Obstacle-avoiding path planning method and device

Abstract

The application provides a barrier-avoiding path planning method and device, wherein the barrier-avoiding path planning method comprises the following steps: when a target vehicle encounters an obstacle and needs to change lanes, obtaining the current running parameters of the target vehicle and the current constraint conditions of the target vehicle and the current driving lane and the target changing lane, the current distance from the target vehicle to the obstacle; performing barrier-avoiding path planning based on the current constraint conditions, the current distance and the current running parameters; judging whether the curvature of the planned path is continuous or the path shape is S-shaped; when the curvature of the planned path is discontinuous or the path shape is S-shaped, performing speed constraint on the target vehicle, and returning to the step of obtaining the current constraint conditions, the current distance and the current running parameters until a target path with continuous curvature and non-S-shaped path shape is obtained. While obtaining the barrier-avoiding target path and providing effective guarantee for subsequent assistance of the barrier-avoiding work of the unmanned equipment, the running stability of the unmanned equipment is greatly improved.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence, and more specifically to a method and apparatus for obstacle avoidance path planning. Background Technology

[0002] With the development of technologies such as artificial intelligence and computer vision, autonomous vehicles and delivery vehicles have been widely used. For these vehicles, the coordination of the operating path and speed is crucial for ensuring smooth operation. During operation, if obstacles or construction sites are encountered, a continuous curvature detour curve needs to be planned based on the predetermined route or lane to guide the autonomous vehicle around them. Current technologies typically employ a fifth-order polynomial method, using the starting and ending points, heading, and curvature as conditions to solve the polynomial equations and derive the path curve. This path planning method may result in unsolvable cases, and even if a solution exists, it is highly likely to result in a serpentine curve. Driving along such a serpentine path contradicts human driving habits and negatively impacts passenger comfort. Summary of the Invention

[0003] Therefore, the technical problem to be solved by the present invention is to overcome the shortcomings of the prior art in that there may be no solution or the planned curve is a serpentine curve in obstacle avoidance path planning, which makes it impossible for unmanned driving equipment to effectively plan obstacle avoidance paths according to human driving habits, thereby providing an obstacle avoidance path planning method and device.

[0004] According to a first aspect, embodiments of the present invention provide an obstacle avoidance path planning method, the method comprising:

[0005] When the target vehicle encounters an obstacle and needs to change lanes, the current constraints between the target vehicle and the current driving lane and the target lane to be changed, the current distance between the target vehicle and the obstacle, and the current operating parameters of the target vehicle are obtained.

[0006] Obstacle avoidance path planning is performed based on the current constraints, the current distance, and the current operating parameters.

[0007] Determine whether the curvature of the planned path is continuous or whether the path shape is S-shaped;

[0008] When the curvature of the planned path is discontinuous or the path shape is S-shaped, the speed of the target vehicle is constrained, and the steps of obtaining the current constraint conditions between the target vehicle and the current driving lane and the target lane change, the current distance between the target vehicle and the obstacle, and the current operating parameters of the target vehicle are returned until a target path with continuous curvature and non-S-shaped path shape is obtained.

[0009] Optionally, the current operating parameters include turning direction and vehicle speed, and the obstacle avoidance path planning based on the current constraints, the current distance, and the current operating parameters includes:

[0010] Determine the rate of curvature change based on the speed of the target vehicle;

[0011] Based on the curvature change rate and the target vehicle's current position, turning direction, and preset sampling step size, the pose information of the current path point is calculated;

[0012] Based on the pose information of the previous path point, the rate of curvature change, the current position of the target vehicle, the turning direction, and the preset sampling step size, the pose information of each path point is calculated sequentially.

[0013] The planned path is drawn based on the pose information of each path point.

[0014] Optionally, the method further includes:

[0015] Based on the pose information of each path point within the planned path, the planned path is divided into a first target sub-path and a second target sub-path, which are centrally symmetrical about the center point of the planned path.

[0016] Optionally, the first target sub-path and the second target sub-path each contain several sub-segments, and the sub-segments are combined sequentially to obtain the planned path.

[0017] Optionally, the method further includes:

[0018] Based on the current constraints, the current distance, and the current operating parameters, determine whether the target vehicle can complete the obstacle avoidance task by traveling along the second target sub-path;

[0019] When the target vehicle cannot complete the obstacle avoidance operation by following the second target sub-path, the length of each sub-segment within the second target sub-path is adjusted, and the second target sub-path and the first target sub-path are centrally symmetrical about the center point of the planned path.

[0020] Optionally, the speed constraint on the target vehicle includes:

[0021] Based on the current distance and the current constraints, determine whether the target vehicle needs to reverse;

[0022] When the target vehicle needs to reverse, control the target vehicle to reverse along the current driving path.

[0023] When the target vehicle does not need to reverse, control the target vehicle to decelerate and continue driving along the current driving path.

[0024] Optionally, determining whether the target vehicle needs to reverse based on the current distance and the current constraints includes:

[0025] Obtain the maximum rotation angle of the steering wheel of the target vehicle;

[0026] Based on the current distance and the current constraints, it is determined whether the target vehicle will collide with the obstacle when turning at the maximum rotation angle;

[0027] When the target vehicle is about to collide with the obstacle when it turns at the maximum rotation angle, it is determined that the target vehicle needs to reverse.

[0028] According to a second aspect, embodiments of the present invention provide an obstacle avoidance path planning device, the device comprising:

[0029] The acquisition module is used to acquire the current constraints between the target vehicle and the current driving lane and the target lane to be changed, the current distance between the target vehicle and the obstacle, and the current operating parameters of the target vehicle when the target vehicle encounters an obstacle and needs to change lanes.

[0030] The first processing module is used to plan an obstacle avoidance path based on the current constraints, the current distance, and the current operating parameters.

[0031] The judgment module is used to determine whether the curvature of the planned path is continuous or whether the path shape is S-shaped;

[0032] The second processing module is used to impose speed constraints on the target vehicle when the curvature of the planned path is discontinuous or the path shape is S-shaped, and return to the step of obtaining the current constraint conditions between the target vehicle and the current driving lane and the target lane change, the current distance between the target vehicle and the obstacle, and the current operating parameters of the target vehicle, until a target path with continuous curvature and non-S-shaped path shape is obtained.

[0033] According to a third aspect, embodiments of the present invention provide an electronic device, comprising:

[0034] A memory and a processor are communicatively connected, the memory storing computer instructions, and the processor executing the computer instructions to perform the method described in the first aspect, or any alternative embodiment of the first aspect.

[0035] According to a fourth aspect, embodiments of the present invention provide a computer-readable storage medium storing computer instructions for causing a computer to perform the method described in the first aspect, or any optional embodiment of the first aspect.

[0036] The technical solution of this invention has the following advantages:

[0037] The obstacle avoidance path planning method and apparatus provided by this invention, when a target vehicle encounters an obstacle and needs to change lanes, acquires the current constraints between the target vehicle and the current driving lane and the target lane to be changed, the current distance between the target vehicle and the obstacle, and the current operating parameters of the target vehicle; performs obstacle avoidance path planning based on the current constraints, the current distance, and the current operating parameters; determines whether the curvature of the planned path is continuous or whether the path shape is S-shaped; when the curvature of the planned path is discontinuous or the path shape is S-shaped, imposes speed constraints on the target vehicle, and returns to the step of acquiring the current constraints between the target vehicle and the current driving lane and the target lane to be changed, the current distance between the target vehicle and the obstacle, and the current operating parameters of the target vehicle, until a target path with continuous curvature and a non-S-shaped path is obtained. By constraining the target vehicle with the current driving lane and the target lane change lane, and planning the obstacle avoidance path based on the current distance between the target vehicle and the obstacle and the current operating parameters of the target vehicle, the target obstacle avoidance path is obtained, providing effective support for subsequent assistance to the unmanned driving equipment in obstacle avoidance work. At the same time, the target path is optimized, so that the planned target path is more in line with human driving habits, and the operational stability of the unmanned driving equipment is greatly improved. Attached Figure Description

[0038] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0039] Figure 1 This is a flowchart of the obstacle avoidance path planning method according to an embodiment of the present invention;

[0040] Figure 2 This is a schematic diagram of the FLU coordinate system according to an embodiment of the present invention;

[0041] Figure 3 This is a schematic diagram of the pose position of a path point based on a Cartesian coordinate system according to an embodiment of the present invention;

[0042] Figure 4This is a graph of the planned path in an embodiment of the present invention;

[0043] Figure 5 This is a schematic diagram of the S2 road segment curve within the first target sub-path of this invention embodiment;

[0044] Figure 6 This is a schematic diagram of the S3 road segment curve within the first target sub-path of this invention embodiment;

[0045] Figure 7 This is a schematic diagram of the design process of the obstacle avoidance path planning method according to an embodiment of the present invention;

[0046] Figure 8 This is a schematic diagram of the obstacle avoidance path planning device according to an embodiment of the present invention;

[0047] Figure 9 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0048] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0049] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0050] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can also refer to the internal connection of two components; and they can refer to a wireless connection or a wired connection. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0051] Furthermore, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0052] With the development of technologies such as artificial intelligence and computer vision, autonomous vehicles and delivery vehicles have been widely used. During the operation of these vehicles, the efficient coordination of the driving path and speed is crucial for ensuring smooth operation. Taking an autonomous vehicle as an example, if obstacles or construction sites are encountered ahead, the vehicle needs to detour. In this case, a continuous curvature curve needs to be planned based on the predetermined route or lane to minimize changes in centrifugal force, thereby ensuring smooth obstacle avoidance while enhancing vehicle comfort and stability. However, current technologies, such as Baidu Apollo, typically use a fifth-order polynomial method, using the starting and ending points, heading, and curvature as conditions to solve the coefficients of the polynomial equation to derive the path curve. This path planning method may result in unsolvable cases, and even if a solution exists, it is highly likely to result in a serpentine curve. Driving along a serpentine path deviates from human driving habits, impacting passenger comfort.

[0053] Against this backdrop, embodiments of the present invention provide an obstacle avoidance path planning method to address the shortcomings of the aforementioned calculation methods. In this embodiment, the present invention analyzes the changes in trajectory and speed of manual driving by introducing reverse speed constraints, segments the manual driving trajectory, and finally obtains the target path to achieve the obstacle avoidance objective.

[0054] like Figure 1 As shown, the obstacle avoidance path planning method specifically includes the following steps:

[0055] Step S101: When the target vehicle encounters an obstacle and needs to change lanes, obtain the current constraints between the target vehicle and the current driving lane and the target lane to be changed, the current distance between the target vehicle and the obstacle, and the current operating parameters of the target vehicle.

[0056] Specifically, in practical applications, constraints include heading constraints, speed constraints, and distance constraints, curvature constraints, and rate of curvature change constraints between lanes constructed based on the current driving lane and the target lane change lane.

[0057] The heading constraint is used to control the direction of travel of the target vehicle based on its current position and the distance between the current driving lane and the target lane to be changed. For example, when the target vehicle is about to leave the target lane to be changed, the heading constraint is used to plan the target path to prevent the target vehicle from going beyond the target lane to be changed.

[0058] Speed ​​constraints can be applied to the speed of a target vehicle, and can be used to control the target vehicle to travel at a safe speed.

[0059] Distance constraints include lateral and longitudinal distance constraints between the target vehicle and the current driving lane and the target lane to be changed, as well as between the current driving lane and the target lane to be changed. By setting distance constraints, it is ensured that the planned target path will not exceed the target vehicle's current driving lane and the target lane to be changed.

[0060] Curvature constraints are used to ensure the curvature continuity of the planned target path, thereby ensuring the smooth obstacle avoidance operation of subsequent target vehicles.

[0061] The curvature change rate constraint is used to ensure the smoothness of the planned target path curve, and to avoid situations where subsequent target vehicles need to make large adjustments to the steering wheel angle when driving according to the target path.

[0062] In practical applications, the constraints can be adjusted according to the target vehicle model, road conditions, and specific obstacles. The constraints are not limited to the heading constraints, speed constraints, distance constraints, curvature constraints, and rate of change of curvature constraints mentioned above.

[0063] Specifically, in practical applications, obstacles are not limited to static obstacles. Situations where the target vehicle needs to detour due to traffic jams or accidents ahead can also be considered obstacle detour operations.

[0064] Step S102: Plan the obstacle avoidance path based on the current constraints, current distance, and current operating parameters.

[0065] Specifically, in practical applications, the current operating parameters of the target vehicle include the vehicle speed.

[0066] Step S103: Determine whether the curvature of the planned path is continuous or whether the path shape is S-shaped.

[0067] Step S104: When the curvature of the planned path is discontinuous or the path shape is S-shaped, apply speed constraints to the target vehicle and return to the steps of obtaining the current constraints between the target vehicle and the current driving lane and the target changing lane, the current distance between the target vehicle and the obstacle, and the current operating parameters of the target vehicle, until a target path with continuous curvature and a non-S-shaped path shape is obtained.

[0068] Specifically, in practical applications, taking into full account the inability to effectively plan the obstacle avoidance target path based on constraints such as distance constraints, the embodiments of the present invention actively constrain the speed of the target vehicle and predict the points that satisfy the speed constraints to calculate the path curve, and finally obtain a target path with continuous curvature and a non-S-shaped path shape.

[0069] By performing the above steps, the obstacle avoidance path planning method provided in this embodiment of the invention constrains the target vehicle with the current driving lane and the target lane change, and plans the obstacle avoidance path based on the current distance between the target vehicle and the obstacle and the current operating parameters of the target vehicle. While obtaining the obstacle avoidance target path and providing effective guarantee for subsequent assistance to unmanned driving equipment in obstacle avoidance work, the target path is optimized, so that the planned target path is more in line with human driving habits and greatly improves the operational stability of unmanned driving equipment.

[0070] Specifically, in one embodiment, the current operating parameters include turning direction and vehicle speed. The above step S102 performs obstacle avoidance path planning based on the current constraints, current distance, and current operating parameters, and specifically includes the following steps:

[0071] Step S201: Determine the rate of curvature change based on the target vehicle's speed.

[0072] Specifically, in practical applications, the value of the rate of change of curvature is limited by the speed of the target vehicle. That is, when the speed is high, the rate of change of curvature will adaptively decrease to avoid dangers such as vehicle rollover when the target vehicle changes lanes at high speeds. At the same time, the rate of change of curvature is also limited by the size of the target vehicle. For example, small vehicles have a relatively large rate of change of curvature.

[0073] Step S202: Based on the rate of curvature change, the current position of the target vehicle, the turning direction, and the preset sampling step size, calculate the pose information of the current path point.

[0074] Step S203: Based on the pose information, curvature change rate, current position of the target vehicle, turning direction, and preset sampling step size of the previous path point, calculate the pose information of each path point in sequence.

[0075] Specifically, in practical applications, when planning obstacle avoidance paths, such as Figure 2 As shown, in this embodiment of the invention, a self-coordinate system (such as an FLU coordinate system) based on the target vehicle can be established, and the origin of the coordinate system can be set as the midpoint of the rear axle of the target vehicle.

[0076] Specifically, the pose information of the first path point can be obtained based on the target vehicle's current position, turning direction, and rate of curvature change. This information can then be processed by performing actions such as... Figure 3The Cartesian coordinate system transformation shown is used, and the pose information of the second path point can be calculated based on the preset sampling step size and the pose information of the first path point. The preset sampling step size can be the length of the target vehicle's fixed-time travel curve. Since the target vehicle is in the process of changing lanes, for example, the preset sampling step size can be the curve arc length ds = 0.1m. However, the actual situation is not limited to this. Since the target vehicle's position change is small and the curvature is large each time, in practical applications, the preset sampling step size can also be regarded as the straight-line distance of the target vehicle's movement. The specific value of the sampling step size can also be adjusted according to the actual situation, so as to obtain more accurate pose information of each path point. The subsequent planned path will also be more accurate. While ensuring the completion of obstacle avoidance work, it further reduces the change in the vehicle's lane change amplitude during obstacle avoidance, and greatly improves passenger comfort.

[0077] Step S204: Based on the pose information of each path point, the planned path is drawn.

[0078] Specifically, in one embodiment, the method further includes the following steps:

[0079] Step S301: Based on the pose information of each path point within the planned path, the planned path is divided into a first target sub-path and a second target sub-path. The first target sub-path and the second target sub-path are centrally symmetrical about the center point of the planned path.

[0080] Specifically, in one embodiment, the first target sub-path and the second target sub-path are each provided with a number of sub-road segments, and the sub-road segments are combined in sequence to obtain the planned path.

[0081] Specifically, in practical applications, such as Figure 4 As shown, in this embodiment of the invention, the target path is divided into a first target sub-path and a second target sub-path based on the driving process of the target vehicle. The first target sub-path and the second target sub-path are centrally symmetrically distributed around the center point of the planned path. Furthermore, the planned path can be further divided based on the lane-changing process of the target vehicle. For example, it can be divided into 7 stages, and the curve characteristics corresponding to each stage are as follows:

[0082] (1) The path curvature increases uniformly from 0 to a (a and A are in one-to-one correspondence): During this stage, the vehicle's heading increases to H1 (the increase is incremental). Through integration, a series of vehicle heading and position information can be calculated.

[0083] (2) Path curvature remains unchanged: During this stage, the heading speed increases uniformly to H2. Through trigonometric function operations, a series of vehicle headings and positions can be calculated.

[0084] (3) The path curvature decreases uniformly from a to 0: During this stage, the heading increases to H3 (the increase is decreasing).

[0085] (4) The route and road are traveling straight at an angle of H3: the heading remains unchanged during this stage.

[0086] (5) The path curvature decreases uniformly from 0 to b (a negative value of b indicates that the direction is opposite to the curvature a, and b corresponds one-to-one with B): During this stage, the heading decreases to H4 (the amount of decrease increases).

[0087] (6) Path curvature remains unchanged: During this stage, the heading speed decreases uniformly to H5.

[0088] (7) The path curvature decreases uniformly from b to 0: During this stage, the heading decreases to H6 (the amount of decrease decreases gradually).

[0089] Specifically, H1 to H6 mentioned above are all changes in the vehicle's heading. After the rate of change of curvature of the planned path curve is determined, the curvature of each point on the curve and the vehicle's heading can be calculated by integration.

[0090] It should be noted that, in order to facilitate the division of obstacle avoidance paths, this embodiment of the invention is set in the vehicle coordinate system (i.e., the FLU coordinate system). The target vehicle's front deflects counterclockwise (to the left), which means that the heading increases from 0 to PI (PI is pi, corresponding to 180 degrees), and the heading decreases from 0 to -PI when it deflects clockwise; H1 to H6 are all headings relative to the starting position.

[0091] Based on the above settings and human driving habits, the overall course change from S1 to S7 in this embodiment of the invention is as follows: increase (variable speed increase) – increase (uniform speed increase) – increase (variable speed increase) – remain unchanged – decrease (variable speed decrease) – decrease (uniform speed decrease) – decrease (variable speed decrease). This not only allows for smooth obstacle avoidance but also better aligns with human driving habits, significantly improving passenger comfort.

[0092] Specifically, the values ​​of 'a' and 'b' are subject to curvature constraints, lateral distance constraints, and speed constraints. In practical applications, to improve the speed of obtaining the planned path, this embodiment of the invention divides the planned path into a first target sub-path and a second target sub-path based on the vehicle's obstacle avoidance process. In this case, the values ​​of 'a' and 'b' are equal, and the curve is centrally symmetrical about the midpoint of segment S4. Once the constraints are met, the curvature value will remain at 'a' and will not increase further.

[0093] Specifically, in one embodiment, the method further includes the following steps:

[0094] Step S401: Based on the current constraints, current distance, and current operating parameters, determine whether the target vehicle can complete the obstacle avoidance operation by traveling along the second target sub-path.

[0095] Step S402: When the target vehicle cannot complete the obstacle avoidance work by traveling along the second target sub-path, adjust the length of each sub-segment within the second target sub-path and make the second target sub-path and the first target sub-path centrally symmetrical about the center point of the planned path.

[0096] Considering that in actual situations, the road width within the second target sub-path may become narrower or small obstacles may exist, preventing the target vehicle from completing the obstacle avoidance work by turning the steering wheel to the right by A degrees, i.e., the values ​​of a and b are not equal at this time, and the center points of the first and second target sub-paths are no longer centrally symmetrically distributed, this embodiment of the invention will determine whether the target vehicle can complete the obstacle avoidance work by traveling along the second target sub-path based on the current constraints, current distance, and current operating parameters. When the obstacle avoidance work cannot be completed, the length of each segment within the second target sub-path will be adjusted in a timely manner according to constraints such as heading, speed, distance, and curvature, thereby ensuring that the center points of the first and second target sub-paths are no longer centrally symmetrically distributed.

[0097] Specifically, in practical applications, such as Figure 4 As shown, considering the actual needs of users such as human driving habits and vehicle operation stability, this embodiment of the invention also adds the S4 section. After the target vehicle completes the first target sub-path driving process, it can maintain the current operating state for a period of time before proceeding to the second target sub-path driving process, avoiding the user experiencing multiple lane changes in a short period of time and greatly improving user satisfaction.

[0098] Combination Figures 2-6 As shown, the calculation process for the planned path is as follows:

[0099] For the calculation of road segment s1, we obtain the turning radius r1 through the rate of change of curvature, sampling with ds = 0.1m (sampling with a smaller length can also be used for higher accuracy, but with a larger computational load). The curvature of each sampling point is (d_kappa, d2_kappa, ..., dn_kappa), that is, the turning radius sequence is (r1, r2, ..., r i ),in, i represents the i-th road segment, thus allowing us to calculate the pose information of each path point in a coordinate system with the previous path point as the origin. Through Cartesian coordinate transformation, the poses of each path point can be obtained: (x0, y0, θ0), (x1, y1, θ1), ..., (x... n y n θ n ).

[0100] The specific calculation formula is as follows:

[0101]

[0102]

[0103]

[0104] The turning radius of road segment S2 is denoted as r2. Since the steering wheel angle of the target vehicle remains constant at A degrees within road segment S2, the arc length of road segment S2 can be calculated using coordinate transformation to obtain the curve of road segment S2 based on the vehicle's coordinate system. The specific calculation formula is as follows:

[0105]

[0106] x m =r2·sinθ m (5)

[0107] y m =r2·(1-cosθ) m (6)

[0108] Where m is a natural number, m = 1, 2, ...

[0109] According to the planning path design principle of the present invention, the first target sub-path includes road segments S1, S2, and S3, and S1 and S3 are centrally symmetrically distributed based on the midpoint of road segment S2. Therefore, by performing coordinate transformation, the pose information of each path point in road segment S3 can be obtained, which will not be elaborated here.

[0110] For section S4, since the steering wheel of the subsequent target vehicle will remain at 0 degrees during this stage, the S4 path curve is a straight line segment. The pose information of each path point within section S4 can be calculated using the following formula:

[0111] θ k =θ3 (7)

[0112] x k =x³ + k·ds·cosθ k (8)

[0113] y k =y3+k·ds·sinθ k (9)

[0114] Where k is a natural number, k = 1, 2, ...; is the angle corresponding to the end point of the S3 road segment; x3 is the x-coordinate of the end point of the S3 road segment; and y3 is the y-coordinate of the end point of the S3 road segment.

[0115] According to the planning path design principle of the present invention, the second target sub-path includes road segments S5, S6, and S7. The second target sub-path is based on the central symmetry between the midpoint of road segment S4 and the first target sub-path. Therefore, by performing coordinate transformation on the pose information of each road point in the first target sub-path and road segment S4, the pose information of each road point in the second target sub-path can be obtained. This will not be elaborated further here.

[0116] Specifically, in practical applications, for curved situations, this embodiment of the invention applies constraints such as curvature, heading, and speed during the path planning process. Using the target vehicle's current operating parameters, distance information from obstacles, and the constraints, the pose information of each path point within the planned path can be calculated. This embodiment uses a left lane change as an example for explanation, but the actual situation is not limited to this. For obstacle avoidance path planning during a right lane change, only symmetrical calculations need to be performed using the above method, which will not be elaborated further here.

[0117] Based on full consideration of human driving habits, this invention designs the planned path and cleverly combines the recursive method with central symmetry to calculate the pose of each path point within the planned path curve, thereby obtaining the final target path. Compared with traditional calculation methods, this invention has the advantages of low computational load and high efficiency, ultimately achieving the goal of efficient obstacle avoidance.

[0118] Specifically, in practical applications, embodiments of the present invention divide the planned path, thereby allowing for timely adjustments to the path based on road and vehicle information during subsequent control of the target vehicle's movement. This ensures obstacle avoidance is completed while reducing the target vehicle's movement deviation, providing users with a better user experience.

[0119] In practical applications, each road segment can be degraded; for example, combined with... Figure 4 As shown:

[0120] Case 1: When the heading constraint is in effect, the S2 segment can be degraded according to the actual calculation structure. That is, when the lateral distance between the current driving lane and the target lane is short, if it is determined by judging the heading constraint of the target vehicle that the first target sub-path cannot be completed, in order to ensure that the subsequent target vehicles can continue to drive according to the first target sub-path, it is necessary to directly run from the S1 stage to the S3 stage. Accordingly, the S2 segment is degraded.

[0121] Scenario 2: When the lateral distance between the lane-changing target point (the end point of the target path) and the starting point of the target vehicle is relatively small, road sections S2, S4, and S6 can be degraded based on actual calculations. The degradation process is similar to that of road section S2 in Scenario 1, and will not be elaborated further here.

[0122] Scenario 3: In extreme cases, the target vehicle may stop in front of the obstacle and then attempt to maneuver around it. In this case, the target vehicle starts planning from 0 speed, and the S1 and S3 sections can be degraded as needed, which is equivalent to turning the steering wheel to a large angle quickly to drive.

[0123] Furthermore, embodiments of the present invention can also perform degradation optimization on the planned path by determining whether the pose information of the endpoint path point of the S3 segment has crossed the centerline of the planned path curve. If the endpoint path point of the S3 segment crosses the centerline, the S4 segment can be degraded, or the S1 segment can be terminated prematurely.

[0124] By setting the planned path into multiple road segments, this invention provides necessary preliminary data and technical support for real-time obstacle avoidance path adjustment based on the current location of the target vehicle.

[0125] Specifically, in one embodiment, step S104 above, which constrains the speed of the target vehicle, includes the following steps:

[0126] Step S501: Determine whether the target vehicle needs to reverse based on the current distance and current constraints.

[0127] Step S502: When the target vehicle needs to reverse, control the target vehicle to reverse along the current driving path.

[0128] Step S503: When the target vehicle does not need to reverse, control the target vehicle to decelerate and continue driving along the current driving path.

[0129] Specifically, in practical applications, embodiments of the present invention ensure the driving safety of the target vehicle by imposing speed constraints on the target vehicle. Furthermore, the speed constraint will form a reverse speed constraint on the planned path, thereby obtaining a better target path.

[0130] Specifically, in practical applications, such as Figure 7 As shown, in this embodiment of the invention, the target vehicle will determine whether it needs to reverse based on the current distance between the target vehicle and the obstacle and the constraints. When an effective planned path cannot be obtained, it may be because the target vehicle is too close to the obstacle or cannot achieve a smooth lane change at the current speed. In this case, it is determined that the target vehicle needs to reverse.

[0131] When the target vehicle needs to reverse, it is controlled to reverse along its original route. Path planning is performed based on the target vehicle's current position, current distance to obstacles, and current operating parameters and constraints to plan a path that can successfully bypass obstacles during the reversing process. When the target vehicle does not need to reverse, it is controlled to decelerate and continue driving along the current path. Path planning is continuously performed based on current data and constraints. Furthermore, embodiments of the present invention can also filter multiple planned paths to obtain the optimal target path.

[0132] Specifically, in one embodiment, step S501 above includes the following steps:

[0133] Step S601: Obtain the maximum rotation angle of the steering wheel of the target vehicle.

[0134] Step S602: Based on the current distance and current constraints, determine whether the target vehicle will collide with the obstacle when turning at the maximum rotation angle.

[0135] Step S603: When the target vehicle will collide with the obstacle when turning at its maximum rotation angle, determine that the target vehicle needs to reverse.

[0136] like Figure 7 As shown, this embodiment of the invention determines whether the target vehicle needs to reverse based on the maximum steering wheel rotation angle. When the target vehicle would collide with an obstacle if it turned at its maximum rotation angle, it is determined that the target vehicle needs to reverse. At this time, the distance between the target vehicle and the obstacle when it decelerates to 0 is calculated based on the target vehicle's current speed. During the reversing process, obstacle avoidance path planning is performed with reference to the current distance to the obstacle and the constraints.

[0137] This invention applies reverse constraints to vehicle speed and incorporates active speed limiting constraints on the target vehicle. It also pre-calculates the path curve after deceleration, ensuring that even in extreme situations such as being extremely close to obstacles, by reducing the vehicle speed to the extreme or even performing reversing planning, a target path with continuous curvature and a non-S-shaped path shape is ultimately obtained. This not only conforms to human driving habits but also makes the solution process more intuitive, significantly improving the efficiency of autonomous vehicle use.

[0138] By performing the above steps, the obstacle avoidance path planning method provided in this embodiment of the invention constrains the target vehicle with the current driving lane and the target lane change, and plans the obstacle avoidance path based on the current distance between the target vehicle and the obstacle and the current operating parameters of the target vehicle. While obtaining the obstacle avoidance target path and providing effective guarantee for subsequent assistance to unmanned driving equipment in obstacle avoidance work, the target path is optimized, so that the planned target path is more in line with human driving habits and greatly improves the operational stability of unmanned driving equipment.

[0139] This invention provides an obstacle avoidance path planning device, such as... Figure 8 As shown, the obstacle avoidance path planning device includes:

[0140] The acquisition module 101 is used to acquire the current constraints between the target vehicle and the current driving lane and the target lane to be changed, the current distance between the target vehicle and the obstacle, and the current operating parameters of the target vehicle when the target vehicle encounters an obstacle and needs to change lanes. For details, please refer to the relevant description of step S101 in the above method embodiment, which will not be repeated here.

[0141] The first processing module 102 is used to plan an obstacle avoidance path based on the current constraints, current distance, and current operating parameters. For details, please refer to the relevant description of step S102 in the above method embodiment, which will not be repeated here.

[0142] The judgment module 103 is used to determine whether the curvature of the planned path is continuous or whether the path shape is S-shaped. For details, please refer to the relevant description of step S103 in the above method embodiment, which will not be repeated here.

[0143] The first processing module 104 is used to impose speed constraints on the target vehicle when the curvature of the planned path is discontinuous or the path shape is S-shaped, and to return to the steps of obtaining the current constraint conditions between the target vehicle and the current driving lane and the target lane change lane, the current distance between the target vehicle and obstacles, and the current operating parameters of the target vehicle, until a target path with continuous curvature and a non-S-shaped path shape is obtained. For details, please refer to the relevant description of step S104 in the above method embodiment, which will not be repeated here.

[0144] For a further description of the obstacle avoidance path planning device described above, please refer to the relevant description of the obstacle avoidance path planning method embodiment described above, which will not be repeated here.

[0145] Through the collaborative efforts of the aforementioned components, the obstacle avoidance path planning device provided in this embodiment of the invention constrains the target vehicle with the current driving lane and the target lane change, and plans the obstacle avoidance path based on the current distance between the target vehicle and the obstacle and the current operating parameters of the target vehicle. While obtaining the obstacle avoidance target path and providing effective support for subsequent assistance to unmanned driving equipment in obstacle avoidance work, the target path is optimized, thereby making the planned target path more in line with human driving habits and greatly improving the operational stability of unmanned driving equipment.

[0146] This invention provides an electronic device, such as... Figure 9As shown, the electronic device includes a processor 901 and a memory 902, which are communicatively connected. The processor 901 and memory 902 can be connected via a bus or other means. Figure 9 Taking the example of a connection between China and Israel via a bus.

[0147] Processor 901 can be a Central Processing Unit (CPU). Processor 901 can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or combinations of the above types of chips.

[0148] The memory 902, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the methods in the embodiments of the present invention. The processor 901 executes various functional applications and data processing of the processor 901 by running the non-transitory software programs, instructions, and modules stored in the memory 902, thereby implementing the methods in the above-described method embodiments.

[0149] The memory 902 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created by the processor 901, etc. Furthermore, the memory 902 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory 902 may optionally include memory remotely located relative to the processor 901, and these remote memories may be connected to the processor 901 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0150] One or more modules are stored in memory 902, and when executed by processor 901, they perform the methods described in the above method embodiments.

[0151] The specific details of the aforementioned electronic device can be understood by referring to the relevant descriptions and effects in the above method embodiments, and will not be repeated here.

[0152] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The implemented program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk drive (HDD), or solid-state drive (SSD), etc.; the storage medium can also include combinations of the above types of memory.

[0153] Obviously, the above embodiments are merely illustrative examples for clear explanation and are not intended to limit the implementation. Those skilled in the art will recognize that other variations or modifications can be made based on the above description. It is neither necessary nor possible to exhaustively list all possible implementations here. However, obvious variations or modifications derived therefrom are still within the scope of protection of this invention.

Claims

1. A method for obstacle avoidance path planning, characterized in that, include: When the target vehicle encounters an obstacle and needs to change lanes, the current constraints between the target vehicle and the current driving lane and the target lane to be changed, the current distance between the target vehicle and the obstacle, and the current operating parameters of the target vehicle are obtained, including the turning direction and the vehicle speed. Obstacle avoidance path planning is performed based on the current constraints, the current distance, and the current operating parameters. Determine whether the curvature of the planned path is continuous or whether the path shape is S-shaped; When the curvature of the planned path is discontinuous or the path shape is S-shaped, the speed of the target vehicle is constrained, and the steps of obtaining the current constraint conditions between the target vehicle and the current driving lane and the target lane change, the current distance between the target vehicle and the obstacle, and the current operating parameters of the target vehicle are returned until a target path with continuous curvature and non-S-shaped path shape is obtained. The obstacle avoidance path planning based on the current constraints, the current distance, and the current operating parameters includes: Based on the target vehicle's speed, the rate of curvature change is determined; based on the rate of curvature change, the target vehicle's current position, turning direction, and preset sampling step size, the pose information of the current path point is calculated; based on the pose information of the previous path point, the rate of curvature change, the target vehicle's current position, turning direction, and preset sampling step size, the pose information of each path point is calculated sequentially; based on the pose information of each path point, the planned path is drawn. Based on the pose information of each path point within the planned path, the planned path is divided into a first target sub-path and a second target sub-path, which are centrally symmetrical about the center point of the planned path. Each of the first and second target sub-paths contains several sub-segments, which are sequentially combined to obtain the planned path. Based on the current constraints, the current distance, and the current operating parameters, it is determined whether the target vehicle can complete the obstacle avoidance operation by traveling along the second target sub-path. When the target vehicle cannot complete the obstacle avoidance operation by traveling along the second target sub-path, the lengths of each sub-segment within the second target sub-path are adjusted, and the second target sub-path and the first target sub-path are centrally symmetrical about the center point of the planned path.

2. The method according to claim 1, characterized in that, The speed constraint on the target vehicle includes: Based on the current distance and the current constraints, determine whether the target vehicle needs to reverse; When the target vehicle needs to reverse, control the target vehicle to reverse along the current driving path. When the target vehicle does not need to reverse, control the target vehicle to decelerate and continue driving along the current driving path.

3. The method according to claim 2, characterized in that, The step of determining whether the target vehicle needs to reverse based on the current distance and the current constraints includes: Obtain the maximum rotation angle of the steering wheel of the target vehicle; Based on the current distance and the current constraints, it is determined whether the target vehicle will collide with the obstacle when turning at the maximum rotation angle; When the target vehicle is about to collide with the obstacle when it turns at the maximum rotation angle, it is determined that the target vehicle needs to reverse.

4. A path planning device for obstacle avoidance, characterized in that, include: The acquisition module is used to acquire the current constraints between the target vehicle and the current driving lane and the target lane to be changed, the current distance between the target vehicle and the obstacle, and the current operating parameters of the target vehicle when the target vehicle encounters an obstacle and needs to change lanes. The current operating parameters include turning direction and vehicle speed. The first processing module is used to plan an obstacle avoidance path based on the current constraints, the current distance, and the current operating parameters. The judgment module is used to determine whether the curvature of the planned path is continuous or whether the path shape is S-shaped; The second processing module is used to impose speed constraints on the target vehicle when the curvature of the planned path is discontinuous or the path shape is S-shaped, and return to the steps of obtaining the current constraint conditions between the target vehicle and the current driving lane and the target changing lane, the current distance between the target vehicle and the obstacle, and the current operating parameters of the target vehicle, until a target path with continuous curvature and non-S-shaped path shape is obtained. The obstacle avoidance path planning based on the current constraints, the current distance, and the current operating parameters includes: Based on the target vehicle's speed, the rate of curvature change is determined; based on the rate of curvature change, the target vehicle's current position, turning direction, and preset sampling step size, the pose information of the current path point is calculated; based on the pose information of the previous path point, the rate of curvature change, the target vehicle's current position, turning direction, and preset sampling step size, the pose information of each path point is calculated sequentially; based on the pose information of each path point, the planned path is drawn. Based on the pose information of each path point within the planned path, the planned path is divided into a first target sub-path and a second target sub-path, which are centrally symmetrical about the center point of the planned path. Each of the first and second target sub-paths contains several sub-segments, which are sequentially combined to obtain the planned path. Based on the current constraints, the current distance, and the current operating parameters, it is determined whether the target vehicle can complete the obstacle avoidance operation by traveling along the second target sub-path. When the target vehicle cannot complete the obstacle avoidance operation by traveling along the second target sub-path, the lengths of each sub-segment within the second target sub-path are adjusted, and the second target sub-path and the first target sub-path are centrally symmetrical about the center point of the planned path.

5. An electronic device, characterized in that, include: A memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, the processor executing the computer instructions to perform the method as described in any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the method as described in any one of claims 1-3.

Images