Vehicle drivable area generation method, apparatus, device, and medium

Abstract

The present disclosure relates to a vehicle drivable area generation method, device, equipment and medium. The method comprises: obtaining environment perception information, wherein the environment perception information comprises at least two of lane information, obstacle information and vehicle information, and the obstacle information comprises static obstacle information and / or dynamic obstacle information; determining lane decision semantic information of each lane based on the environment perception information, wherein the lane decision semantic information comprises a passing time cost and a safety cost; and generating a drivable area based on the lane decision semantic information. The embodiment of the present disclosure generates a drivable area based on lane decision semantic information, can quickly generate a drivable area with high passing and safety, accelerates the generation of a driving trajectory, and is suitable for the processing of obstacles in a dynamic environment.

Description

Technical Field

[0001] This disclosure relates to the field of autonomous driving technology, and in particular to a method, apparatus, device and medium for generating a vehicle drivable area. Background Technology

[0002] With the development of vehicle intelligence technology, autonomous vehicle control technology has gradually become a hot topic in the field of vehicle research. Autonomous driving systems need to plan smooth, safe, and passable paths to ensure that vehicles do not collide with obstacles.

[0003] In optimization-based planning algorithms, Julius Ziegler proposed an optimization method in Cartesian space, which can transform a planning problem into an optimization problem. However, this method significantly increases the computational burden on the planning module, cannot solve fast obstacle avoidance problems, reduces the trajectory generation speed, and is not suitable for handling obstacles in dynamic environments. Summary of the Invention

[0004] In order to solve the above-mentioned technical problems, or at least partially solve the above-mentioned technical problems, this disclosure provides a method, apparatus, device and medium for generating a vehicle drivable area.

[0005] This disclosure provides a method for generating a drivable area for a vehicle, including:

[0006] Acquire environmental perception information, wherein the environmental perception information includes at least two of lane information, obstacle information, and vehicle information, and the obstacle information includes static obstacle information and / or dynamic obstacle information;

[0007] Based on the environmental perception information, lane decision semantic information for each lane is determined, wherein the lane decision semantic information includes time cost and safety cost.

[0008] Based on the lane decision semantic information, a drivable area is generated.

[0009] This disclosure provides a vehicle drivable area generation apparatus, including:

[0010] A perception information acquisition module is used to acquire environmental perception information, wherein the environmental perception information includes at least two of lane information, obstacle information and vehicle information, and the obstacle information includes static obstacle information and / or dynamic obstacle information;

[0011] The lane decision semantic information determination module is used to determine the lane decision semantic information of each lane based on the environmental perception information, wherein the lane decision semantic information includes the time cost and the safety cost.

[0012] The drivable area generation module is used to generate a drivable area based on the lane decision semantic information.

[0013] This disclosure provides an electronic device, including:

[0014] Memory and one or more processors;

[0015] The memory is communicatively connected to the one or more processors, and the memory stores instructions that can be executed by the one or more processors. When the instructions are executed by the one or more processors, the electronic device is used to implement the vehicle drivable area generation method provided in any embodiment of this disclosure.

[0016] This disclosure provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a computing device, can be used to implement the vehicle drivable area generation method provided in any embodiment of this disclosure.

[0017] The technical solution provided in this disclosure has the following advantages compared with the prior art:

[0018] The technical solution provided in this disclosure determines lane decision semantic information for each lane based on environmental perception information, and transforms the lane decision semantic information into the constraint boundary of the drivable area, taking into account both passability and safety. It can quickly generate drivable areas with high passability and safety, accelerate the generation of driving trajectories, and achieve rapid obstacle avoidance. At the same time, both time cost and safety cost can characterize the passage cost of dynamic obstacles, and time cost can also characterize the passage cost of static obstacles. Therefore, the technical solution of this disclosure generates drivable areas based on time cost and safety cost, and can simultaneously realize passage planning for both dynamic and static obstacles, and is applicable to the handling of obstacles in dynamic environments. Attached Figure Description

[0019] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0020] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 A functional block diagram of a decision planning module provided in an embodiment of this disclosure;

[0022] Figure 2 A flowchart illustrating the method for generating a drivable area for a vehicle provided in this embodiment of the disclosure;

[0023] Figure 3 A scenario diagram corresponding to the lane passage time cost provided in this embodiment of the disclosure;

[0024] Figure 4 ST diagram for lane safety assessment provided in this embodiment of the disclosure;

[0025] Figure 5 A schematic diagram of the discretization of the drivable area boundary provided in an embodiment of this disclosure;

[0026] Figure 6 This is a scenario diagram corresponding to the lane width toll cost provided in the embodiments of this disclosure;

[0027] Figure 7 This is a schematic diagram illustrating an embodiment of the present disclosure that updates a drivable area based on preset traffic rules.

[0028] Figure 8 A schematic diagram illustrating the kinematic and dynamic constraints of a vehicle for updating the drivable area, as provided in an embodiment of this disclosure;

[0029] Figure 9 This is a schematic diagram illustrating the updating of obstacle semantic information and preset safe zone to a drivable area, as provided in an embodiment of this disclosure.

[0030] Figure 10 A schematic diagram illustrating the generation of a Frenet bounding box provided in an embodiment of this disclosure;

[0031] Figure 11 A schematic diagram illustrating static obstacle information, obstacle decision semantic information, and ray tracing algorithm updates of a drivable area, provided in an embodiment of this disclosure;

[0032] Figure 12 This is a functional block diagram of a vehicle drivable area generation device provided in an embodiment of the present disclosure;

[0033] Figure 13 This is a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of this disclosure. Detailed Implementation

[0034] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0035] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0036] This disclosure provides a method for generating a drivable area for a vehicle. This method is applicable to situations where an autonomous vehicle generates a drivable area for static and / or dynamic obstacles. The method can be executed by a drivable space generator. In some embodiments, Figure 1 A functional block diagram of a decision-making and planning module is shown. For example... Figure 1 As shown, the decision planning module 1 may include a constraint generation unit 11, a trajectory generation unit 12, and a trajectory smoothing unit 13. The constraint generation unit 11 includes a base coordinate system generator 111, a guide line generator 112, an obstacle decision-maker 113, and a driving space generator 114. The base coordinate system generator 111 generates a base coordinate system, such as the Frenet coordinate system; the guide line generator 112 generates guide lines to determine a general future driving trajectory for the vehicle; the obstacle decision-maker 113 makes obstacle decisions; and the driving space generator 114 generates a drivable area based on the obstacle decisions. In some embodiments, the trajectory generation unit 12 generates the driving trajectory of the autonomous vehicle based on the drivable area; and the trajectory smoothing unit 13 smooths the driving trajectory. In some embodiments, the driving space generator 114 is specifically used to: acquire environmental perception information; determine lane decision semantic information for each lane based on the environmental perception information, wherein the lane decision semantic information includes time cost and safety cost; and generate a drivable area based on the lane decision semantic information.

[0037] Based on the above technical solutions Figure 2 This is a flowchart illustrating a method for generating a drivable area for a vehicle, as provided in an embodiment of this disclosure. Figure 2 As shown, the method includes the following steps:

[0038] S110. Obtain environmental perception information.

[0039] The environmental perception information includes at least two of lane information, obstacle information, and vehicle information. The obstacle information includes static obstacle information and / or dynamic obstacle information. In some embodiments, lane information may include lane line information and road boundary information, which can be acquired using an onboard camera; obstacle information may include obstacle location information, obstacle size information, and obstacle motion information, wherein obstacle location information can be acquired using a high-precision map and an onboard camera / LiDAR, obstacle size information can be acquired using an onboard camera, and obstacle motion information can be acquired using an onboard camera and / or LiDAR; vehicle information may include vehicle location information and vehicle motion information, wherein vehicle location information can be acquired using a high-precision map and a vehicle positioning module (such as GPS), and vehicle motion information can be acquired using vehicle motion sensors (such as speed sensors and acceleration sensors).

[0040] S120. Based on environmental perception information, determine the lane decision semantic information for each lane.

[0041] The lane decision semantic information includes passage time cost and safety cost. Passage time cost is used to characterize the traffic situation of a lane; for example, if vehicles can pass through a lane quickly, then the passage time of that lane is fast. Safety cost is used to characterize the safety of a lane.

[0042] In some embodiments, the passage time cost for each lane can be determined based on the relationship between the longitudinal speed of the vehicle and the longitudinal speed of the obstacle. Accordingly, when the lane decision semantic information includes the passage time cost, the lane decision semantic information for each lane is determined based on environmental perception information, including: for each lane, determining the collision time between the vehicle and the first obstacle in front of the vehicle based on environmental perception information; and determining the collision time as the passage time cost.

[0043] Specifically, the environmental perception information includes the vehicle's position information and longitudinal speed information, as well as the obstacle position information and longitudinal speed information of the nearest obstacle ahead in each lane. Based on the vehicle's position information and obstacle position information, the longitudinal distance from the vehicle to the nearest obstacle ahead in each lane is calculated. Based on the vehicle's longitudinal speed information and the obstacle's longitudinal speed information, it is determined whether the obstacle's longitudinal speed is less than the vehicle's longitudinal speed. When the obstacle's longitudinal speed is less than the vehicle's longitudinal speed, the collision time when the vehicle collides with the obstacle ahead is predicted based on the longitudinal distance, the vehicle's longitudinal speed information, and the obstacle's longitudinal speed information, and this collision time is determined as the passage time cost. Furthermore, if there is no obstacle ahead of the vehicle or the longitudinal speed of the first obstacle ahead of the vehicle is greater than or equal to the vehicle's longitudinal speed, a preset duration is determined as the passage time cost. Based on the above technical solution, the passage time cost can be calculated using the following formula:

[0044]

[0045] Where TCC is the time cost, v adv v is the longitudinal speed of the vehicle. obs TCC is the longitudinal velocity of the obstacle. max The preset duration is a fixed value, greater than the collision time, for example, 1000 (this is just a numerical value; the unit is the same as the collision time, such as seconds or milliseconds). From this formula, it can be seen that the lower the longitudinal velocity of the first obstacle in front of the vehicle, the lower the time cost of passing through, and the worse the passability of the corresponding lane. When there is no obstacle in front of the vehicle, or when the longitudinal velocity of the first obstacle in front of the vehicle is greater than or equal to the longitudinal velocity of the vehicle, the vehicle will not collide with the obstacle in the corresponding lane, and the passability of the corresponding lane is optimal.

[0046] For example, such as Figure 3 As shown, in lanes traveling in the same direction, the first obstacle in front of this vehicle is obstacle 1, and in the adjacent lane, the first obstacle in front of this vehicle is obstacle 2. The longitudinal speed of this vehicle is 5 m / s, the longitudinal speed of obstacle 1 is 1 m / s, and the longitudinal speed of obstacle 2 is 10 m / s. For this vehicle's lane, the longitudinal speed of obstacle 1 is less than the longitudinal speed of this vehicle, so a collision will occur. At this time, the distance D between this vehicle and obstacle 1 is determined to be 16 m. According to the above formula, the collision time between this vehicle and obstacle 1 is determined to be 4 seconds. Therefore, the time cost for passing through this vehicle's lane is 4. For the adjacent lane, the longitudinal speed of obstacle 2 is greater than the longitudinal speed of this vehicle, so a collision will not occur. At this time, the time cost for passing through the adjacent lane is a preset duration, such as 10000. Therefore, it can be determined that the time cost for passing through the adjacent lane is greater than the time cost for passing through this vehicle's lane, meaning the adjacent lane has better passability.

[0047] In some embodiments, to ensure vehicle safety, it is also necessary to determine the safety cost of each lane. Accordingly, when the lane decision semantic information includes the safety cost, the lane decision semantic information for each lane is determined based on environmental perception information, including: determining the vehicle's lane and other lanes based on lane information and vehicle information; for the vehicle's lane, determining a first preset safety cost as the safety cost; for other lanes, if based on environmental perception information it is determined that an obstacle enters the vehicle's danger zone within a preset time, then a second preset safety cost is determined as the safety cost; if based on environmental perception information it is determined that an obstacle does not enter the vehicle's danger zone within a preset time, then the first preset safety cost is determined as the safety cost, wherein the second preset safety cost is different from the first preset safety cost.

[0048] Specifically, environmental perception information includes lane information, vehicle information, and obstacle information. Based on lane and vehicle information, the system determines the vehicle's lane and other lanes. For the vehicle's lane, it is assumed that the vehicle has absolute right-of-way, meaning the lane in which the vehicle is located has the highest safety. For other lanes, the system assesses the safety of obstacles within the vehicle's observation area. If it is predicted that an obstacle within the vehicle's observation area will enter the vehicle's danger zone within a certain period of time (i.e., a preset time), it indicates that the lane in which the obstacle is currently located has low safety. If it is predicted that an obstacle within the vehicle's observation area will not enter the vehicle's danger zone within a certain period of time, it indicates that the lane in which the obstacle is currently located has high safety.

[0049] It is understood that the safety of the lane corresponding to the second preset safety cost is lower than the safety of the lane corresponding to the first preset safety cost. In some embodiments, the second preset safety cost is less than the first preset safety cost. In some embodiments, a penalty mechanism may be used to assign values ​​to the first preset safety cost and the second preset safety cost, for example, the first preset safety cost is 0 and the second preset safety cost is -100000.

[0050] Based on the above technical solution, an ST diagram (longitudinal displacement-time diagram) can be used to determine whether obstacles in other lanes will enter the vehicle's danger zone within a future period. In some embodiments, based on environmental perception information, the vehicle's ST diagram curve and the obstacle's ST diagram curve are determined; based on the vehicle's ST diagram curve, the vehicle's danger zone is determined; it is determined whether the obstacle's ST diagram curve overlaps with the vehicle's danger zone within a preset time period; if the obstacle's ST diagram curve overlaps with the vehicle's danger zone within the preset time period, it is determined that the obstacle entered the vehicle's danger zone within the preset time period; otherwise, it is determined that the obstacle did not enter the vehicle's danger zone within the preset time period. For example, as shown... Figure 4 As shown, the ST curve of this vehicle is the curve indicated by this vehicle in the diagram. The ST curves of the obstacles include the curves indicated by obstacles 1, 2, 3, and 4 in the diagram. The danger zone of this vehicle includes the danger zone behind this vehicle (the area corresponding to interval L2) and the danger zone in front of this vehicle (the area corresponding to interval L3). The observation zone of this vehicle includes the observation zone behind this vehicle (the area corresponding to interval L1) and the observation zone in front of this vehicle (the area corresponding to interval L4). The preset time is T_e. Optionally, L1 is 100 meters, L2 is 20 meters, L3 is 10 meters, L4 is 100 meters, and T_e is 6 seconds. See also Figure 4Based on the ST curves of the vehicle and each obstacle, it can be seen that the ST curve of obstacle 2 in the rear observation area overlaps with the rear danger zone of the vehicle within a preset time T_e. The ST curve of obstacle 1 in the rear observation area does not overlap with the rear danger zone of the vehicle within a preset time T_e. The ST curve of obstacle 3 in the front observation area overlaps with the front danger zone of the vehicle within a preset time T_e. The ST curve of obstacle 4 in the front observation area does not overlap with the front danger zone of the vehicle within a preset time T_e. Therefore, it can be concluded that obstacles 2 and 3 entered the vehicle's danger zone within the preset time, and the lanes in which obstacles 2 and 3 are located at the current moment have low safety, meaning the safety cost of the corresponding lanes is the second preset safety cost. On the other hand, obstacles 1 and 4 did not enter the vehicle's danger zone within the preset time, and the lanes in which obstacles 1 and 4 are located at the current moment have high safety, meaning the safety cost of the corresponding lanes is the first preset safety cost. It should be noted that the overlap between the obstacle ST curve and the vehicle's danger zone includes situations where the obstacle ST curve is entirely within the vehicle's danger zone, or where a portion of the obstacle ST curve is within the vehicle's danger zone. In the above embodiment, to simplify calculations, the obstacle is assumed to move at a constant speed, the obstacle ST curve is a straight line, and the vehicle's danger zone is a parallelogram, both being convex hull types. Thus, a collision detection algorithm based on the Gilbert–Johnson–Keerthi algorithm can be used to quickly calculate whether the obstacle will enter the vehicle's danger zone within a preset time T_e.

[0051] S130. Based on lane decision semantic information, generate a drivable area.

[0052] For each lane, embodiments of this disclosure can generate a drivable area based on both transit time cost and safety cost, thereby selecting a lane that balances transit time and safety.

[0053] In some embodiments, the costs in the lane decision semantic information can be weighted and summed; based on the weighted summation result, a drivable area is generated. In this embodiment, the time cost and safety cost are weighted and summed to obtain the weighted summation result. For example:

[0054] f = w1f pass +w2f safe ;

[0055] Where f is the weighted summation result (or weighted summation value), f pass To achieve this through time cost, f safeAs a safety cost, w1 represents the weight of the time cost, and w2 represents the weight of the safety cost. w1 and w2 can be obtained from simulation or actual vehicle testing experiments. Based on this technical solution, embodiments of this disclosure can determine the lane with the largest weighted sum as the drivable area.

[0056] In some embodiments, to facilitate the planner's reception of the drivable area, the boundary of the drivable area is discretized, forming drivable area boundary points, including left and right boundary points. For example, the drivable area can be discretized at a fixed resolution based on the Frener coordinate system. Figure 5 As shown, based on lane decision information and the Frena coordinate system constructed from the lane center curve, the left and right boundaries of the drivable area are generated at a fixed resolution. The left boundary represents the upper bound of the L value in the Frena coordinate system, and the right boundary represents the lower bound of the L value in the Frena coordinate system. The longitudinal distance between two adjacent left boundary points or two adjacent right boundary points is the aforementioned fixed resolution. Figure 5 This indicates that the vehicle is in the right lane, and the lane decision result is also the right lane, so the left and right boundaries of the drivable area are as follows: Figure 5 As shown. If the lane decision results in a lane change, then the drivable area at this time includes two lanes.

[0057] The vehicle drivable area generation method provided in this disclosure determines lane decision semantic information for each lane based on environmental perception information, and converts the lane decision semantic information into constraint boundaries of the drivable area. It takes into account both passability and safety, and can quickly generate drivable areas with high passability and safety, accelerate the generation of driving trajectories, and achieve rapid obstacle avoidance. At the same time, both time cost and safety cost can characterize the passage cost of dynamic obstacles, and time cost can also characterize the passage cost of static obstacles. Therefore, the technical solution of this disclosure generates drivable areas based on time cost and safety cost, and can simultaneously realize passage planning for both dynamic and static obstacles, and is applicable to obstacle handling in dynamic environments.

[0058] Based on the above technical solution, when the drivable area determined based on lane decision semantic information includes at least two lanes, and at least two lanes have static obstacles, an optimal lane can be further selected based on the passage width cost. In some embodiments, the lane decision semantic information also includes a passage width cost. Based on environmental perception information, the lane decision semantic information for each lane is determined, including: determining the minimum passage width of the lane based on lane information and static obstacle information; and determining the minimum passage width as the passage width cost. The passage width cost is used to characterize the congestion of the lane by static obstacles in front of the vehicle. In some embodiments, determining the minimum passage width of the lane based on lane information and static obstacle information includes: determining the maximum passage width of each static obstacle on the lane based on lane information and static obstacle information; and determining the minimum value among the maximum passage widths of each static obstacle as the minimum passage width of the lane.

[0059] Specifically, a Frena coordinate system is established, and each static obstacle is projected into the Frena coordinate system to generate the SL bounding box for each obstacle. For each lane, the left and right passage widths of each static obstacle are calculated. The maximum passage width of each static obstacle is determined from the left and right passage widths. The minimum maximum passage width is selected from all the maximum passage widths of static obstacles as the minimum passage width of the lane, and this minimum passage width is determined as the passage width cost. The larger this passage width cost, the less congestion the static obstacle causes to the lane. For example, as shown... Figure 6 As shown, the lane for this vehicle includes obstacle 1 and obstacle 2, and the adjacent lane includes obstacle 3 (obstacles 1, 2, and 3 are all static obstacles). The maximum passage width of obstacle 1 is d1, the maximum passage width of obstacle 2 is d2, and the maximum passage width of obstacle 3 is d3. Since d1 is less than d2 and d2 is less than d3, the minimum passage width for this vehicle's lane is d1, meaning the passage width cost for this lane is d1. The minimum passage width for the adjacent lane is d3, meaning the passage width cost for the adjacent lane is d3. At this point, the obstruction level of the adjacent lane is less than that of the lane for this vehicle. Therefore, adjacent lanes can be further selected to generate a drivable area.

[0060] Based on the above technical solution, when the optimal drivable area cannot be determined based on the costs in the lane decision semantic information, in order to ensure the stability of the vehicle's trajectory, a stability cost is added to the lane decision semantic information to preferentially select the vehicle's lane to generate the drivable area. Correspondingly, in some embodiments, the lane decision semantic information also includes a stability cost. Based on environmental perception information, the lane decision semantic information for each lane is determined, including: determining the vehicle's lane and other lanes based on lane information and vehicle information; for the vehicle's lane, a first preset stability cost is determined as the stability cost; for other lanes, a second preset stability cost is determined as the stability cost, wherein the second preset stability cost is different from the first preset stability cost. In this technical solution, the first preset stability cost can be greater than the second preset stability cost, wherein the first preset stability cost can be 100, and the second preset stability cost can be 0.

[0061] Based on the above embodiments, the costs in the lane decision semantic information are weighted and summed to obtain the weighted sum result, which can be calculated using the following formula:

[0062] f = w1f pass +w2f safe +w3f narrow +w4f stable ;

[0063] Among them, f narrow For the cost of passage width, f stable w3 is the weight of the traffic width cost, and w4 is the weight of the stability cost.

[0064] Based on the above technical solution, in some embodiments, after generating the drivable area based on lane decision semantic information, the method further includes at least one of the following:

[0065] Update the drivable area based on preset traffic rules;

[0066] The drivable area is updated based on the vehicle's kinematic and dynamic constraints;

[0067] Based on obstacle semantic information and preset safe zones, update the drivable area, and connect the preset safe zone with the drivable area;

[0068] Based on static obstacle information, obstacle decision semantic information, and ray tracing algorithm, the drivable area is updated. The obstacle decision semantic information includes whether to pass the obstacle on the left or the obstacle on the right.

[0069] Specifically, in some embodiments, it can be determined whether a drivable area violates traffic rules based on preset traffic rules, and then the drivable area that violates traffic rules can be trimmed to update the drivable area. In this embodiment of the disclosure, the preset traffic rules may include common traffic rules such as solid and dashed yellow lines, solid and dashed white lines, and lane markings. For example, Figure 7 As shown, after lane decision-making, the vehicle will choose to change lanes, so the two lanes during the lane-changing process are initially used as the drivable area, i.e., the original drivable area. However, since the end of the lane is a solid line, the drivable area will be trimmed based on preset traffic rules, resulting in... Figure 7 The black dots represent the drivable area defined by the boundary points, which is the updated drivable area.

[0070] In some embodiments, the drivable area can also be updated based on the vehicle's kinematic and dynamic constraints. For example, when a vehicle temporarily uses another lane, the drivable area is updated by adding an additional drivable area based on the vehicle's kinematic and dynamic constraints. Figure 8 As shown, the angle between the heading angle of this vehicle and the heading angle of the road network is Δθ, and the curvature of this vehicle at its lane position is k. r The L-coordinate of this vehicle in the Frener coordinate system is d. Therefore, according to the Frener kinematic equations, the lateral velocity of this vehicle relative to the Frener coordinate system is d′=(1-k r d)tan(Δθ), the transverse acceleration is

[0071]

[0072] Where, k ADV Given the wheel angle δ of the autonomous bicycle model, and the curve curvature of the vehicle's trajectory, and the wheelbase of the vehicle being B, then... k r Let ′ be the rate of change of curvature of the road network. For approximate calculation, let k r =0, in order to calculate the additional dable area. extra Assuming the final lateral velocity of the car in the Frena coordinate system is 0, then based on the kinematics of the Frena coordinate system, we have: Thus, the drivable area is expanded outwards by calculating the additional drivable area in order to update the drivable area.

[0073] In some embodiments, considering that there may be dynamic obstacles on adjacent lanes affecting the drivable area, which may result in the drivable area not being absolutely safe, the areas of the drivable area that may be affected by dynamic obstacles can be trimmed to ensure the safety of the remaining drivable area.

[0074] Specifically, based on obstacle semantic information, obstacles requiring lateral avoidance are identified. If the trajectory of the obstacle requiring lateral avoidance occupies a preset safety zone, the portion of the drivable area corresponding to the location occupying the preset safety zone is trimmed. In this embodiment, obstacle semantic information may include information characterizing the obstacle's movement state, such as obstacle merging, obstacle crossing, obstacle parallel travel, and obstacle reverse travel. Based on the obstacle semantic information, the vehicle automatically determines whether lateral avoidance of the obstacle is necessary. For example, if the obstacle semantic information determines that it is merging, the vehicle does not need to laterally avoid the obstacle; if the obstacle semantic information determines that it is too close to the vehicle's lane, the vehicle needs to laterally avoid the obstacle. For example, as shown... Figure 9 As shown, preset safety zones are added on both sides of the drivable area (if the drivable area is adjacent to the road boundary, a preset safety zone can be added only on the inside of the drivable area). It is determined whether the obstacle prediction module (in the previous module, not covered in this disclosure) outputs an obstacle's movement trajectory that occupies the preset safety zone. If the movement trajectory occupies the preset safety zone, the portion of the drivable area corresponding to the location occupying the preset safety zone is trimmed, such as... Figure 9 The trimmed areas are used to update the drivable areas.

[0075] In some embodiments, since the drivable area obtained in the above embodiments still includes the area where the static obstacle is located, it does not meet the obstacle avoidance constraint. Therefore, it is necessary to further trim the area where the static obstacle is located from the drivable area to update the drivable area. In order to avoid the problem that the existing solution uses Freyner bounding boxes to generate an approximate drivable area, which leads to a decrease in vehicle passability, the present disclosure combines obstacle decision semantic information and ray tracing algorithm to accurately determine the area where the static obstacle is located.

[0076] Specifically, the drivable area is updated based on static obstacle information, obstacle decision semantic information, and a ray tracing algorithm. This includes: determining the collision point between the ray and the obstacle based on the static obstacle information, obstacle decision semantic information, and the ray tracing algorithm, wherein the collision point is located within the drivable area; and updating the drivable area based on the collision point. In some embodiments, determining the collision point between the ray and the obstacle based on the static obstacle information, obstacle decision semantic information, and the ray tracing algorithm includes: determining the light source point and the ray projection direction based on the obstacle decision semantic information; determining the ray projection range based on the static obstacle information; scanning the obstacle with rays based on the light source point, the ray projection direction, and the ray projection range; and determining the collision point between the ray and the obstacle. In some embodiments, the ray tracing algorithm may employ a ray projection algorithm based on the Gilbert–Johnson–Keerthi algorithm to improve the solution accuracy.

[0077] For example, obstacle decision semantic information includes passing from the left or right side of the obstacle. When the obstacle decision semantic information indicates passing from the left, the light source is determined to be located to the left of the static obstacle, and the light projection direction is perpendicular to the lane travel direction and towards the static obstacle; when the obstacle decision semantic information indicates passing from the right, the light source is determined to be located to the right of the static obstacle, and the light projection direction is perpendicular to the lane travel direction and towards the static obstacle. Based on static obstacle information, such as the location and size information of the static obstacle, the area where the static obstacle is located can be determined, thereby determining the light projection range. After determining the collision point between the light and the obstacle, the drivable area defined by each collision point is trimmed. This disclosure does not limit the specific location of the light source; in some embodiments, the light source may be located at the boundary point of the drivable area.

[0078] In one specific embodiment, such as Figure 10 As shown, the Frenet bounding box of the static obstacle, box_sl = {S_min, S_max, L_min, L_max}, can be determined first. Based on the Frenet bounding box, the ID range of the static obstacle in the longitudinal direction of the drivable area is determined. When the resolution of the boundary point of the drivable area is Δs, the above ID range is (id_start, id_end), which is the ray projection range, where id_start = floor(s_min / Δs), id_end = ceil(s_max / Δs), floor represents the rounding down operation of a floating-point number, and ceil represents the rounding up operation of a floating-point number. It should be noted that this embodiment only uses the Frenet bounding box to determine the ray projection range that can contain the entire static obstacle to ensure that the ray completely scans the obstacle. The collision point determined subsequently is located on the static obstacle, not on the boundary of the Frenet bounding box. Figure 11As shown, the drivable area contains two static obstacles, namely obstacle 1 and obstacle 2. Based on the obstacle decision semantic information of obstacle 1, it can be determined that the vehicle will pass from the right side of obstacle 1, and based on the obstacle decision semantic information of obstacle 2, it can be determined that the vehicle will pass from the left side of obstacle 2. Taking obstacle 1 as an example, based on the obstacle decision semantic information of obstacle 1, the point light source is determined to be located at the right boundary point of the drivable area. Based on the static obstacle information of obstacle 1, the light projection range of the light source onto obstacle 1 is determined, i.e., the aforementioned ID range. Thus, the point light source can scan obstacle 1 sequentially according to the ID range. Specifically, when the light collides with obstacle 1, if the collision point is within the drivable area, the drivable area on the side away from the point light source from the collision point is trimmed. This process continues until the scanning of the light projection range is completed. Using the above technical solution, while ensuring that the drivable area meets obstacle avoidance constraints, the accuracy of solving for the area occupied by static obstacles within the drivable area can be improved, thereby improving the vehicle's passability.

[0079] Figure 12 This is a functional block diagram of a vehicle drivable area generation device provided in an embodiment of this disclosure. Figure 12 As shown, the vehicle drivable area generation device includes a perception information acquisition module 201, a lane decision semantic information determination module 202, and a drivable area generation module 203.

[0080] The perception information acquisition module 201 is used to acquire environmental perception information, which includes at least two of lane information, obstacle information and vehicle information, and the obstacle information includes static obstacle information and / or dynamic obstacle information.

[0081] The lane decision semantic information determination module 202 is used to determine the lane decision semantic information of each lane based on environmental perception information, wherein the lane decision semantic information includes the time cost and the safety cost.

[0082] The drivable area generation module 203 is used to generate drivable areas based on lane decision semantic information.

[0083] In some embodiments, when the lane decision semantic information includes a passage time cost, the lane decision semantic information determination module 202 is specifically used for:

[0084] For each lane, based on environmental perception information, determine the collision time between the vehicle and the first obstacle in front of it;

[0085] The collision time is defined as the time cost of passage.

[0086] In some embodiments, the lane decision semantic information determination module 202 is further configured to:

[0087] If, based on environmental perception information, it is determined that there are no obstacles in front of the vehicle or that the longitudinal speed of the first obstacle in front of the vehicle is greater than or equal to the longitudinal speed of the vehicle, then the preset duration is determined as the time cost for passing through.

[0088] In some embodiments, when the lane decision semantic information includes a safety cost, the lane decision semantic information determination module 202 is specifically used for:

[0089] Based on lane information and vehicle information, determine the vehicle's lane and other lanes;

[0090] For this vehicle's lane, the first preset safety cost is determined as the safety cost;

[0091] For other lanes, if based on environmental perception information it is determined that an obstacle enters the vehicle's danger zone within a preset time, then the second preset safety cost is determined as the safety cost. If based on environmental perception information it is determined that an obstacle does not enter the vehicle's danger zone within a preset time, then the first preset safety cost is determined as the safety cost. The second preset safety cost is different from the first preset safety cost.

[0092] In some embodiments, the lane decision semantic information determination module 202 is specifically used for:

[0093] Based on environmental perception information, determine the ST curve of the vehicle and the ST curve of the obstacle;

[0094] Based on the ST diagram curve of this vehicle, the danger zone of this vehicle is determined;

[0095] Determine whether the ST curve of the obstacle overlaps with the vehicle's danger zone within a preset time period;

[0096] If the obstacle ST curve overlaps with the vehicle's danger zone within the preset time, it is determined that the obstacle entered the vehicle's danger zone within the preset time; otherwise, it is determined that the obstacle did not enter the vehicle's danger zone within the preset time.

[0097] In some embodiments, the lane decision semantic information further includes a traffic width cost, and the lane decision semantic information determination module 202 is specifically used for:

[0098] Based on lane information and static obstacle information, determine the minimum passage width of the lane;

[0099] The minimum passage width is determined as the passage width cost.

[0100] In some embodiments, the lane decision semantic information determination module 202 is specifically used for:

[0101] Based on lane information and static obstacle information, determine the maximum passage width for each static obstacle on the lane;

[0102] The minimum value among the maximum passage widths of all static obstacles is determined as the minimum passage width of the lane.

[0103] In some embodiments, the lane decision semantic information further includes a stability cost, and the lane decision semantic information determination module 202 is specifically used for:

[0104] Based on lane information and vehicle information, determine the vehicle's lane and other lanes;

[0105] For this vehicle's lane, the first preset stability cost is determined as the stability cost;

[0106] For other lanes, the second preset stability cost is determined as the stability cost, wherein the second preset stability cost is different from the first preset stability cost.

[0107] In some embodiments, the drivable area generation module 203 is specifically used for:

[0108] The costs in the lane decision semantic information are weighted and summed.

[0109] Based on the weighted summation result, a drivable region is generated.

[0110] In some embodiments, the above-described apparatus further includes:

[0111] The discrete module is used to discretize the boundaries of the drivable area after generating the drivable area based on lane decision semantic information.

[0112] In some embodiments, the above-described apparatus further includes a drivable area update module, which, after generating a drivable area based on lane decision semantic information, is specifically used for at least one of the following update operations:

[0113] Update the drivable area based on preset traffic rules;

[0114] The drivable area is updated based on the vehicle's kinematic and dynamic constraints;

[0115] Based on obstacle semantic information and preset safe zones, update the drivable area, and connect the preset safe zone with the drivable area;

[0116] Based on static obstacle information, obstacle decision semantic information, and ray tracing algorithm, the drivable area is updated. The obstacle decision semantic information includes whether to pass from the left or right side of the obstacle.

[0117] In some embodiments, the drivable area update module is specifically used for:

[0118] Based on the semantic information of obstacles, identify the obstacles that need to be avoided laterally;

[0119] If the trajectory of an obstacle that needs to be avoided laterally occupies the preset safety zone, then the portion of the drivable area corresponding to the location occupying the preset safety zone will be trimmed.

[0120] In some embodiments, the drivable area update module is specifically used for:

[0121] Based on static obstacle information, obstacle decision semantic information, and ray tracing algorithm, the collision point between the ray and the obstacle is determined, and the collision point is located within the drivable area.

[0122] Update the drivable area based on the collision point.

[0123] In some embodiments, the drivable area update module is specifically used for:

[0124] Based on obstacle decision semantic information, determine the light source point and the direction of light projection;

[0125] Determine the range of light projection based on static obstacle information;

[0126] The obstacle is scanned by light based on the light source point, the direction of light projection, and the range of light projection.

[0127] Determine the point of collision between the light and the obstacle.

[0128] The vehicle drivable area generation apparatus disclosed in the above embodiments can execute the vehicle drivable area generation method disclosed in the above embodiments and has the same or corresponding beneficial effects. To avoid repetition, it will not be described again here.

[0129] This disclosure also provides an electronic device, including: a memory and one or more processors; wherein the memory is communicatively connected to the one or more processors, and the memory stores instructions that can be executed by the one or more processors. When the instructions are executed by the one or more processors, the electronic device is used to implement the vehicle drivable area generation method described in any embodiment of this disclosure.

[0130] Figure 13 This is a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present disclosure. For example... Figure 13 As shown, the electronic device 300 includes a central processing unit (CPU) 301, which can execute various processes described in the foregoing embodiments according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage section 308 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the electronic device 300. The CPU 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0131] The following components are connected to I / O interface 305: an input section 306 including a keyboard, mouse, etc.; an output section 307 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN card, modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to I / O interface 305 as needed. A removable medium 311, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 310 as needed so that computer programs read from it can be installed into storage section 308 as needed.

[0132] In particular, according to embodiments of this disclosure, the methods described above can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program tangibly contained on a readable medium thereof, the computer program containing program code for performing the aforementioned obstacle avoidance method. In such embodiments, the computer program can be downloaded and installed from a network via communication section 309, and / or installed from removable medium 311.

[0133] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0134] The units or modules described in the embodiments of this disclosure can be implemented in software or hardware. The described units or modules can also be located in a processor, and the names of these units or modules do not necessarily constitute a limitation on the unit or module itself.

[0135] Furthermore, this disclosure also provides a computer-readable storage medium, which may be the computer-readable storage medium included in the apparatus described in the above embodiments; or it may be a standalone computer-readable storage medium not assembled into the device. The computer-readable storage medium stores computer-executable instructions, which, when executed by a computing device, can be used to implement the vehicle drivable area generation method described in any embodiment of this disclosure.

[0136] Option 1: A method for generating a drivable area for vehicles, comprising:

[0137] Acquire environmental perception information, wherein the environmental perception information includes at least two of lane information, obstacle information, and vehicle information, and the obstacle information includes static obstacle information and / or dynamic obstacle information;

[0138] Based on the environmental perception information, lane decision semantic information for each lane is determined, wherein the lane decision semantic information includes time cost and safety cost.

[0139] Based on the lane decision semantic information, a drivable area is generated.

[0140] Option 2: According to the method described in Option 1, when the lane decision semantic information includes the time cost of passage, based on the environmental perception information, determine the lane decision semantic information for each lane, including:

[0141] For each lane, based on the environmental perception information, the collision time between the vehicle and the first obstacle in front of the vehicle is determined;

[0142] The collision time is determined as the passage time cost.

[0143] Option 3: The method described in Option 2, further comprising:

[0144] If, based on the environmental perception information, it is determined that there are no obstacles in front of the vehicle or that the longitudinal speed of the first obstacle in front of the vehicle is greater than or equal to the longitudinal speed of the vehicle, then the preset duration is determined as the passage time cost.

[0145] Option 4: According to the method described in Option 1, when the lane decision semantic information includes safety costs, based on the environmental perception information, determine the lane decision semantic information for each lane, including:

[0146] Based on the lane information and the vehicle information, determine the vehicle's lane and other lanes;

[0147] For the lane of this vehicle, the first preset safety cost is determined as the safety cost;

[0148] For the other lanes, if based on the environmental perception information it is determined that an obstacle enters the vehicle's danger zone within a preset time, then the second preset safety cost is determined as the safety cost; if based on the environmental perception information it is determined that the obstacle does not enter the vehicle's danger zone within the preset time, then the first preset safety cost is determined as the safety cost, wherein the second preset safety cost is different from the first preset safety cost.

[0149] Option 5: The method described in Option 4 further includes:

[0150] Based on the environmental perception information, determine the ST curve of the vehicle and the ST curve of the obstacle;

[0151] Based on the ST diagram curve of this vehicle, the danger zone of this vehicle is determined;

[0152] Determine whether the ST curve of the obstacle overlaps with the danger zone of the vehicle within the preset time period;

[0153] If the ST curve of the obstacle overlaps with the vehicle's danger zone within the preset time, it is determined that the obstacle has entered the vehicle's danger zone within the preset time; otherwise, it is determined that the obstacle has not entered the vehicle's danger zone within the preset time.

[0154] Option 6: According to the method described in Option 1, the lane decision semantic information further includes traffic width cost. Based on the environmental perception information, the lane decision semantic information for each lane is determined, including:

[0155] Based on the lane information and the static obstacle information, the minimum passage width of the lane is determined;

[0156] The minimum passage width is determined as the passage width cost.

[0157] Option 7: According to the method described in Option 6, based on the lane information and the static obstacle information, determine the minimum passage width of the lane, including:

[0158] Based on the lane information and the static obstacle information, determine the maximum passage width of each static obstacle on the lane;

[0159] The minimum value among the maximum passage widths of all static obstacles is determined as the minimum passage width of the lane.

[0160] Option 8: According to the method described in Option 1 or 6, the lane decision semantic information further includes a stability cost. Based on the environmental perception information, the lane decision semantic information for each lane is determined, including:

[0161] Based on the lane information and the vehicle information, determine the vehicle's lane and other lanes;

[0162] For the lane of this vehicle, the first preset stability cost is determined as the stability cost;

[0163] For the other lanes, a second preset stability cost is determined as the stability cost, wherein the second preset stability cost is different from the first preset stability cost.

[0164] Option 9: Based on the lane decision semantic information, generate a drivable area according to the method described in Option 1, including:

[0165] The costs in the lane decision semantic information are weighted and summed.

[0166] Based on the weighted summation result, a drivable region is generated.

[0167] Option 10: According to the method described in Option 1, after generating the drivable area based on the lane decision semantic information, the method further includes:

[0168] Discretize the boundaries of the drivable region.

[0169] Solution 11: According to the method described in Solution 1, after generating the drivable area based on the lane decision semantic information, the method further includes at least one of the following:

[0170] The drivable area is updated based on preset traffic rules;

[0171] The drivable area is updated based on the vehicle's kinematic and dynamic constraints;

[0172] Based on obstacle semantic information and a preset safe zone, the drivable area is updated, and the preset safe zone is connected to the drivable area;

[0173] Based on the static obstacle information, obstacle decision semantic information, and ray tracing algorithm, the drivable area is updated. The obstacle decision semantic information includes passing through the obstacle from the left or from the obstacle from the right.

[0174] Solution 12: According to the method described in Solution 11, update the drivable area based on obstacle semantic information and a preset safe zone, including:

[0175] Based on the semantic information of obstacles, identify the obstacles that need to be avoided laterally;

[0176] If the trajectory of the obstacle that needs to be avoided laterally occupies the preset safety zone, then the portion of the drivable area corresponding to the location occupying the preset safety zone is trimmed.

[0177] Solution 13: According to the method described in Solution 11, update the drivable area based on the static obstacle information, obstacle decision semantic information, and ray tracing algorithm, including:

[0178] Based on the static obstacle information, obstacle decision semantic information, and ray tracing algorithm, the collision point between the ray and the obstacle is determined, and the collision point is located within the drivable area;

[0179] The drivable area is updated based on the collision point.

[0180] Solution 14: According to the method described in Solution 13, based on the static obstacle information, obstacle decision semantic information, and ray tracing algorithm, determine the collision point between the ray and the obstacle, including:

[0181] Based on the obstacle decision semantic information, determine the light source point and the direction of light projection;

[0182] Based on the static obstacle information, the light projection range is determined;

[0183] Based on the light source point, the light projection direction, and the light projection range, the obstacle is scanned by light.

[0184] Determine the point of collision between the light ray and the obstacle.

[0185] Option 15: A vehicle drivable area generation device, comprising:

[0186] A perception information acquisition module is used to acquire environmental perception information, wherein the environmental perception information includes at least two of lane information, obstacle information and vehicle information, and the obstacle information includes static obstacle information and / or dynamic obstacle information;

[0187] The lane decision semantic information determination module is used to determine the lane decision semantic information of each lane based on the environmental perception information, wherein the lane decision semantic information includes the time cost and the safety cost.

[0188] The drivable area generation module is used to generate a drivable area based on the lane decision semantic information.

[0189] Option 16: An electronic device, comprising:

[0190] Memory and one or more processors;

[0191] The memory is communicatively connected to the one or more processors, and the memory stores instructions that can be executed by the one or more processors. When the instructions are executed by the one or more processors, the electronic device is used to implement the vehicle drivable area generation method as described in any one of Schemes 1-14.

[0192] Solution 17: A computer-readable storage medium storing computer-executable instructions thereon, which, when executed by a computing device, can be used to implement the vehicle drivable area generation method as described in any one of Solutions 1-14.

[0193] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0194] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for generating a drivable area for vehicles, characterized in that, include: Acquire environmental perception information, wherein the environmental perception information includes at least two of lane information, obstacle information, and vehicle information, and the obstacle information includes static obstacle information and / or dynamic obstacle information; Based on the environmental perception information, lane decision semantic information for each lane is determined, wherein the lane decision semantic information includes passage time cost, passage width cost, stability cost, and safety cost; Based on the lane decision semantic information, a drivable area is generated; The boundary of the drivable area is discretized to form drivable area boundary points, wherein the drivable area boundary points include left boundary points and right boundary points; The step of determining lane decision semantic information for each lane based on the environmental perception information includes: Based on the lane information and the static obstacle information, determine the maximum passage width of each static obstacle on the lane; The minimum value among the maximum passage widths of all static obstacles is determined as the minimum passage width of the lane; The minimum passage width is determined as the passage width cost.

2. The method according to claim 1, characterized in that, When the lane decision semantic information includes the time cost of passage, based on the environmental perception information, the lane decision semantic information for each lane is determined, including: For each lane, based on the environmental perception information, the collision time between the vehicle and the first obstacle in front of the vehicle is determined; The collision time is determined as the passage time cost.

3. The method according to claim 2, characterized in that, The method further includes: If, based on the environmental perception information, it is determined that there are no obstacles in front of the vehicle or that the longitudinal speed of the first obstacle in front of the vehicle is greater than or equal to the longitudinal speed of the vehicle, then the preset duration is determined as the passage time cost.

4. The method according to claim 1, characterized in that, When the lane decision semantic information includes safety costs, the lane decision semantic information for each lane is determined based on the environmental perception information, including: Based on the lane information and the vehicle information, determine the vehicle's lane and other lanes; For the lane of this vehicle, the first preset safety cost is determined as the safety cost; For the other lanes, if based on the environmental perception information it is determined that an obstacle enters the vehicle's danger zone within a preset time, then the second preset safety cost is determined as the safety cost; if based on the environmental perception information it is determined that the obstacle does not enter the vehicle's danger zone within the preset time, then the first preset safety cost is determined as the safety cost, wherein the second preset safety cost is different from the first preset safety cost.

5. The method according to claim 4, characterized in that, The method further includes: Based on the environmental perception information, determine the ST curve of the vehicle and the ST curve of the obstacle; Based on the ST diagram curve of this vehicle, the danger zone of this vehicle is determined; Determine whether the ST curve of the obstacle overlaps with the danger zone of the vehicle within the preset time period; If the ST curve of the obstacle overlaps with the vehicle's danger zone within the preset time, it is determined that the obstacle has entered the vehicle's danger zone within the preset time; otherwise, it is determined that the obstacle has not entered the vehicle's danger zone within the preset time.

6. The method according to claim 1, characterized in that, The lane decision semantic information also includes a stability cost. Based on the environmental perception information, the lane decision semantic information for each lane is determined, including: Based on the lane information and the vehicle information, determine the vehicle's lane and other lanes; For the lane of this vehicle, the first preset stability cost is determined as the stability cost; For the other lanes, a second preset stability cost is determined as the stability cost, wherein the second preset stability cost is different from the first preset stability cost.

7. The method according to claim 1, characterized in that, Based on the lane decision semantic information, a drivable area is generated, including: The costs in the lane decision semantic information are weighted and summed. Based on the weighted summation result, a drivable region is generated.

8. The method according to claim 1, characterized in that, After generating a drivable area based on the lane decision semantic information, the method further includes: Discretize the boundaries of the drivable region.

9. The method according to claim 1, characterized in that, After generating a drivable area based on the lane decision semantic information, the method further includes at least one of the following: The drivable area is updated based on preset traffic rules; The drivable area is updated based on the vehicle's kinematic and dynamic constraints; Based on obstacle semantic information and a preset safe zone, the drivable area is updated, and the preset safe zone is connected to the drivable area; Based on the static obstacle information, obstacle decision semantic information, and ray tracing algorithm, the drivable area is updated. The obstacle decision semantic information includes passing through the obstacle from the left or from the obstacle from the right.

10. The method according to claim 9, characterized in that, Based on obstacle semantic information and a preset safe zone, the drivable area is updated, including: Based on the semantic information of obstacles, identify the obstacles that need to be avoided laterally; If the trajectory of the obstacle that needs to be avoided laterally occupies the preset safety zone, then the portion of the drivable area corresponding to the location occupying the preset safety zone is trimmed.

11. The method according to claim 9, characterized in that, Based on the static obstacle information, obstacle decision semantic information, and ray tracing algorithm, the drivable area is updated, including: Based on the static obstacle information, obstacle decision semantic information, and ray tracing algorithm, the collision point between the ray and the obstacle is determined, and the collision point is located within the drivable area; The drivable area is updated based on the collision point.

12. The method according to claim 11, characterized in that, Based on the static obstacle information, obstacle decision semantic information, and ray tracing algorithm, the collision point between the ray and the obstacle is determined, including: Based on the obstacle decision semantic information, determine the light source point and the direction of light projection; Based on the static obstacle information, the light projection range is determined; Based on the light source point, the light projection direction, and the light projection range, the obstacle is scanned by light. Determine the point of collision between the light ray and the obstacle.

13. A device for generating a drivable area for a vehicle, characterized in that, include: A perception information acquisition module is used to acquire environmental perception information, wherein the environmental perception information includes at least two of lane information, obstacle information and vehicle information, and the obstacle information includes static obstacle information and / or dynamic obstacle information; The lane decision semantic information determination module is used to determine the lane decision semantic information of each lane based on the environmental perception information, wherein the lane decision semantic information includes passage time cost, passage width cost, stability cost and safety cost; A drivable area generation module is used to generate a drivable area based on the lane decision semantic information; A discrete module is used to discretize the boundary of the drivable area to form drivable area boundary points, wherein the drivable area boundary points include left boundary points and right boundary points; The step of determining lane decision semantic information for each lane based on the environmental perception information includes: Based on the lane information and the static obstacle information, determine the maximum passage width of each static obstacle on the lane; The minimum value among the maximum passage widths of all static obstacles is determined as the minimum passage width of the lane; The minimum passage width is determined as the passage width cost.

14. An electronic device, characterized in that, include: Memory and one or more processors; The memory is communicatively connected to the one or more processors, and the memory stores instructions that can be executed by the one or more processors. When the instructions are executed by the one or more processors, the electronic device is used to implement the vehicle drivable area generation method as described in any one of claims 1-12.

15. A computer-readable storage medium having computer-executable instructions stored thereon, characterized in that, When the computer-executable instructions are executed by a computing device, they can be used to implement the vehicle drivable area generation method as described in any one of claims 1-12.

Images