routes of other target vehicles / pedestrians. This planning or collision risk judgment method can bring great safety margins, but it undoubtedly limits the planning space of the vehicle to a great extent, because this method abandons the interaction between vehicles and vehicles, and vehicles and pedestrians. The present invention provides a vehicle collision risk detection and planning method, which can plan the path using the maximum planning space under the premise of ensuring the driving safety of the vehicle and other target objects.

[0072] Specifically, the present application embodiment provides a path planning method, such as Figure 1As shown, the method provided in the embodiment of the present application can be executed by an electronic device, and the electronic device is a server. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a vehicle-mounted computing device, etc., but is not limited to this. The terminal device and the electronic device can be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiment of the present application. The method includes:

[0073] S101, obtaining a first coordinate of the vehicle and a second coordinate corresponding to at least one end point in a target coordinate system;

[0074] The target coordinate system is a coordinate system composed of the speed axis, the S axis and the L axis, and the speed axis is perpendicular to the S axis and the L axis;

[0075] Among them, reference Figure 2 , Figure 2 A schematic diagram of a target coordinate system provided in an embodiment of the present application is used to establish a VSL coordinate system, where V represents speed, S represents the direction of the front of the vehicle, and L represents the direction perpendicular to the front of the vehicle. The position (0, 0, 0) of the VSL coordinate system is the position of the particle when the speed of the vehicle is 0.

[0076] The end point refers to the target position that the vehicle needs to reach, which is a three-dimensional position specified by the user. There is at least one, and it can be two or more. The end point can be in the vehicle's lane or in other lanes, which is not limited in the embodiments of the present application.

[0077] S102, determining a plurality of planned trajectories in a target coordinate system according to a first coordinate of the vehicle and a second coordinate corresponding to at least one end point;

[0078] Path planning for each endpoint can obtain several planned trajectories, and the planned trajectories corresponding to all endpoints are integrated to obtain multiple planned trajectories.

[0079] In the embodiment of the present application, points are scattered in the target coordinate system, and the end point is marked in the target coordinate system to obtain multiple planned paths.

[0080] See also Figure 3 , the movement of the vehicle in the S-axis direction can be planned on the VS plane in the target coordinate system. For each vehicle speed (taking 80km / h as an example), the intervals are evenly distributed. point. Among them, Δt represents a cycle of program operation (for example, 20ms), v is the vehicle speed, It represents the distance that can be traveled within Δt at the vehicle speed v. As v increases in the VS coordinate system, the spacing between points will also increase. At different vehicle speeds, the VS plane can be divided into countless points. For example, when planning the trajectory of the vehicle to reach the end point, you can point to the position of any point from the current position. It should be noted that the direction of the arrow, that is, the slope, corresponds to the acceleration of the vehicle, which is the rate of change of speed per unit time (Δt). It should be noted that when selecting a point, the acceleration needs to be within the maximum acceleration range of the vehicle.

[0081] See also Figure 4 , the movement of the vehicle in the L-axis direction can be planned on the SL plane in the target coordinate system, and the inverse of the slope of the arrow corresponds to the lateral acceleration of the vehicle per unit time (Δt).

[0082] Figure 4 The vehicle is described in the first direction, that is, in the longitudinal direction. Figure 5 As shown, by adjusting the vS coordinate system to the SL coordinate system, the movement of the vehicle in the second direction, that is, the lateral movement, can be represented. Taking l2 as the starting point, the inverse of the slope pointed by arrows s3 and s4 corresponds to the lateral acceleration of the vehicle per unit time (Δt).

[0083] Combination Figure 5 and Figure 6 . Figure 5 A schematic diagram of a planning of longitudinal motion of a vehicle provided in an embodiment of the present application, wherein the first coordinate of the vehicle can reach point1 (corresponding to the maximum deceleration a1) and point2 (corresponding to the maximum acceleration a0); Figure 6 A schematic diagram of a vehicle lateral motion planning provided in an embodiment of the present application. Projecting point2 into the SL coordinate system can obtain the lateral displacement L0 of the vehicle from S0 to S2 within a unit time Δt.

[0084] refer to Figure 7 For the first coordinate of the vehicle, it can move to the curved trapezoid shown in the figure. Select several points in the plane of the first coordinate, and then the selected points can form a curved trapezoid again. Select points again until all the planned trajectories from the first coordinate to the end point are planned.

[0085] After obtaining multiple planning trajectories, the cost function can be used to determine an optimal path.

[0086] S103, determining the confidence level, minimum horizontal length, and minimum vertical length of other target object trajectories corresponding to the target planning trajectory;

[0087] Among them, other target objects may be other vehicles, pedestrians, or other obstacles, specifically, target objects that are closest to the vehicle and affect the driving of the vehicle.

[0088] The minimum lateral length is the distance between the target planning trajectory and other target object trajectories projected to the lateral danger zone of the vehicle in the target coordinate system, and the minimum longitudinal length is the distance between the target planning trajectory and other target object trajectories projected to the longitudinal danger zone of the vehicle in the target coordinate system; the target planning trajectory is any trajectory among multiple planned trajectories;

[0089] The confidence of other target object trajectories refers to the credibility of the predicted trajectories of other target objects on the road (the own lane or other lanes). Among them, the minimum lateral length is used to measure the safety impact of other targets in the lateral direction, and the minimum longitudinal length is used to measure the safety impact of other targets in the longitudinal direction.

[0090] S104, determining a cost value corresponding to the target planning trajectory according to trajectory information corresponding to the target planning trajectory, vehicle information, and trajectory confidence, minimum lateral length, and minimum longitudinal length of other target objects;

[0091] In the embodiment of the present application, the actual situation of the target planning trajectory is comprehensively considered and the possible interactions of other target object trajectories are also taken into account to jointly determine the cost value of the target planning trajectory. The lower the cost value, the more suitable the trajectory is as the final driving path.

[0092] S105 . Determine an optimal planned trajectory from the multiple planned trajectories according to the cost values ​​corresponding to the multiple planned trajectories, so as to control the driving of the vehicle in the next time frame based on the optimal planned trajectory.

[0093] Among them, the optimal planning trajectory is the planning trajectory with the smallest cost.

[0094] It should be noted that in the embodiment of the present application, planning can be performed according to a time frame. For example, the vehicle determines the optimal planning trajectory from multiple planning trajectories at the first coordinate at the first moment, and drives according to the optimal planning trajectory; at the second moment, the vehicle drives to a new first coordinate, and then re-determines multiple planning trajectories according to actual conditions, determines a new optimal planning trajectory from multiple planning trajectories, and drives according to the new optimal planning trajectory; incorrect planning and driving are performed until the destination is reached.

[0095] It can be seen that in the embodiment of the present application, in the target coordinate system composed of the speed axis, the S axis and the L axis, the coordinates of the ego vehicle and at least one end point are obtained; multiple planned trajectories are determined based on these coordinates, so that the ego vehicle has multiple possible driving paths to choose from; then, by evaluating the corresponding trajectory confidence, minimum lateral length and minimum longitudinal length of other target objects for each planned trajectory, the actual impact of other target objects on the ego vehicle during driving is comprehensively considered; according to the trajectory information, ego vehicle information corresponding to the target planned trajectory, and the trajectory confidence, minimum lateral length and minimum longitudinal length of other target objects, the cost value corresponding to the target planned trajectory is determined, and the minimum lateral length and minimum longitudinal length are introduced into the cost value calculation, which can ensure that a sufficient safety distance is maintained between the ego vehicle and other target objects, and effectively avoid potential collision risks; the optimal planned trajectory is determined based on the cost values ​​of multiple planned trajectories, which significantly improves the accuracy and reliability of path planning.

[0096] In an embodiment of the present application, a possible implementation of the embodiment of the present application, determining the minimum horizontal length and the minimum vertical length corresponding to the target planning trajectory in S103 includes: SA1-SA4, wherein:

[0097] SA1. Determine the third coordinate of the vehicle in the target coordinate system and the fourth coordinate of the other target in the target coordinate system at the moment when the distance between the vehicles is closest, based on the target planned trajectory and the predicted trajectory corresponding to the other target;

[0098] Among them, the predicted trajectory corresponding to other target objects is obtained by the electronic device through the speed and acceleration of other target objects. Here, other target objects are other target objects closest to the vehicle.

[0099] The moment when the distance between vehicles is the shortest refers to the time point when the relative distance between the ego vehicle and other target vehicles in the target coordinate system reaches the minimum. The potential collision risk can be evaluated by the status of the ego vehicle and other target objects at this time point.

[0100] SA2, determine the danger zone corresponding to the third coordinate of the vehicle in the target coordinate system;

[0101] The vehicle collision area is established as a dangerous area. For a vehicle traveling on the road, it usually has a maximum longitudinal deceleration ac and a maximum lateral acceleration al. In the longitudinal direction, the distance s0 that the vehicle can stop at v with the maximum deceleration ac can be approximately expressed as In the longitudinal direction, before the braking distance s0, the risk T is 1, and as it moves away from s0, the risk gradually decreases. The slope K can be calculated based on the calibrated deceleration a lonc It can be concluded that the vehicle can be stopped at a comfortable deceleration at a certain point to obtain the stopping distance s1, and the curvature K can be obtained by connecting s0 and s1. Based on this, the following can be established based on the distance: Figure 8 Longitudinal risk graph shown;

[0102] Similarly, for the horizontal direction, assuming that the current lane change is to the right, the risk within 1.5 times the vehicle width is 1 (regardless of vehicle heading), and the position l0 represents the minimum safe distance allowed between vehicles (the distance between the vehicle centers). Based on this, in the horizontal direction, we can establish Fig. 9 Horizontal risk map shown.

[0103] Map the horizontal and vertical directions to the target coordinate system, and the risk area in front of a vehicle with a driving speed of v is as follows: Fig.10 As shown, the blue solid rectangle represents the vehicle, the area surrounded by the yellow line segment represents the area where the risk T ranges from 0 to 1, and the area surrounded by the red part represents the area where the risk is 1. The area surrounded by the purple line segment is the area where the lateral risk T ranges from 0 to 1, and the area surrounded by the green line segment is the area where the lateral risk is 1.

[0104] Therefore, in the embodiment of the present application, after determining the nearest coordinate points of the vehicle and other target objects, determine the danger zone corresponding to the third coordinate of the vehicle in the target coordinate system, including: constructing a longitudinal danger zone according to the braking distance, the braking distance is determined according to the maximum deceleration and the speed of the vehicle, and the distance to brake at the maximum deceleration; constructing a transverse danger zone according to the preset width, the preset width is a preset multiple of the body width of the vehicle; mapping the longitudinal danger zone and the transverse danger zone to the target coordinate system, and obtaining the danger zone corresponding to the third coordinate of the vehicle in the target coordinate system. The preset multiple can be set by the user, such as 1.5.

[0105] When determining the danger zone corresponding to the third coordinate of the ego vehicle in the target coordinate system, the maximum distance at which the ego vehicle can stop in an emergency is taken into consideration, and the longitudinal danger zone is constructed based on the stopping distance, thereby ensuring a more accurate assessment of the longitudinal safety; the lateral space that may be required by the ego vehicle during driving is fully considered, and the lateral danger zone is constructed based on the preset width; these two danger zones are mapped to the target coordinate system to obtain the danger zone corresponding to the third coordinate of the ego vehicle in the target coordinate system, which makes the determination of the danger zone more intuitive and accurate, and can more effectively assess the potential risks that the ego vehicle may face during driving, thereby ensuring the safety and reliability of path planning.

[0106] SA3, determine the minimum horizontal length according to the horizontal dangerous area of ​​the dangerous area and the fourth coordinates of other targets in the target coordinate system;

[0107] See also Fig.11 , project the fourth coordinate point into the longitudinal danger zone of the vehicle, and determine the distance AB between the two coordinate points in the target coordinate system according to the third and fourth coordinate points (i.e. , where f(t) is the trajectory of other targets, g(t) is the trajectory of the vehicle), and then a corresponding to the longitudinal curvature k and AB are multiplied to obtain i, that is, the minimum longitudinal length, a=sin(arctan(K)).

[0108] SA4. Determine the minimum lateral length according to the lateral danger zone of the danger zone and the fourth coordinates of other target vehicles in the target coordinate system.

[0109] The minimum horizontal length in the horizontal direction is obtained by referring to the vertical calculation method, which will not be described in detail in this embodiment.

[0110] In a possible implementation of the embodiment of the present application, the confidence levels of other target object trajectories corresponding to the target planning trajectory are determined in S102, including: SC1-SC2, where:

[0111] SC1: If the destination corresponding to the target planning trajectory is on the vehicle's own lane, the confidence of the trajectory of other targets is determined to be 1;

[0112] Among them, when the vehicle does not change lanes, it is less affected by other targets. Therefore, the confidence of the trajectory of other targets can be set to 1.

[0113] SC2. If the end point corresponding to the target planning trajectory is not on the self-lane of the vehicle, the longitudinal other target trajectory confidence is determined according to the longitudinal other target trajectory initial confidence, target duration and trajectory confidence unit increment; the lateral other target trajectory confidence is determined according to the lateral other target trajectory initial confidence, target duration and trajectory confidence unit increment; the sum of the longitudinal other target trajectory confidence and the lateral other target trajectory confidence is taken as the other target trajectory confidence;

[0114] The target duration is the duration between the start of planning and the target time. If the current time is less than the time when the vehicle crosses the line, the target time is the current time. If the current time is greater than the time when the vehicle crosses the line, the target time is the time when the vehicle crosses the line.

[0115] The confidence level of the longitudinal trajectories of other target objects is not greater than a first threshold, and the confidence level of the lateral trajectories of other target objects is not greater than a second threshold. The sum of the first threshold and the second threshold is 1.

[0116] Other targets refer to the targets that are closest to the vehicle and affect the driving, which can be vehicles or pedestrians. For example, if the other target is target A, then the trajectory confidence of the other target is the trajectory confidence of target A, specifically the sum of the longitudinal trajectory confidence of target A and the lateral trajectory confidence of target A.

[0117] Among them, in the embodiment of the present application, it is defined that all vehicles have a risk avoidance mechanism, that is, the vehicle will try to avoid other targets from invading the collision risk area of ​​the vehicle. If the end point is on a non-self-driving lane, that is, the vehicle needs to change lanes, the longitudinal constraint and the lateral constraint have cconf, and, over time, the cconf corresponding to each path is dynamically adjusted.

[0118] In the longitudinal direction, the vehicle is not allowed to invade the risk area of ​​the vehicle within the next t1 seconds. Therefore, t1 can be customized, such as 8s. In the pre-set function, the longitudinal weight is increased, where cconf is the confidence of other target object trajectories, which is the sum of the confidence of other target object trajectories in the lateral direction and the confidence of other target object trajectories in the longitudinal direction:

[0119] ,

[0120] t1 is the length of time that the prediction module can give the vehicle predicted trajectory. Represents the predicted trajectory of other targets, such as the trajectory of other cars, It represents the planned trajectory predicted by the ego vehicle. The physical meaning of i is as follows (the minimum distance from the front vehicle to the projection of the collision area), that is, the minimum longitudinal length. When the vehicle is in the risk area in the lateral direction, a=sin(arctan(K)) can be obtained according to the curvature K.

[0121] Increase cconf. When changing lanes, the vehicle and other objects may have intersecting tracks and may collide. In the embodiment of the present application, the possibility that other objects may give way is taken into consideration, and cconf is the probability that other objects give way to the vehicle.

[0122] In the horizontal direction, the vehicle is not allowed to invade the risk area of ​​the vehicle within the next t1 seconds. Similarly, we can get:

[0123] .

[0124] Wherein, a2=sin(arctan(K)), k=1 / (L0-L1), where L0 is the minimum safe distance allowed between vehicle centers, and L1 is the vehicle width at a preset multiple, where the preset multiple can be 1.5.

[0125] It should be noted that for each vehicle's predicted trajectory f(x)i, its trajectory will include a change confidence (cconf), which does not exceed 1. cconf includes two dimensions, horizontal and vertical, and the total cconf is at most 1. The horizontal other target object trajectory confidence and the vertical other target object trajectory confidence are both set with corresponding maximum thresholds. The two thresholds (the first threshold and the second threshold) can be the same, both 0.5, or different. This embodiment is not limited thereto. Preferably, both are 0.5.

[0126] In an embodiment of the present application, in three-dimensional trajectory planning, when the ego vehicle changes lanes or turns, the cconf between the target lane and the rear vehicle will be checked (the front vehicle will not be checked because the trajectory of the ego vehicle will not affect the front vehicle). An initial confidence in the longitudinal trajectory of other target objects and an initial confidence in the lateral trajectory of other target objects are set. Since the path planning of the ego vehicle and the selection of the optimal path will be performed at certain intervals, the confidence in the trajectory of other target objects will be dynamically adjusted based on the initial confidence in the trajectory of other target objects. Each time planning starts, each frame will run and an increment will be fed back to the prediction: cconf'. As the cconf of the vehicle increases, the impact of the trajectory of other target objects on the collision area will gradually increase. The time point when cconf increases the most can be taken as the time when the vehicle crosses the line, see Fig.12 .

[0127] Specifically, the adjustment value is determined according to the time from the initial moment to the current moment , in order to adjust the confidence of other target object trajectories, and set conditions for stopping updating the adjustment value, including: the current moment is greater than the time when the vehicle crosses the line, or the longitudinal / lateral confidence of other target object trajectories is greater than the corresponding threshold, after which the adjustment value remains unchanged.

[0128] in, As an adjustment value, t is the time from when the vehicle starts to change lanes to when the vehicle crosses the lane, or as an adjustment value.

[0129] It can be seen that in the embodiment of the present application, for the case where the end point of the planned trajectory is on the self-lane, since other targets have little impact on the self-vehicle, the trajectory confidence of the other target object is directly assigned to 1; for the case where the end point of the planned trajectory is not on the self-lane, the longitudinal and lateral confidences of the other target object trajectories are calculated respectively according to the initial longitudinal and lateral confidences of the other target object trajectories, the target duration, and the unit increment of the trajectory confidence, fully considering the impact of the possible driving conditions of other targets on the driving path of the self-vehicle; the longitudinal and lateral confidences of the other target object trajectories are added together to obtain the total value of the confidence of the other target object trajectories, so that the cost value of the evaluation path is more accurate and more in line with the actual pedestrian or vehicle yielding situation.

[0130] A possible implementation method of the embodiment of the present application also includes: at the beginning of planning, determining whether other targets in the adjacent lane meet preset conditions, the preset conditions being: the distance between the other target and the vehicle in the adjacent lane is greater than the preset distance, and the collision time of the other target is greater than the preset collision time threshold; or there is no vehicle in the adjacent lane of the other target; if the preset conditions are met, determining that the initial confidence value of the longitudinal trajectory of the other target is 0, and the initial confidence value of the lateral trajectory of the other target is 0; if the preset conditions are not met, determining that the initial confidence value of the lateral trajectory of the other target is the second threshold, and the initial confidence value of the longitudinal trajectory of the other target is 0.

[0131] In an embodiment of the present application, in the lateral dimension, taking the first threshold and the second threshold both being 0.5 as an example, the initial confidence of the lateral trajectory of other target objects is between 0 and 0.5, and this value depends on the TTC with other target vehicles and whether lane change is possible. Specifically, it is determined whether other targets in the destination lane meet the preset conditions, and the preset conditions are: the distance between other targets and vehicles in the adjacent lane is greater than the preset distance 2v, and the collision time of other targets is greater than the preset collision time threshold of 5.0; or there is no vehicle in the adjacent lane of the target lane; wherein the preset distance can be a preset multiple of the vehicle speed, such as twice the vehicle speed; the preset collision time threshold can be user-defined by the user, and can be set to 5s; the collision time of other targets is determined based on the current vehicle speed and the speed of the nearest vehicle in the adjacent lane.

[0132] If it is not satisfied, it means that the lane cannot be changed, the initial confidence of the lateral other target object trajectories is set to 0.5, the initial confidence of the longitudinal other target object trajectories cconf is 0, and the initial confidence of the other target object trajectories is 0.5+0=0.5; if it is not satisfied, it means that the lane can be changed, and the initial confidence of the longitudinal other target object trajectories cconf is determined to be 0, the initial confidence of the lateral other target object trajectories cconf is 0, and the initial confidence of the other target object trajectories is 0+0.

[0133] In a possible implementation of the embodiment of the present application, S104 determines the cost value corresponding to the target planning trajectory according to the trajectory information corresponding to the target planning trajectory, the vehicle information, and the trajectory confidence, minimum lateral length, and minimum longitudinal length of other target objects, including:

[0134] S1041, determining the first child value according to the trajectory information and the vehicle information corresponding to the target planning trajectory;

[0135] Among them, the trajectory information corresponding to the target planning trajectory includes: time loss t c 、Current lateral acceleration a long、Current longitudinal acceleration a lat , terminal lane information tar x 、Lane width w d ;

[0136] The vehicle information includes: the first distance d between the vehicle and the center of the lane c , the second distance d from the vehicle to the nearest line r , vehicle speed v c , the road speed threshold v of the self-lane max , the minimum longitudinal distance d between the vehicle and other target vehicles long , the minimum lateral distance d between the vehicle and other target vehicles lat .

[0137] For the first child value, the first child value f1 is calculated by formula (1), which is:

[0138]

[0139]

[0140] in, It is a proportional coefficient, which is used to adjust the influence of each weight on the final output. Users can customize the settings. is the distance from the vehicle to the lane center (the center of each lane can be judged based on the center of the vehicle, and the minimum value is taken, which can be given by the visual lane centerline / map lane centerline), is the judgment function of the vehicle on the solid lane line / roadside line, is the distance from the vehicle to the solid lane line / roadside line (take the smaller value, multiple distances can be given by the visual lane centerline / map lane centerline, and then take the minimum value), Indicates the lane width, which can be given by the visual lane centerline / map lane centerline. It represents the time loss, which can be calculated by the difference between the unit time for the vehicle to reach the target point of the lane when there are no obstacles (the fastest time to reach the target point planned under the condition of meeting the speed and maximum acceleration requirements) and the unit time planned to reach the target point. and Indicates the currently planned lateral and longitudinal accelerations. and Indicates the calibrated maximum comfortable longitudinal acceleration / deceleration and maximum comfortable lateral acceleration / deceleration. It indicates the minimum longitudinal distance between the vehicle and other targets, which can be obtained by sensors. Indicates the minimum lateral distance between the vehicle and other targets, which can be obtained by sensors. Indicates the current vehicle speed, Indicates the upper limit of road speed. Indicates which lane the destination is in, and will be executed in sequence during planning. tarR indicates the right lane; tarL indicates the left lane; tarego indicates the ego lane. abs() is the absolute value function; δ and φ are preset values.

[0141] S1042, determining the longitudinal constraint value of the other target object as the second child value according to the trajectory confidence and the minimum longitudinal length of the other target object;

[0142] Only using the first child value for path selection is still conservative. In the embodiment of the present application, optimization is made on this basis: establishing a vehicle collision area, establishing a single-vehicle avoidance mechanism based on the collision area, and establishing a vehicle-to-vehicle avoidance mechanism to optimize the above planning, so that the planning method can achieve planning effects in high-density traffic flows or complex traffic environments. Specifically, add lateral constraints on other targets and longitudinal constraints on other targets, and determine the lateral constraint values ​​of other targets and longitudinal constraints of other targets corresponding to each path respectively.

[0143] In the longitudinal direction, the vehicle is not allowed to invade the risk area of ​​the vehicle within the next t1 seconds (t1 is the preset time, such as 8s). Therefore, the weights of the longitudinal constraints of the following other targets are increased:

[0144] ;

[0145] t1 is the length of time that the prediction module can give the vehicle predicted trajectory. represents the predicted trajectory of other targets p, represents the predicted trajectory of the vehicle, and i is the minimum longitudinal length. For example, if there are other target objects 1, other target objects 2, and other target objects 3, the corresponding trajectories are f1(t), f2(t), and f3(t); for other target object 1, calculate , get the shortest i1; for other target 2, calculate , get the shortest i2; for other targets 3, calculate , get the shortest i3, and then select the shortest one from i1, i2, and i3 as i. Specifically, taking i1 as an example, when calculating, refer to Fig.11 , a1=sin(arctan(K)), k=1 / (S1-S0), where , .

[0146] S1043, determining the lateral constraint value of the other target object as the third child value according to the trajectory confidence and the minimum lateral length of the other target object;

[0147] Similarly, in the horizontal direction, the longitudinal constraint values ​​of other targets are determined as the third child value according to the trajectory confidence of other targets and the minimum horizontal length.

[0148] Specifically, in the lateral direction, the vehicle is not allowed to invade the risk area of ​​the vehicle within the next t1 seconds (t1 is the preset time, such as 8s). Therefore, the weights of the lateral constraints of the following other targets are increased:

[0149]

[0150] Wherein, a2=sin(arctan(K)), k=1 / (L0-L1), where L0 is the minimum safe distance allowed between vehicle centers, and L1 is the vehicle width at a preset multiple, where the preset multiple can be 1.5.

[0151] S1044. Determine the generation value corresponding to each planning trajectory according to the first child generation value, the second child generation value, and the third child generation value.

[0152] The sum of the first child generation value, the second child generation value and the third child generation value is determined as the cost value corresponding to each planning trajectory.

[0153] It can be seen that in the embodiment of the present application, the cost value function is updated, and the first sub-generation value is determined according to the trajectory information of the target planning trajectory and the ego vehicle information; the second sub-generation value, that is, the lateral constraint value of other targets, is determined in combination with the trajectory confidence and the minimum longitudinal length of other targets, so as to facilitate the evaluation of the restrictions of other targets on the lateral movement of the ego vehicle; the third sub-generation value, that is, the longitudinal constraint value of other targets, is determined according to the trajectory confidence and the minimum lateral length of other targets, so as to facilitate the evaluation of the restrictions of other targets on the longitudinal movement of the ego vehicle; these three sub-generation values ​​are combined to determine the total cost value of each planned trajectory. This process not only takes into account the driving needs of the ego vehicle, but also fully weighs the potential impact of other targets on the driving path of the ego vehicle, so as to be able to more comprehensively evaluate the planned trajectory.

[0154] Based on any of the above embodiments, the present application provides a specific path planning method, including:

[0155] At the first moment, the position of the ego vehicle in the target coordinate system is the first coordinate, and the user specifies at least one end point of the ego lane and / or the target lane, and the position corresponding to the end point is the second coordinate;

[0156] In the target coordinate system, multiple trajectories are planned based on the vehicle speed, acceleration / deceleration requirements, lane speed requirements, etc.

[0157] Determine the cost function as:

[0158] ;

[0159] in, ,

[0160] ;

[0161] If the destination corresponding to the target planning trajectory is on the lane of the vehicle, the confidence of the other vehicle’s trajectory cconf is determined to be 1;

[0162] If the destination of the target planning trajectory is not on the lane of the vehicle, determine whether the other vehicle of the target vehicle meets the preset condition. The preset condition is: the distance between the other vehicle and the vehicle in the adjacent lane is greater than the preset distance, such as 2v c , and the collision time of the other vehicle is greater than the preset collision time threshold, such as 5s; or there is no vehicle in the adjacent lane of the target lane; if the preset conditions are met, the initial longitudinal other vehicle trajectory confidence value is determined to be 0, the initial lateral other vehicle trajectory confidence value cconf is determined to be 0, and cconf is obtained to be 0; if the preset conditions are not met, the initial lateral other vehicle trajectory confidence value cconf is determined to be 0.5, the initial longitudinal other vehicle trajectory confidence value cconf is determined to be 0, and cconf is obtained to be 0.5.

[0163] According to the calculated cconf and the trajectory information corresponding to the target planning trajectory, the vehicle information, the other vehicle trajectory confidence, the minimum lateral length, the minimum longitudinal length, combined with the cost function, the cost value corresponding to each planning trajectory is obtained;

[0164] Determining an optimal planned trajectory from the multiple planned trajectories according to the cost values ​​corresponding to each of the multiple planned trajectories, so as to control the driving of the vehicle in the next time frame based on the optimal planned trajectory;

[0165] After completing the control of the next time frame, a new first coordinate of the current ego vehicle is obtained, and based on the new first coordinate and a second coordinate corresponding to at least one end point, a plurality of new planned trajectories in the target coordinate system are determined;

[0166] If the destination corresponding to the target planning trajectory is on the lane of the vehicle, the confidence of the other vehicle’s trajectory is determined to be 1;

[0167] If the end point corresponding to the target planning trajectory is not on the lane of the vehicle, the longitudinal other vehicle trajectory confidence is determined according to the initial longitudinal other vehicle trajectory confidence, target duration and trajectory confidence unit increment; the lateral other vehicle trajectory confidence is determined according to the initial lateral other vehicle trajectory confidence, target duration and trajectory confidence unit increment; the sum of the longitudinal other vehicle trajectory confidence and the lateral other vehicle trajectory confidence is used as the other vehicle trajectory confidence; wherein the target duration is the time between the start planning time and the target time, if the current time is less than the time when the vehicle crosses the line, the target time is the current time, if the current time is greater than the time when the vehicle crosses the line, the target time is the time when the vehicle crosses the line; the longitudinal other vehicle trajectory confidence is not greater than the first threshold, the lateral other vehicle trajectory confidence is not greater than the second threshold, and the sum of the first threshold and the second threshold is 1;

[0168] Based on the cost function and the confidence of the new other vehicle trajectory, determine the cost value corresponding to each new planned trajectory;

[0169] Determining an optimal planned trajectory from the multiple planned trajectories according to the cost values ​​corresponding to each of the multiple planned trajectories, so as to control the driving of the vehicle in the next time frame based on the optimal planned trajectory;

[0170] Then continue to repeat the above process in the next time frame until reaching any end point.

[0171] The following is an example to illustrate this mechanism. Fig.13 , assume the following scenario: the vehicle in front of it is speeding down and wants to change lanes to the right lane. At this time, the vehicle's speed is 20m / s. There is a normal-moving vehicle A behind the right lane, with a speed of 25m / s. The distance between the vehicle and the normal-moving vehicle is 30 meters, and there is a normal lane with no vehicles on the right side of the normal-moving vehicle.

[0172] Because the target vehicle can change lanes, its initial cconf=0. When the ego vehicle starts planning in space, the calculated fi=0, it is considered that there is no risk of collision between the two vehicles, and the ego vehicle starts to change lanes to the right. The time to start changing lanes is calculated as t2, and the time to change lanes to the following position is calculated as t3. At this time, the cconf fed back to the prediction by the planning is: (t is the time from when the vehicle starts changing lanes to when it crosses the lane), at this time the cost value of the vehicle will gradually increase. At this time, the other vehicle may have two situations:

[0173] 1. Vehicle A continues to drive without slowing down (yellow line segment). The prediction gives its trajectory normally and its trajectory cconf is high. This is because the increase in cconf causes the cost value to be higher if the vehicle continues to change lanes. Therefore, the plan will not choose to continue changing lanes to the right (because the plan needs to keep the cost value low).

[0174] 2. Vehicle A starts to change lanes to the right (green line). The prediction gives its trajectory normally and cconf is high, but because it has already evaded to the right, the calculated i will still be calculated to be a lower value under the condition of high cconf, and the final cost will also be low because the vehicle will continue to change lanes.

[0175] From the above implementations, we can see that the introduction of collision area and cconf mechanism can make the vehicle not always avoid the trajectory of other vehicles, but actively drive to the target lane under the premise of ensuring safety. Through the collision area, the calculation method of i value and the cconf increment method, the interaction between vehicles can be further adjusted.

[0176] A device provided in an embodiment of the present application is introduced below. The device described below and the method described above can be referred to each other. The device of this embodiment is set in an electronic device. Fig.14 , Fig.14 It is a structural block diagram of a device of one embodiment of the present application, comprising:

[0177] An acquisition module 210 is used to acquire a first coordinate of the vehicle and a second coordinate corresponding to at least one end point in a target coordinate system, wherein the target coordinate system is a coordinate system composed of a speed axis, an S axis, and an L axis, wherein the speed axis is perpendicular to the S axis and the L axis;

[0178] A first determination module 220, configured to determine a plurality of planned trajectories in a target coordinate system according to a first coordinate of the ego vehicle and a second coordinate corresponding to at least one end point;

[0179] The second determination module 230 is used to determine the confidence, minimum lateral length, and minimum longitudinal length of other target object trajectories corresponding to the target planning trajectory, wherein the minimum lateral length is the distance from the shortest distance between the target planning trajectory and the other target object trajectories projected to the lateral danger area of ​​the vehicle in the target coordinate system, and the minimum longitudinal length is the distance from the shortest distance between the target planning trajectory and the other target object trajectories projected to the longitudinal danger area of ​​the vehicle in the target coordinate system; the target planning trajectory is any trajectory among the multiple planning trajectories;

[0180] The third determination module 240 is used to determine the cost value corresponding to the target planning trajectory according to the trajectory information corresponding to the target planning trajectory, the vehicle information, and the trajectory confidence, minimum lateral length, and minimum longitudinal length of other target objects;

[0181] The path screening module 250 is used to determine the optimal planned trajectory from the multiple planned trajectories according to the cost values ​​corresponding to the multiple planned trajectories, so as to control the driving of the vehicle in the next time frame based on the optimal planned trajectory.

[0182] In one achievable manner, the third determination module 240 is used to determine the first child value according to the trajectory information and the ego vehicle information corresponding to the target planning trajectory;

[0183] According to the confidence level and the minimum longitudinal length of the trajectory of other target objects, the longitudinal constraint value of other target objects is determined as the second child value;

[0184] According to the confidence level and minimum lateral length of the trajectories of other targets, the lateral constraint values ​​of other targets are determined as the third child value;

[0185] The cost value corresponding to each planning trajectory is determined according to the first child value, the second child value and the third child value.

[0186] In one achievable manner, the trajectory information corresponding to the target planning trajectory includes: time loss, current lateral acceleration, current longitudinal acceleration, end lane information, and lane width;

[0187] The vehicle information includes: the first distance between the vehicle and the center of the lane, the second distance between the vehicle and the nearest line, the vehicle speed, the road speed threshold of the lane, the minimum longitudinal distance between the vehicle and other target vehicles, and the minimum lateral distance between the vehicle and other target vehicles.

[0188] In one achievable manner, the second determination module 230 is configured to determine that the confidence level of the trajectory of the other target object is 1 if the end point corresponding to the target planning trajectory is on the lane of the vehicle;

[0189] If the end point corresponding to the target planning trajectory is not on the self-lane of the vehicle, the longitudinal trajectory confidence of the other target objects is determined according to the initial confidence of the longitudinal trajectory of the other target objects, the target duration and the unit increment of the trajectory confidence; the lateral trajectory confidence of the other target objects is determined according to the initial confidence of the lateral trajectory of the other target objects, the target duration and the unit increment of the trajectory confidence; the sum of the longitudinal trajectory confidence of the other target objects and the lateral trajectory confidence of the other target objects is taken as the trajectory confidence of the other target objects;

[0190] The target duration is the duration between the start of planning and the target time. If the current time is less than the time when the vehicle crosses the line, the target time is the current time. If the current time is greater than the time when the vehicle crosses the line, the target time is the time when the vehicle crosses the line.

[0191] The confidence level of the longitudinal trajectories of other target objects is not greater than a first threshold, and the confidence level of the lateral trajectories of other target objects is not greater than a second threshold. The sum of the first threshold and the second threshold is 1.

[0192] In an achievable manner, the second determination module 230 is further used to determine whether other targets in the adjacent lanes meet preset conditions at the start of planning, the preset conditions being: the distance between the other targets and the vehicles in the adjacent lanes is greater than a preset distance, and the collision time of the other targets is greater than a preset collision time threshold; or there is no vehicle in the adjacent lanes of the other targets;

[0193] If the preset conditions are met, the initial confidence values ​​of the longitudinal other target object trajectories are determined to be 0, and the initial confidence values ​​of the lateral other target object trajectories are determined to be 0;

[0194] If the preset condition is not met, it is determined that the initial confidence value of the lateral other target object trajectories is taken as the second threshold, and the initial confidence value of the longitudinal other target object trajectories is taken as 0.

[0195] In an implementable manner, the second determining module 230 is further configured to:

[0196] According to the target planning trajectory and the predicted trajectory corresponding to the other target objects, determine the third coordinate of the self-vehicle in the target coordinate system and the fourth coordinate of the other target objects in the target coordinate system at the moment when the distance between the vehicles is the shortest;

[0197] Determine the danger zone corresponding to the third coordinate of the ego vehicle in the target coordinate system;

[0198] Determine the minimum lateral length according to the lateral lateral lateral area of ​​the hazard zone and the fourth coordinates of other targets in the target coordinate system;

[0199] The minimum longitudinal length is determined according to the longitudinal length of the dangerous area and the fourth coordinates of other targets in the target coordinate system.

[0200] In an achievable manner, the second determining module 230 is further used to construct a longitudinal danger zone according to a braking distance, where the braking distance is determined according to the maximum deceleration and the vehicle speed to determine the distance for braking at the maximum deceleration;

[0201] A lateral danger zone is constructed according to a preset width, where the preset width is a preset multiple of the body width of the vehicle;

[0202] The longitudinal danger zone and the lateral danger zone are mapped to the target coordinate system to obtain the danger zone corresponding to the third coordinate of the vehicle in the target coordinate system.

[0203] An electronic device is provided in an embodiment of the present application, such as Fig.15 As shown, Fig.15The electronic device 300 shown includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 300 does not constitute a limitation on the embodiments of the present application.

[0204] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0205] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.15 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0206] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0207] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above method embodiment.

[0208] Fig.15 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0209] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding content in the aforementioned method embodiment.

[0210] An embodiment of the present application provides a computer program product, including a computer program, which implements the corresponding contents of the aforementioned method embodiment when the computer program is executed by a processor.

[0211] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0212] The above are only some implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A path planning method, characterized in that: include: Acquire a first coordinate of the vehicle and a second coordinate corresponding to at least one end point in a target coordinate system, wherein the target coordinate system is a coordinate system composed of a speed axis, an S axis, and an L axis, and the speed axis is perpendicular to the S axis and the L axis; Determining a plurality of planned trajectories in the target coordinate system according to the first coordinate of the ego vehicle and the second coordinate corresponding to the at least one end point; Determine the confidence, minimum lateral length, and minimum longitudinal length of other target object trajectories corresponding to the target planning trajectory, wherein the minimum lateral length is the distance from the shortest distance between the target planning trajectory and the other target object trajectories projected to the lateral danger area of ​​the vehicle in the target coordinate system, and the minimum longitudinal length is the distance from the shortest distance between the target planning trajectory and the other target object trajectories projected to the longitudinal danger area of ​​the vehicle in the target coordinate system; the target planning trajectory is any one of the multiple planned trajectories; Determine the cost value corresponding to the target planning trajectory according to the trajectory information corresponding to the target planning trajectory, the vehicle information, and the trajectory confidence, minimum lateral length, and minimum longitudinal length of other target objects; According to the cost values ​​corresponding to the multiple planned trajectories, an optimal planned trajectory is determined from the multiple planned trajectories, so as to control the driving of the vehicle in the next time frame based on the optimal planned trajectory.

2. The method according to claim 1, characterized in that According to the trajectory information corresponding to the target planning trajectory, the vehicle information, and the trajectory confidence, minimum lateral length, and minimum longitudinal length of other target objects, the cost value corresponding to the target planning trajectory is determined, including: Determine the first child value based on the trajectory information and vehicle information corresponding to the target planning trajectory; According to the confidence level and the minimum longitudinal length of the trajectory of other target objects, the longitudinal constraint value of other target objects is determined as the second child value; According to the confidence level and minimum lateral length of the trajectories of other targets, the lateral constraint values ​​of other targets are determined as the third child value; The cost value corresponding to each planning trajectory is determined according to the first child value, the second child value and the third child value.

3. The method according to claim 2, characterized in that The trajectory information corresponding to the target planning trajectory includes: time loss, current lateral acceleration, current longitudinal acceleration, end lane information, and lane width; The vehicle information includes: a first distance between the vehicle and the center of the lane, a second distance between the vehicle and the nearest line, the vehicle speed, a road speed threshold of the lane, a minimum longitudinal distance between the vehicle and other target vehicles, and a minimum lateral distance between the vehicle and other target vehicles.

4. The method according to claim 1, characterized in that: Determine the confidence of other target object trajectories corresponding to the target planning trajectory, including: If the end point corresponding to the target planning trajectory is on the vehicle's own lane, the confidence of the trajectory of other target objects is determined to be 1; If the end point corresponding to the target planning trajectory is not on the self-lane of the vehicle, the longitudinal other target trajectory confidence is determined according to the longitudinal other target trajectory initial confidence, target duration and trajectory confidence unit increment; the lateral other target trajectory confidence is determined according to the lateral other target trajectory initial confidence, target duration and trajectory confidence unit increment; the sum of the longitudinal other target trajectory confidence and the lateral other target trajectory confidence is used as the other target trajectory confidence; The target duration is the duration between the start of planning and the target time. If the current time is less than the time when the vehicle crosses the line, the target time is the current time. If the current time is greater than the time when the vehicle crosses the line, the target time is the time when the vehicle crosses the line. The confidence level of the longitudinal other target object trajectories is not greater than a first threshold, the confidence level of the lateral other target object trajectories is not greater than a second threshold, and the sum of the first threshold and the second threshold is 1.

5. The method according to claim 4, characterized in that Also includes: At the beginning of planning, determine whether other targets in the adjacent lanes meet preset conditions, which are: the distance between other targets and vehicles in the adjacent lanes is greater than a preset distance, and the collision time of other targets is greater than a preset collision time threshold; or there is no vehicle in the adjacent lanes of other targets; If the preset conditions are met, the initial confidence values ​​of the longitudinal other target object trajectories are determined to be 0, and the initial confidence values ​​of the lateral other target object trajectories are determined to be 0; If the preset condition is not met, it is determined that the initial confidence value of the lateral other target object trajectories is taken as the second threshold, and the initial confidence value of the longitudinal other target object trajectories is taken as 0.

6. The method according to claim 1, characterized in that Determine the minimum horizontal length and minimum vertical length corresponding to the target planning trajectory, including: According to the target planning trajectory and the predicted trajectory corresponding to the other target objects, determine the third coordinate of the self-vehicle in the target coordinate system and the fourth coordinate of the other target objects in the target coordinate system at the moment when the distance between the vehicles is the shortest; Determine the danger zone corresponding to the third coordinate of the ego vehicle in the target coordinate system; Determine a minimum lateral length according to the lateral lateral lateral area of ​​the lateral lateral area and the fourth coordinates of other targets in the target coordinate system; The minimum longitudinal length is determined according to the longitudinal length of the dangerous area and fourth coordinates of other targets in the target coordinate system.

7. The method according to claim 6, characterized in that The determining of the danger zone corresponding to the third coordinate of the vehicle in the target coordinate system includes: A longitudinal danger zone is constructed according to the braking distance, wherein the braking distance is determined according to the maximum deceleration and the vehicle speed to determine the distance for braking at the maximum deceleration; Constructing a lateral danger zone according to a preset width, wherein the preset width is a preset multiple of the body width of the vehicle; The longitudinal danger zone and the lateral danger zone are mapped to a target coordinate system to obtain a danger zone corresponding to a third coordinate of the vehicle in the target coordinate system.

8. A path planning device, characterized in that: include: an acquisition module, used to acquire a first coordinate of the vehicle and a second coordinate corresponding to at least one end point in a target coordinate system, wherein the target coordinate system is a coordinate system composed of a speed axis, an S axis and an L axis, and the speed axis is perpendicular to the S axis and the L axis; A first determination module, configured to determine a plurality of planned trajectories in the target coordinate system according to the first coordinate of the ego vehicle and the second coordinate corresponding to the at least one end point; The second determination module is used to determine the confidence, minimum lateral length, and minimum longitudinal length of other target object trajectories corresponding to the target planning trajectory, wherein the minimum lateral length is the distance from the shortest distance between the target planning trajectory and the other target object trajectories projected to the lateral danger area of ​​the vehicle in the target coordinate system, and the minimum longitudinal length is the distance from the shortest distance between the target planning trajectory and the other target object trajectories projected to the longitudinal danger area of ​​the vehicle in the target coordinate system; the target planning trajectory is any trajectory among the multiple planning trajectories; The third determination module is used to determine the cost value corresponding to the target planning trajectory according to the trajectory information corresponding to the target planning trajectory, the vehicle information, and the trajectory confidence, minimum lateral length, and minimum longitudinal length of other target objects; The path screening module is used to determine the optimal planned trajectory from the multiple planned trajectories according to the cost values ​​corresponding to the multiple planned trajectories, so as to control the driving of the vehicle in the next time frame based on the optimal planned trajectory.

9. An electronic device, characterized in that: include: one or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more applications are configured to: perform the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The storage medium stores at least one instruction, at least one program, code set or instruction set, and the at least one instruction, at least one program, code set or instruction set is loaded by the processor and executes the steps of the method according to any one of claims 1 to 7.

Images