Path planning method, vehicle control method, computer program product, and electronic device

Abstract

The application provides a path planning method, a vehicle control method, a computer program product and an electronic device. According to the above method provided by the application, path planning related information for representing a path starting point, a path ending point and a path reference line of a vehicle can be obtained. By using a heuristic search algorithm, a driving path planning result of the vehicle can be generated according to the path starting point, the path ending point and a target evaluation function constructed based on a lateral distance between the vehicle and the path reference line, so as to control the vehicle based on the driving path planning result of the vehicle by using a driving assistance function of the vehicle in an active state.

Description

Technical Field

[0001] This application relates to the field of path planning technology, and in particular to a path planning method, a vehicle control method, a computer program product, and an electronic device. Background Technology

[0002] With the continuous iteration and upgrading of intelligent driving technology, vehicle path planning has become a core functional module of advanced driver assistance systems (ADAS), and its performance affects the vehicle's driving safety, comfort, and reliability. Currently, due to limitations such as insufficient coverage of high-precision electronic maps, complex and ever-changing driving environments, and bottlenecks in the accuracy of vehicle surrounding perception, existing path planning methods struggle to plan smooth and reasonable driving paths for vehicles in a timely and efficient manner when driving in scenarios with complex road topology, unclear or missing lane markings, or inadequate traffic infrastructure. This impacts the safety, smoothness, and user experience of the driving process. Summary of the Invention

[0003] Based on this, this application provides a path planning method, a vehicle control method, a computer program product, and an electronic device. Using the above method can improve the real-time performance, accuracy, and reliability of vehicle driving path planning and vehicle control.

[0004] On the one hand, this application provides a path planning method, the method comprising: Obtain the path planning information of this vehicle; wherein, the path planning information is used to characterize the path start point, path end point, and path reference line of this vehicle; Using a heuristic search algorithm, the driving path planning result of the vehicle is generated based on the path start point, the path end point, and the target evaluation function; wherein, the target evaluation function is an evaluation function constructed based on the lateral distance between the vehicle and the path reference line.

[0005] On the other hand, this application also provides a vehicle control method, including: Obtain the path planning information of this vehicle; wherein, the path planning information is used to characterize the path start point, path end point, and path reference line of this vehicle; Using a heuristic search algorithm, the driving path planning result of the vehicle is generated based on the path start point, the path end point, and the target evaluation function; wherein, the target evaluation function is an evaluation function constructed based on the lateral distance between the vehicle and the path reference line; Using the vehicle's active driving assistance functions, and based on the vehicle's driving path planning results, driving control is performed on the vehicle.

[0006] On the other hand, this application also provides a computer program product comprising a computer program that, when executed, implements the steps of the above-described path planning method and vehicle control method.

[0007] On the other hand, this application also provides an electronic device, including: a processor and a memory; wherein the memory stores computer-readable instructions adapted to be loaded by the processor and executed by the steps of the above-described path planning method and vehicle control method.

[0008] According to the path planning method and vehicle control method provided in this application, path planning related information, such as the path start point, path end point, and path reference line, can be obtained to characterize the vehicle. Using a heuristic search algorithm, based on the path start point, the path end point, and a target evaluation function constructed based on the lateral distance between the vehicle and the path reference line, the vehicle's driving path planning result can be generated efficiently and accurately. Therefore, by utilizing the vehicle's active driving assistance function, and based on the vehicle's real-time and accurate driving path planning result, precise driving control of the vehicle can be performed, which is beneficial to improving the real-time performance, accuracy, and reliability of vehicle driving path planning and vehicle control.

[0009] It should be understood that the description in the Summary Section is not intended to limit the key or essential features of the embodiments of this application, nor is it intended to restrict the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0010] Figure 1 A flowchart illustrating a path planning method provided in an embodiment of this application; Figure 2 A schematic diagram illustrating a path planning scenario provided in an embodiment of this application; Figure 3 A schematic flowchart of a vehicle control method provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0011] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application. The order of some steps in the methods provided in one or more embodiments of this application can be interchanged according to actual needs, or some steps can be omitted or deleted, without specific limitations.

[0012] In the description of one or more embodiments of this application, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc., may refer to different or the same objects and are not used to limit their quantity. Other explicit and implicit definitions may also be included below.

[0013] The term "at least one" should be understood to include one or more situations. For example, "at least one of A and B" can include "A alone," "B alone," and "A and B." Similarly, "at least one of A, B, and C" can include "A alone," "B alone," "C alone," "A and B," "A and C," "C and B," and "A, B, and C." Other explicit and implicit definitions may also be included below, but are not specifically limited thereto.

[0014] In the description of one or more embodiments of this application, the term "and / or" should be understood to include one or more situations. For example, "A and / or B" may include "A alone", "B alone", and "A and B". As another example, "A and / or B and / or C" may include "A alone", "B alone", "C alone", "A and B", "A and C", "C and B", and "A, B and C".

[0015] The driving environment is complex and ever-changing. During vehicle operation, there may be a lack of high-precision map navigation information, and the onboard system may be unable to accurately identify lane boundaries around the vehicle. Some existing path planning schemes may fail to function due to a lack of accurate path planning reference information, affecting the reliability and stability of path planning and vehicle intelligent control. Other path planning schemes may employ path search algorithms that do not rely on path planning reference information, but this involves spending more time planning the vehicle's driving path. However, the path planning process is time-consuming, and the accuracy and rationality of the path planning results are poor, making it difficult to meet the requirements of vehicle intelligent control.

[0016] Based on this, this application proposes a path planning method and a vehicle control method. This method can obtain path planning-related information, such as the path start point, path end point, and path reference line, which characterize the vehicle. Using a heuristic search algorithm, based on the path start point, the path end point, and a target evaluation function constructed based on the lateral distance between the vehicle and the path reference line, the driving path planning result of the vehicle can be generated efficiently and accurately. Thus, the vehicle's active driving assistance function can be used to precisely control the vehicle based on the real-time and accurate driving path planning result, which is beneficial to improving the real-time performance, accuracy, reliability, and availability of the vehicle driving path planning and vehicle control scheme.

[0017] Please see Figure 1 This is a flowchart illustrating a path planning method provided in an embodiment of this application. The executor of this process can be a program mounted on a domain controller or vehicle. Alternatively, the executor of this process can also be a domain controller or vehicle, or other devices capable of communicating with a domain controller or vehicle; no specific limitation is made in this regard.

[0018] The following is about Figure 1 The process shown will be described in detail. The path planning method may specifically include the following steps: Step S102: Obtain the path planning information of the vehicle; wherein, the path planning information can be used to characterize the path start point, path end point and path reference line of the vehicle.

[0019] In this embodiment, the starting point of the vehicle's path can represent the starting point when using a heuristic search algorithm to plan the vehicle's path. The ending point of the vehicle's path can represent the ending point when using a heuristic search algorithm to plan the vehicle's path. The reference line of the vehicle's path can represent a baseline used to guide the vehicle's movement. It can serve as a geometric reference and smoothing constraint during path planning, thereby improving the rationality, smoothness, and safety of the planned vehicle's driving path.

[0020] Step S104: Using a heuristic search algorithm, generate the driving path planning result of the vehicle based on the path start point, the path end point, and the target evaluation function; wherein, the target evaluation function can be an evaluation function constructed based on the lateral distance between the vehicle and the path reference line.

[0021] In this embodiment, the heuristic search algorithm is a widely used path planning algorithm. It utilizes heuristic information during the search process to evaluate the "cost" between the current state and the target state, thereby prioritizing the exploration of paths that seem more likely to reach the goal. This reduces the blindness and inefficiency of traditional breadth-first or depth-first search to some extent. When this heuristic search algorithm runs, it generally requires the use of a path start point, a path end point, and an evaluation function. This allows it to prioritize expanding the path node that minimizes the evaluation function value starting from the path start point, without relying on path reference lines for path planning.

[0022] In this embodiment, although the heuristic search algorithm can generate vehicle driving path planning results without relying on path reference lines, it is time-consuming, has poor real-time performance, and the generated driving path planning results are prone to significant differences from the user's expected path. The solution in this application constructs the target evaluation function of the heuristic search algorithm by combining the lateral distance between the vehicle and the path reference line. This allows the algorithm to search for available driving paths for the vehicle using the path reference line as a guide. This reduces the time and complexity of path search, improving path planning efficiency and real-time performance, and also makes the generated driving path planning results closer to the user's expected path, thus improving the rationality and accuracy of the path planning results.

[0023] In practical applications, the aforementioned heuristic search algorithms can be of various types, such as the A* search algorithm (i.e., A* algorithm) and the ARA* (Anytime Repairing A*) search algorithm, without specific limitations. The ARA* search algorithm is an improved and optimized version of the A* algorithm. It can provide a suboptimal solution in a very short time and then continuously optimize this solution using the remaining time, making it increasingly closer to the optimal solution. It can achieve a dynamic balance between search efficiency and path optimality, making it suitable for autonomous driving path planning scenarios with high real-time requirements and dynamically changing environments. When the heuristic search algorithm mentioned in step S104 is the ARA* search algorithm, the solution in this application can construct the target evaluation function required by the ARA* search algorithm by combining the lateral distance between the vehicle and the path reference line, thereby further improving its efficiency in finding the optimal solution. This is beneficial for improving the accuracy and timeliness of the generated path planning results, thus meeting the needs of intelligent vehicle control.

[0024] Figure 1 The method described above can obtain path planning information related to the starting point, ending point, and reference line of the path used to characterize the vehicle. By using a heuristic search algorithm, the driving path planning result of the vehicle can be generated efficiently and accurately based on the starting point, ending point, and target evaluation function constructed based on the lateral distance between the vehicle and the reference line. This is beneficial to improving the real-time performance, accuracy, and usability of the vehicle driving path planning scheme.

[0025] In some feasible implementations, the path reference line may include at least one of the following: the lane centerline of the lane in which the vehicle is located, the estimated driving trajectory of the vehicle, the driving trajectory of the target vehicle being followed, and the historical planned path of the vehicle.

[0026] The historical planned paths of this vehicle may include, but are not limited to: the most recent available planned path of this vehicle generated using the heuristic search algorithm based on the target evaluation function, or available planned paths of this vehicle generated within a historical time period with an interval less than or equal to a preset duration (e.g., tens of milliseconds to several seconds) from the current time. The aforementioned available planned paths can refer to planned paths that can meet vehicle control requirements and ensure driving safety and stability, which will not be elaborated further.

[0027] The lane centerline of the lane in which this vehicle is located may include: the lane centerline of the lane in which this vehicle is located, determined based on at least one of the vehicle's surrounding environment perception data and electronic map data. The driving trajectory of the vehicle being followed may include: the driving trajectory of the vehicle ahead within a recent period (e.g., several seconds or tens of seconds) when this vehicle is following the vehicle. The estimated driving trajectory of this vehicle may include: the driving trajectory that this vehicle may generate within a certain future period (e.g., several seconds or tens of seconds) estimated based on the vehicle's motion state data (e.g., speed, acceleration, heading, wheel angle). No specific limitations are imposed on this.

[0028] In some feasible implementations, when the number of path reference line types is 1, the value of the actual cost function in the target evaluation function can be positively correlated with the lateral distance between the vehicle and the path reference line. Alternatively, When the number of path reference line types is greater than 1, the value of the actual cost function in the target evaluation function can be positively correlated with the comprehensive lateral distance between the vehicle and each type of path reference line; wherein, the comprehensive lateral distance can be determined based on the lateral distance between the vehicle and each type of path reference line and the weights corresponding to each type of path reference line, and the weights corresponding to each type of path reference line can be related to the driving scenario type in which the vehicle is located.

[0029] In this embodiment, the target evaluation function may include an actual cost function and a heuristic estimated cost function. The actual cost function represents the true cumulative cost from the starting point of the path to the planned current path node. The heuristic estimated cost function represents the estimated cost from the current path node to the path endpoint. The value of the target evaluation function may be positively correlated with the values ​​of the actual cost function and the heuristic estimated cost function, respectively.

[0030] In this embodiment, the path reference line of the vehicle can represent the path that the user expects the vehicle to travel to a certain extent. In this case, the actual cost function in the target evaluation function can be constructed based on the lateral distance between the vehicle and the path reference line. Furthermore, the lateral distance between the vehicle and the path reference line can be positively correlated with the value of the actual cost function, so that the path reference line can be used as guidance information to quickly search for a suitable path, which is beneficial to improving the efficiency and accuracy of the vehicle driving path planning scheme.

[0031] Specifically, when running a path planning scheme, only one path reference line for the vehicle may be obtained. In this case, the value of the actual cost function in the target evaluation function can be positively correlated with the lateral distance between the vehicle and that path reference line, which is convenient and fast.

[0032] Alternatively, during the path planning process, multiple path reference lines may be obtained for the vehicle, such as the lane centerline of the current lane, the vehicle's estimated trajectory, the trajectory of the vehicle's following target, and the vehicle's historical planned path. In this case, the weights of each type of path reference line can be determined based on the driving scenario. By combining the lateral distance between the vehicle and each type of path reference line with their respective weights, a comprehensive lateral distance between the vehicle and each type of path reference line can be calculated. This comprehensive lateral distance is then positively correlated with the value of the actual cost function in the target evaluation function. This helps to achieve collaboration and smooth transition among multiple path reference lines, improving the continuity and robustness of the path planning results.

[0033] In practical applications, the driving scenario type of this vehicle can be set according to actual needs, such as highway scenarios, urban road scenarios, intersection scenarios, turning scenarios, traffic congestion scenarios, and unstructured / complex scenarios. The weights corresponding to various path reference lines under specific driving scenario types can also be set according to actual needs. For example, in highway scenarios, the lane center line of the vehicle's current lane or the vehicle's historical planned path can be given higher weight. In traffic congestion scenarios, the trajectory of the vehicle's following target can be given higher weight. In unstructured / complex scenarios, the vehicle's estimated trajectory can be given higher weight. No specific limitations are imposed on any of these.

[0034] Understandably, nearby path nodes in the planned driving path have a significant impact on the vehicle's current control commands and safety, thus requiring high accuracy to ensure vehicle stability and safety. Conversely, distant path nodes primarily provide macroscopic guidance and are greatly affected by dynamic environmental changes, allowing for a more relaxed accuracy requirement. Furthermore, for the same driving scenario, different positions on the same path reference line can correspond to multiple weights. For example, positions closer to the path start point can have higher weights, enhancing the flexibility of path planning; no specific limitations are imposed on this.

[0035] Figure 2 This is a schematic diagram illustrating a path planning scenario provided in an embodiment of this application. For ease of understanding, it is illustrated herein in conjunction with... Figure 2 An example is given to illustrate the actual cost function in the objective evaluation function. For example... Figure 2As shown, assume that during vehicle path planning, the lane centerline 202 of the road where vehicle 201 is located and the historical planned path 203 of vehicle 201 are obtained as path reference lines, and the locations of the path start point 204 and the path end point 205 are also obtained. In this case, the current driving scenario type of vehicle 201 can be determined first, and then the weights of various path reference lines under this driving scenario type can be determined. During the path search process, the comprehensive lateral distance can be calculated based on the lateral distance between the path nodes and multiple types of path reference lines (e.g., lane centerline 202 and historical planned path 203) and the aforementioned weights, thereby determining the actual cost function in the target evaluation function. This will not be elaborated further.

[0036] In some feasible implementations, the value of the actual cost function may also be positively correlated with at least one of the vehicle's lane crossing cost, collision cost, and heading change cost.

[0037] Specifically, when the vehicle is located within the cross-lane cost calculation area corresponding to the adjacent lane boundary line, the cross-lane cost is negatively correlated with the distance from the vehicle to the adjacent lane boundary line. The cross-lane cost calculation area includes the region within the target width range of the adjacent lane boundary line closer to the vehicle. And / or, when the vehicle is located within the cross-lane cost calculation area corresponding to the adjacent lane boundary line, the cross-lane cost corresponding to the same distance between the vehicle and the adjacent lane boundary line may differ for different types of adjacent lane boundary lines. And / or, when the adjacent lane boundary line is a non-crossable lane boundary line, the cross-lane cost corresponding to the entire vehicle body crossing the adjacent lane boundary line may be greater than the cross-lane cost corresponding to the partial vehicle body crossing the adjacent lane boundary line. And / or, when the adjacent lane boundary line is a crossable lane boundary line, the cross-lane cost corresponding to the entire vehicle body crossing the adjacent lane boundary line may be less than the cross-lane cost corresponding to the partial vehicle body crossing the adjacent lane boundary line.

[0038] When the distance between the vehicle and the static obstacle is less than or equal to a first distance, the collision cost may be negatively correlated with the distance between the vehicle and the static obstacle; and / or, the collision cost corresponding to a collision between the vehicle and the static obstacle may be greater than the collision cost corresponding to a collision when the vehicle does not collide with the static obstacle.

[0039] The cost of the heading change can be positively correlated with the difference in heading angle between adjacent path nodes. And / or, for different driving scenario types, the cost of the heading change when the vehicle generates the same difference in heading angle between adjacent path nodes can be different.

[0040] In the embodiments of this application, vehicle driving scenarios often have multiple conflicting requirements, making the path planning problem a multi-objective optimization problem. In order to meet the multiple requirements of safety, efficiency, comfort, and regulations during path planning, in addition to constructing the actual cost function in the objective evaluation function by combining the lateral distance between the vehicle and the path reference line, the actual cost function can also be constructed by combining the vehicle's crossing cost, collision cost, heading change cost, or other types of path planning costs, so as to generate accurate, robust, and human-like path planning results.

[0041] In this embodiment, the lane crossing cost can be used to measure the degree to which a vehicle's trajectory deviates from the lane centerline of its current lane or crosses the boundary line of an adjacent lane. Setting a lane crossing cost helps guide vehicles to travel within their current lane, reducing the risk of vehicles continuously crossing lane lines, illegally changing lanes, or running off the road.

[0042] Specifically, the cross-lane cost calculation area corresponding to the adjacent lane boundary lines of the vehicle (e.g., the nearest lane boundary line on the left and right sides of the vehicle) can be pre-defined. Generally, when a path node is located within this cross-lane cost calculation area, the vehicle is considered to have a high risk of crossing lanes. In this case, when the vehicle's path node is within this area, the distance from the vehicle to the adjacent lane boundary line can be negatively correlated with the cross-lane cost; conversely, when the vehicle's path node is outside this area, the corresponding cross-lane cost can be set to a fixed value (e.g., 0 or other values). This improves both path planning efficiency and the rationality and safety of the path planning results. In practical applications, the cross-lane cost calculation area can be set according to actual needs. For example, it can include the area within a target width range (e.g., tens to hundreds of centimeters) of the adjacent lane boundary line closest to the vehicle, or it can include the area within a specified width range of the adjacent lane boundary line furthest from the vehicle; there are no specific limitations on this. In practical applications, when the distance from the vehicle to the boundary line of the adjacent lane decreases linearly, the corresponding crossing cost can increase exponentially, or it can increase in other ways, without specific limitations.

[0043] In practical applications, the types of adjacent lane boundary lines for this vehicle can vary. For example, there may be dashed lane lines that allow lane changes, solid lane lines that do not allow lane changes, and lane boundary lines formed by guardrails or curbs. No specific limitations are imposed on these. It is understandable that the risks associated with driving over or crossing different types of adjacent lane boundary lines will differ. For instance, driving over or crossing a dashed lane line carries a lower risk, driving over or crossing a solid lane line carries a legal risk, and driving over or crossing a lane boundary line formed by guardrails or curbs carries a higher safety risk. In such cases, when the vehicle is located within the calculation area for the crossing cost corresponding to an adjacent lane boundary line, the crossing cost for the same distance between the vehicle and that adjacent lane boundary line can differ depending on the type of adjacent lane boundary line. For example, the crossing cost when the vehicle is at a specific distance from the adjacent dashed lane line can be less than the crossing cost when the vehicle is at that specific distance from the adjacent solid lane line, or the crossing cost when the vehicle is at a specific distance from the adjacent solid lane line can be less than the crossing cost when the vehicle is at that specific distance from the adjacent curb. No specific limitations are imposed on this.

[0044] In practical applications, the lane boundary lines adjacent to this vehicle can include: lane boundary lines that cannot be crossed and lane boundary lines that can be crossed. Lane boundary lines that cannot be crossed can refer to lane boundary lines where there is a high safety risk or legal risk if the vehicle drives over or crosses them; for example, these can include solid lane lines, lane boundary lines formed by guardrails, or curbs. Lane boundary lines that can be crossed can refer to lane boundary lines where there is a low safety risk or legal risk if the vehicle drives over or crosses them; for example, dashed lane lines. No specific limitations are imposed on this.

[0045] In this situation, when the adjacent lane boundary line is a non-crossable type, ensuring that the crossing cost for the entire vehicle body to cross the adjacent lane boundary line is greater than the crossing cost for only part of the vehicle body to cross the adjacent lane boundary line helps prevent traffic violations or leaving the road area. Alternatively, when the adjacent lane boundary line is a crossable type, ensuring that the crossing cost for the entire vehicle body to cross the adjacent lane boundary line is less than the crossing cost for only part of the vehicle body to cross the adjacent lane boundary line facilitates normal lane changes and improves route planning flexibility.

[0046] In this embodiment, collision cost can be used to measure the risk of overlap or excessive proximity between the vehicle and a static obstacle in the environment. Since the collision risk is low when the distance between the obstacle and the vehicle's path node is too far, the corresponding collision cost can be set to a fixed value (e.g., 0 or other values). When the distance between the obstacle and the vehicle's path node (e.g., Euclidean distance) is close (e.g., the distance is less than or equal to a first distance), the collision cost can be negatively correlated with the distance between the vehicle and the static obstacle, and the collision cost corresponding to a collision with the static obstacle can be greater than the collision cost corresponding to a collision without a collision. This helps reduce the collision risk between the vehicle and the static obstacle. The aforementioned first distance can be set according to actual needs, for example, from tens of centimeters to tens of meters, without specific limitation. In practical applications, when the distance between the vehicle and the static obstacle decreases linearly, the corresponding collision cost can increase exponentially, or it can exhibit other increasing trends, without specific limitation.

[0047] In this embodiment, the heading change cost can be used to measure the magnitude of the change in the vehicle's heading angle between different path nodes, which is directly related to the vehicle's kinematic feasibility and ride comfort. In this case, by making the heading change cost positively correlated with the difference in the vehicle's heading angle between adjacent path nodes, it helps to improve the smoothness of the path planning results.

[0048] In practical applications, the amount of heading angle change required for safe driving varies depending on the type of driving scenario. For example, the required heading angle change for safe driving on a straight road is smaller, while the required heading angle change for safe driving on a curve is larger. Therefore, the heading change cost for the same heading angle difference between adjacent path nodes can differ depending on the driving scenario type, which helps improve the flexibility and rationality of path planning. Specifically, different weights corresponding to different driving scenario types can be pre-configured to determine the heading change cost by combining the heading angle difference between adjacent path nodes and the weight corresponding to the current driving scenario type. The weights corresponding to different driving scenario types can be set according to actual needs; for example, the weight for a straight road can be greater than the weight for a curve, without specific limitations.

[0049] For ease of understanding, this is combined with Figure 2 Examples are provided to illustrate the costs of crossing lanes, collisions, and changes in course for this vehicle. For instance... Figure 2As shown, the right-side adjacent lane boundary line 206 of this vehicle can have a corresponding cross-lane cost calculation area 207, and the left-side adjacent lane boundary line 208 of this vehicle can have a corresponding cross-lane cost calculation area 209. When the path node of this vehicle is located in the cross-lane cost calculation area 209, the distance from the path node to the left-side adjacent lane boundary line 208 of this vehicle can be negatively correlated with the corresponding cross-lane cost. For example, the cross-lane cost corresponding to path node 211 can be greater than the cross-lane cost corresponding to path node 212. The cross-lane cost corresponding to a path node located outside the cross-lane cost calculation area (e.g., path node 210) can be a fixed value.

[0050] Assuming there is a static obstacle 213 in front of the vehicle, when the distance between the path node of the vehicle and the static obstacle 213 is less than or equal to a first distance, the smaller the distance between the path node and the static obstacle 213, the greater the relative collision cost can be. Furthermore, the collision cost when the vehicle collides with the static obstacle can also be greater than the collision cost when the vehicle does not collide with the static obstacle.

[0051] Assuming that the heading angles of this vehicle at two adjacent path nodes in the planned route are a first heading angle of 214 and a second heading angle of 215, then the difference in heading angles between adjacent path nodes can be the difference between the first heading angle of 214 and the second heading angle of 215. Furthermore, as this difference in heading angles increases, the corresponding cost of heading changes can also increase.

[0052] In some feasible implementations, the step of generating the vehicle's driving path planning result using a heuristic search algorithm based on the path start point, the path end point, and the target evaluation function may include: Using a heuristic search algorithm, the driving path planning result of this vehicle is generated based on the path start point, the path end point, the target evaluation function, and the path planning constraint information.

[0053] The path planning constraint information may include at least one of the following: search step size constraint information and heading change constraint information.

[0054] The search step size constraint information can be used to reflect that the search step size used by the heuristic search algorithm during operation is positively correlated with the current driving speed of the vehicle.

[0055] The heading change constraint information can be used to reflect that the maximum heading angle difference allowed between adjacent path nodes is negatively correlated with the current speed of the vehicle, and / or the maximum heading angle difference is positively correlated with the search step size, and / or the maximum heading angle difference is positively correlated with the maximum lateral acceleration allowed for the vehicle.

[0056] In this embodiment, path planning constraint information can be set according to actual needs, so that the heuristic search algorithm can generate driving path planning results that conform to the path planning constraint information. The path planning constraint information can be of various types; for example, the heuristic search algorithm needs to use a search step size parameter, which defines the increment in time or distance when the algorithm expands from the current path node to the next candidate path node. Setting a reasonable search step size helps balance search time and search space. Based on this, the path planning constraint information can include: search step size constraint information reflecting a positive correlation between the search step size used by the heuristic search algorithm and the vehicle's current driving speed (e.g., longitudinal driving speed, overall driving speed), which is beneficial for ensuring path planning efficiency.

[0057] To improve the dynamic feasibility of the planned path and the driving comfort of the vehicle, the path planning constraint information can include heading change constraint information reflecting the maximum allowable heading angle difference between adjacent path nodes. Specifically, this heading change constraint information can characterize that the maximum allowable heading angle difference between adjacent path nodes is negatively correlated with the vehicle's current speed, and / or, the maximum heading angle difference can be positively correlated with the search step size and the maximum allowable lateral acceleration of the vehicle. This allows for a more flexible approach when the vehicle speed is high, reducing the possible heading angle change within a shorter path; and when the vehicle's lateral acceleration is large or the search step size is large, relaxing the restrictions on the possible heading angle change within a shorter path.

[0058] In some feasible implementations, the step of generating the vehicle's driving path planning result using a heuristic search algorithm based on the path start point, the path end point, and the target evaluation function may include: Using a heuristic search algorithm, the initial planned path for this vehicle is generated based on the path start point, the path end point, and the target evaluation function.

[0059] By using a constrained iterative linear quadratic regulator, the initial planned path is smoothed to obtain the vehicle's driving path planning result.

[0060] In this embodiment, the Constrained Iterative Linear Quadratic Regulator (CILQR) is a smoothing algorithm widely used in autonomous driving motion planning. It is commonly used to generate planned paths that conform to the vehicle's kinematics model, satisfy road geometric constraints, and simultaneously consider driving comfort and other personalized needs. By using a heuristic search algorithm to generate the initial planned path for the vehicle based on the objective evaluation function, and then using the Constrained Iterative Linear Quadratic Regulator to smooth this initial planned path, the smoothness of the vehicle's driving path planning results and driving comfort are improved.

[0061] In some feasible implementations, the step of smoothing the initial planned path using a constrained iterative linear quadratic regulator to obtain the vehicle's driving path planning result may include: Based on the vehicle's initial speed limit information, the preset vehicle model, and the initial planned path, the initial simulation trajectory of the vehicle is generated.

[0062] Determine the target speed limit information corresponding to the maximum curvature of the initial simulation trajectory.

[0063] Based on the target speed limit information, the preset vehicle model, and the initial planned path, the target simulation trajectory of the vehicle is generated, and the initial solution of the constrained iterative linear quadratic regulator is obtained.

[0064] By using a constrained iterative linear quadratic regulator and smoothing the initial solution based on path smoothing constraint information, the driving path planning result of the vehicle is obtained.

[0065] In this embodiment, the initial speed limit information of the vehicle can characterize the maximum (longitudinal) speed allowed on the road where the vehicle is currently located. For example, the initial speed limit information of the road where the vehicle is located can be determined by combining the vehicle's current positioning data and electronic map data. Alternatively, a preset value can be used as the initial speed limit information of the road where the vehicle is located. Or, the initial speed limit information of the road where the vehicle is located can be obtained from the vehicle's surrounding environment perception data. No specific limitations are imposed on this.

[0066] In practical applications, the initial speed limit information obtained during vehicle path planning may lack accuracy. Furthermore, the vehicle's speed limit value can be negatively correlated with the curvature of its trajectory. In such cases, the initial planned path can be used to estimate a more accurate target speed limit for the road where the vehicle is located. This target speed limit information can then be used to smooth the initial planned path, improving the smoothness and rationality of the planned path.

[0067] Specifically, simulation processing can be performed first based on the vehicle's initial speed limit information, a preset vehicle model, and the vehicle's initial planned path to generate an initial simulation trajectory for the vehicle traveling along that path. After determining the maximum curvature at the initial simulation trajectory, a speed limit value matching the maximum curvature at that trajectory can be determined as the target speed limit information based on calibration information or other principles. By combining the target speed limit information, the preset vehicle model, and the vehicle's initial planned path for further simulation processing, the generated target simulation trajectory can be used as the initial solution for a constrained iterative linear quadratic regulator, which helps improve the accuracy and rationality of the initial solution used during smoothing. The preset vehicle model can include a bicycle model and other types of vehicle motion models; no specific limitations are imposed.

[0068] In practical applications, the path smoothing constraint information required by the constraint iterative linear quadratic regulator can be set according to actual needs. This path smoothing constraint information can be of various types, such as the target speed limit information used to characterize the maximum speed allowed for the vehicle, and the path curvature constraint information used to characterize the maximum curvature allowed at the vehicle's trajectory. No specific limitations are imposed on these.

[0069] In some feasible implementations, when there is no historical planned path for the vehicle, for example, during the first path planning cycle, the starting point of the vehicle's path may include the location of the vehicle.

[0070] When a historical planned path for the vehicle exists, for example, in a path planning cycle following the first, the starting point of the vehicle's path can include a position two distances ahead of the vehicle's projected position on the historical planned path. The historical planned path can include the most recently generated available planned path for the vehicle, or it can be an available planned trajectory generated within a recent period. The aforementioned second distance can be set according to actual needs, for example, several meters or tens of meters. No specific limitation is made.

[0071] The destination of this vehicle's path can be a location at a specified distance (e.g., tens of meters or hundreds of meters) from the vehicle's current driving baseline and the vehicle's starting point or current location. The vehicle's current driving baseline can include the center line of the lane the vehicle is currently in, the vehicle's most recently available planned path, or a possible driving trajectory determined using other principles; no specific limitations are imposed on this.

[0072] For ease of understanding, this is combined with Figure 2 Here are some examples illustrating the starting and ending points of the route for this vehicle. For instance... Figure 2As shown, assuming that during vehicle path planning, the lane centerline 202 of the road where vehicle 201 is located and the historical planned path 203 can be obtained, then the position two distances ahead of the projection position of vehicle 201 on the historical planned path 203 can be used as the path start point 204. And, the position on the historical planned path 203 that is a specified distance from the path start point 204 or the position of vehicle 201 can be used as the path end point 205. If the historical planned path 203 cannot be obtained, but the lane centerline 202 of the road where vehicle 201 is located is obtained, the endpoint of the lane centerline 202 closer to the vehicle can be used as the path start point, and the position on the lane centerline 202 that is a specified distance from the path start point or the position of vehicle 201 can be used as the path end point. The aforementioned historical planned path 203 can be the most recently planned available driving path for the vehicle, and there are no specific limitations on it.

[0073] In some feasible implementations, generating the initial planned path for the vehicle using a heuristic search algorithm based on the path start point, the path end point, and the target evaluation function may include: Using a heuristic search algorithm, based on the target evaluation function, a first planned path for the vehicle from the starting point to the ending point of the path is generated, thus obtaining the initial planned path for the vehicle.

[0074] Correspondingly, the process of smoothing the initial planned path using a constrained iterative linear quadratic regulator to obtain the vehicle's driving path planning result may include: The initial planned path is smoothed using a constrained iterative linear quadratic regulator to obtain the second planned path for the vehicle.

[0075] The second planned path and the first historical planned path of the vehicle are spliced ​​together to obtain the driving path planning result of the vehicle; wherein, the first historical planned path may include: the path from the current position of the vehicle to the starting point of the path in the historical planned path of the vehicle.

[0076] In this embodiment, when a historical planned path for the vehicle exists, the starting point of the path can be a position two distances ahead of the vehicle's projected position on the historical planned path, rather than the vehicle's current position. In this case, on the one hand, the first historical planned path from the vehicle's current position to the starting point can be continued; on the other hand, a heuristic search algorithm and a constrained iterative linear quadratic regulator can be used to generate a smooth and accurate second planned path from the starting point to the ending point of the path. By splicing the first historical planned path and the second planned path of the vehicle as the driving path planning result generated in the current path planning cycle, the path across cycles can remain consistent and continuous, which is beneficial to improving the smoothness and stability of the entire path planning process.

[0077] In some feasible implementations, generating the initial planned path for the vehicle using a heuristic search algorithm based on the path start point, the path end point, and the target evaluation function may include: Using a heuristic search algorithm, based on the target evaluation function, a third planned path is generated for the vehicle from the starting point of the path to the ending point of the path.

[0078] The third planned path is spliced ​​with the second historical planned path of the vehicle to obtain the initial planned path of the vehicle; wherein, the second historical planned path may include: the path from the current position of the vehicle to the starting point of the path in the historical planned path of the vehicle.

[0079] In this embodiment, when a historical planned path for the vehicle exists, the starting point of the path can be a position two distances ahead of the vehicle's projected position on the historical planned path, rather than the vehicle's current position. In this case, on the one hand, a heuristic search algorithm can be used to generate a more accurate third planned path for the vehicle from the path starting point to the path ending point. On the other hand, a second historical planned path from the vehicle's current position to the path starting point can be obtained from the vehicle's historical planned path. By concatenating the second historical planned path and the third planned path for the vehicle, an initial planned path for the vehicle is obtained. Subsequently, a constrained iterative linear quadratic regulator is used to smooth the initial planned path from the vehicle's current position to the path ending point to obtain the vehicle's driving path planning result. This not only ensures that the path across cycles remains consistent and continuous but also improves the smoothness and stability of the entire path.

[0080] It is understandable that when using a constrained iterative linear quadratic regulator to smooth the initial planned path of the vehicle based on path smoothing constraint information, it is possible to generate a path that satisfies the path smoothing constraint information, or it may not. If a path that satisfies the path smoothing constraint information can be generated, the path splicing scheme in the above embodiments can be combined to finally generate a smooth and accurate usable planned path for the vehicle, so that the driving path planning results generated in the current path planning cycle can be used to characterize the usable planned paths of the vehicle. If a path that satisfies the path smoothing constraint information cannot be generated, the driving path planning results generated in the current path planning cycle can be used to characterize the unusable planned paths of the vehicle (e.g., the initial planned path of the vehicle generated using a heuristic search algorithm), so that drivers and passengers can perceive whether the path planning is successful, which is beneficial to improving the user experience.

[0081] Please see Figure 3 This is a schematic flowchart illustrating a vehicle control method provided in an embodiment of this application. The executor of this process can be a program mounted on a domain controller or in the vehicle. Alternatively, the executor of this process can also be a domain controller or the vehicle, or other devices capable of communicating with a domain controller or the vehicle; no specific limitation is made in this regard.

[0082] The following is about Figure 3 The process shown will be described in detail. The vehicle control method may specifically include the following steps: Step S302: Obtain the path planning information of the vehicle; wherein, the path planning information is used to characterize the path start point, path end point and path reference line of the vehicle.

[0083] In this embodiment of the application, step S302 and Figure 1 The implementation principle of step S102 in the process can be consistent, so it will not be elaborated here.

[0084] Step S304: Using a heuristic search algorithm, generate the driving path planning result of the vehicle based on the path start point, the path end point, and the target evaluation function; wherein, the target evaluation function can be an evaluation function constructed based on the lateral distance between the vehicle and the path reference line.

[0085] In this embodiment of the application, step S304 and Figure 1 The implementation principle of step S104 in the process can be consistent, so it will not be elaborated here.

[0086] Step S306: Using the vehicle's active driving assistance function, the vehicle is controlled based on the driving path planning results.

[0087] In this embodiment, the driving assistance function may include functions that, during vehicle operation, control the vehicle's longitudinal and lateral movements and provide safety warnings based on the vehicle's driving path planning results, thereby reducing driver workload and improving safety and comfort. For example, it may include, but is not limited to, Navigate on Autopilot (NOA), Mapless Driving Function, and Level 2 Driving Automation, without specific limitations. By utilizing the vehicle's active driving assistance function to control the vehicle based on accurate, smooth, and continuous driving path planning results, it is beneficial to improve the vehicle's driving safety and ride comfort.

[0088] Figure 3 The method described above can obtain path planning information, including the path start point, path end point, and path reference line, representing the vehicle. Using a heuristic search algorithm, based on the path start point, the path end point, and a target evaluation function constructed based on the lateral distance between the vehicle and the path reference line, the driving path planning result for the vehicle can be generated efficiently and accurately. This allows for the use of the vehicle's active driving assistance functions, and precise driving control based on the vehicle's real-time and accurate driving path planning result, thus improving the real-time performance, accuracy, and usability of vehicle driving path planning and vehicle control schemes.

[0089] In some feasible implementations, the method of utilizing the vehicle's active driving assistance functions to control the vehicle's driving based on the vehicle's driving path planning results includes: When the driving path planning results are used to characterize the available planned paths for the vehicle, the vehicle is controlled to drive along the available planned paths using the vehicle's active driving assistance functions, and / or, the available planned paths are controlled to be displayed in a first visual effect. Alternatively, When the driving path planning results are used to characterize the unavailable planned paths of the vehicle, the vehicle's active driving assistance functions are used to control the display of the unavailable planned paths in a second visual effect, and / or, control the display of obstacle information that poses a collision risk when the vehicle travels along the unavailable planned paths, and / or, control the display of information to indicate that the vehicle does not have available planned paths.

[0090] In the embodiments of this application, when using a heuristic search algorithm and a constrained iterative linear quadratic regulator for path planning, it is possible to generate an available planned path for the vehicle with good safety, accuracy, and smoothness, or it is possible to fail to obtain an available planned path for the vehicle and obtain an unavailable planned path with poor safety, accuracy, and smoothness.

[0091] By utilizing the vehicle's active driving assistance functions to control the vehicle to travel along the available planned path when the currently generated driving path planning result is used to represent the vehicle's available planned path, and / or to control the display of the available planned path in a first-person view, the safety and user experience of the vehicle's operation are improved. Conversely, when the currently generated driving path planning result is used to represent the vehicle's unavailable planned path, the display of the unavailable planned path in a second-person view, information on obstacles posing a collision risk when the vehicle travels along the unavailable planned path, and / or information indicating that there is no available planned path, helps drivers and passengers easily and clearly understand the current path planning status and the risks faced by the vehicle, also contributing to an improved user experience.

[0092] In practical applications, the first visual effect for available planned paths and the second visual effect for unavailable planned paths can often differ. For example, the path color, path brightness, and path width can differ. Alternatively, the two types of paths can be displayed in a static or dynamic manner, or different texts and icons can be used to indicate the two types of paths. There are no specific limitations on this.

[0093] This application also provides a computer program product, which may include a computer program. When the computer program is executed, it can implement the steps of the path planning method and vehicle control method provided in at least some of the above embodiments. For the specific execution process, please refer to the specific description in the above embodiments, which will not be repeated here.

[0094] This application also provides Figure 4 The diagram shows the structure of the electronic device. Figure 4 As shown, at the hardware level, the electronic device may include a processor 41 and a memory 45, and may also include an internal bus 42, a network interface 43, a memory 44, and other hardware required for the services. The processor 41 can read the corresponding computer program from the memory 45 into the memory and then run it to implement the above-mentioned path planning method and vehicle control method. For the specific execution process, please refer to the detailed description in the above embodiments, which will not be repeated here.

[0095] In some feasible implementations, the aforementioned electronic equipment may include at least one of radar equipment, image acquisition equipment, and domain controllers. In addition, it may also include other types of controllers and vehicles, without specific limitations.

[0096] Finally, the various embodiments in this application are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, for embodiments such as computer program products and electronic devices, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiments.

[0097] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A path planning method, comprising: Obtain the path planning information of this vehicle; wherein, the path planning information is used to characterize the path start point, path end point, and path reference line of this vehicle; Using a heuristic search algorithm, the driving path planning result of the vehicle is generated based on the path start point, the path end point, and the target evaluation function; wherein, the target evaluation function is an evaluation function constructed based on the lateral distance between the vehicle and the path reference line.

2. The method according to claim 1, wherein the path reference line comprises: The vehicle's lane centerline, the vehicle's estimated trajectory, the trajectory of the vehicle's following target, and the vehicle's historical planned path are at least one of the following. The historical planned path of this vehicle includes: the most recent available planned path of this vehicle generated based on the target evaluation function using the heuristic search algorithm.

3. According to claim 1, when the number of path reference line types is 1, the value of the actual cost function in the target evaluation function is positively correlated with the lateral distance between the vehicle and the path reference line; or, When the number of path reference line types is greater than 1, the value of the actual cost function in the target evaluation function is positively correlated with the comprehensive lateral distance between the vehicle and each type of path reference line; wherein... The comprehensive lateral distance is determined based on the lateral distance between the vehicle and various types of path reference lines, as well as the weights corresponding to each type of path reference line. Furthermore, the weights corresponding to each type of path reference line are related to the driving scenario in which the vehicle is located.

4. The method according to claim 3, wherein the value of the actual cost function is also positively correlated with at least one of the vehicle's lane crossing cost, collision cost, and heading change cost; When the vehicle is located in the cross-lane cost calculation area corresponding to the adjacent lane boundary line, the cross-lane cost is negatively correlated with the distance from the vehicle to the adjacent lane boundary line. The cross-lane cost calculation area includes the area within the target width range of the adjacent lane boundary line closer to the vehicle. When the distance between the vehicle and the static obstacle is less than or equal to the first distance, the collision cost is negatively correlated with the distance between the vehicle and the static obstacle; The cost of the heading change is positively correlated with the difference in heading angle between adjacent path nodes.

5. The method according to claim 4, wherein when the vehicle is located in the cross-lane cost calculation area corresponding to the adjacent lane boundary line, the cross-lane cost corresponding to the vehicle having the same distance from the adjacent lane boundary line is different for different types of adjacent lane boundary lines; and / or, When the adjacent lane boundary line is a non-crossable lane boundary line, the crossing cost corresponding to the entire vehicle body crossing the adjacent lane boundary line is greater than the crossing cost corresponding to the partial vehicle body crossing the adjacent lane boundary line; and / or, When the adjacent lane boundary line is a crossable lane boundary line, the crossing cost corresponding to the entire vehicle body crossing the adjacent lane boundary line is less than the crossing cost corresponding to a portion of the vehicle body crossing the adjacent lane boundary line; and / or, The collision cost corresponding to the vehicle colliding with the static obstacle is greater than the collision cost corresponding to the vehicle not colliding with the static obstacle; and / or, The cost of heading change varies depending on the type of driving scenario when the vehicle generates the same heading angle difference between adjacent path nodes.

6. The method according to claim 1, wherein generating the vehicle's driving path planning result using a heuristic search algorithm based on the path start point, the path end point, and the target evaluation function includes: Using a heuristic search algorithm, the driving path planning result of this vehicle is generated based on the path start point, the path end point, the target evaluation function, and the path planning constraint information. The path planning constraint information includes at least one of the following: search step size constraint information and heading change constraint information; The search step size constraint information is used to reflect that the search step size used by the heuristic search algorithm is positively correlated with the current driving speed of the vehicle. The heading change constraint information is used to reflect that the maximum heading angle difference allowed between adjacent path nodes is negatively correlated with the current speed of the vehicle, and / or the maximum heading angle difference is positively correlated with the search step size, and / or the maximum heading angle difference is positively correlated with the maximum lateral acceleration allowed for the vehicle.

7. The method according to claim 1, wherein generating the vehicle's driving path planning result using a heuristic search algorithm based on the path start point, the path end point, and the target evaluation function includes: Using a heuristic search algorithm, an initial planned path for the vehicle is generated based on the path start point, the path end point, and the target evaluation function; By using a constrained iterative linear quadratic regulator, the initial planned path is smoothed to obtain the vehicle's driving path planning result.

8. The method according to claim 7, wherein the step of smoothing the initial planned path using a constrained iterative linear quadratic regulator to obtain the vehicle's driving path planning result includes: Based on the vehicle's initial speed limit information, the preset vehicle model, and the initial planned path, the initial simulation trajectory of the vehicle is generated. Determine the target speed limit information corresponding to the maximum curvature of the initial simulation trajectory; Based on the target speed limit information, the preset vehicle model, and the initial planned path, the target simulation trajectory of the vehicle is generated, and the initial solution of the constrained iterative linear quadratic regulator is obtained. By using a constrained iterative linear quadratic regulator and smoothing the initial solution based on path smoothing constraint information, the driving path planning result of the vehicle is obtained.

9. The method according to claim 7, wherein when a historical planned route for the vehicle exists, the starting point of the route includes: The vehicle is positioned at the second distance ahead of its projected location on the historical planned path.

10. The method according to claim 9, wherein generating an initial planned path for the vehicle using a heuristic search algorithm based on the path start point, the path end point, and the target evaluation function comprises: Using a heuristic search algorithm, based on the target evaluation function, a first planned path for the vehicle from the starting point of the path to the ending point of the path is generated, thus obtaining the initial planned path for the vehicle. The process of smoothing the initial planned path using a constrained iterative linear quadratic regulator to obtain the vehicle's driving path planning result includes: The initial planned path is smoothed using a constrained iterative linear quadratic regulator to obtain the second planned path for the vehicle. The second planned path and the first historical planned path of the vehicle are spliced ​​together to obtain the driving path planning result of the vehicle; wherein, the first historical planned path includes: the path from the current position of the vehicle to the starting point of the path in the historical planned path of the vehicle.

11. The method according to claim 9, wherein generating an initial planned path for the vehicle using a heuristic search algorithm based on the path start point, the path end point, and the target evaluation function comprises: Using a heuristic search algorithm, based on the target evaluation function, a third planned path is generated for the vehicle from the starting point of the path to the ending point of the path; The third planned path is spliced ​​with the second historical planned path of the vehicle to obtain the initial planned path of the vehicle; wherein, the second historical planned path includes: the path from the current position of the vehicle to the starting point of the path in the historical planned path of the vehicle.

12. A vehicle control method, comprising: Obtain the path planning information of this vehicle; wherein, the path planning information is used to characterize the path start point, path end point, and path reference line of this vehicle; Using a heuristic search algorithm, the driving path planning result of the vehicle is generated based on the path start point, the path end point, and the target evaluation function; wherein, the target evaluation function is an evaluation function constructed based on the lateral distance between the vehicle and the path reference line; Using the vehicle's active driving assistance functions, and based on the vehicle's driving path planning results, driving control is performed on the vehicle.

13. The method according to claim 12, wherein the step of using the vehicle's activated driving assistance function to perform driving control on the vehicle based on the vehicle's driving path planning result includes: When the driving path planning results are used to characterize the available planned paths for the vehicle, the vehicle is controlled to travel along the available planned paths using the vehicle's active driving assistance functions, and / or, the available planned paths are controlled to be displayed in a first visual effect; or... When the driving path planning results are used to characterize the unavailable planned paths of the vehicle, the vehicle's active driving assistance functions are used to control the display of the unavailable planned paths in a second visual effect, and / or, control the display of obstacle information that poses a collision risk when the vehicle travels along the unavailable planned paths, and / or, control the display of information to indicate that the vehicle does not have available planned paths.

14. A computer program product comprising a computer program that, when executed, performs the steps of the method according to any one of claims 1 to 13.

15. An electronic device comprising: A processor and a memory; wherein the memory stores computer-readable instructions adapted to be loaded by the processor and to perform the steps of the method as claimed in any one of claims 1 to 13.

16. The electronic device of claim 15, wherein the electronic device comprises: At least one of a domain controller, radar equipment, and image acquisition equipment.

Images