Vehicle driving path planning method and readable storage medium in shovel loading area

Abstract

The present invention provides a method for planning a vehicle driving path in a shoveling area and a readable storage medium. The method comprises the following steps: S1. determining the starting point and the end point of the path; S2. exploring the path using a hybrid A* algorithm; if the distance between the current point and the end point is not less than the distance, continuing to explore and move forward; otherwise, turning to S3; S3. generating a connecting path; if there are no obstacles on the connecting path, turning to S4, otherwise, turning to S2; S4. connecting the explored path and the connecting path is the global path of the vehicle. The method for planning a vehicle driving path in the shoveling area can quickly generate a driving path that meets the posture requirements at the starting point and the end point of the path by combining the hybrid A* algorithm with a dynamic curve. Since it is not necessary to use the hybrid A* algorithm to traverse the map throughout the entire process to determine the optimal path, instead, a method of using a dynamic curve to quickly generate a connecting path at the end of the path and then determine obstacles can effectively improve the execution efficiency of the hybrid A* algorithm.

Description

Technical Field

[0001] The present invention relates to the technical field of automatic driving path planning, and in particular to a method for planning a vehicle driving path in a shovel loading area and a readable storage medium. Background Art

[0002] The Hybrid A* algorithm (Hybrid A Star Algorithm) is a global path planning algorithm that is often used in parking scenarios for commercial vehicle autonomous driving, but its application in autonomous driving path planning for mining vehicles is rarely mentioned. On December 31, 2021, the applicant applied for an invention application entitled "A Mining Truck Path Planning Method Based on Global Map Update", which was published on April 12, 2022, with the publication number CN114326744A. The mining truck path planning method is divided into two layers: global path planning and local path planning. The global path planning uses the hybrid A* algorithm to generate a global path as the input of the lower-level local path planning.

[0003] Due to the special characteristics of the shoveling area, such as the complex terrain and uncertain obstacle distribution, and the fact that the hybrid A* algorithm is a search algorithm that traverses nodes on the map, in addition to the problems of long path planning time and high CPU resource usage, it also faces the following challenges: there are certain restrictions on the path endpoints, and it is difficult to guarantee the posture constraints of the vehicle at the path endpoints using the hybrid A* algorithm directly; the endpoints of path planning are uncertain, and it is necessary to consider selecting appropriate endpoints to ensure that the global path generated by the plan is optimal; the planned path needs to consider both forward and reverse states. For the reverse route, the generated path is too long, which will affect the work efficiency of the shoveling area; there are multiple mine cars in the shoveling area at the same time, and there are situations where they enter and exit the shoveling area at the same time. In this case, it is necessary to avoid intersections of mine car paths and collisions. Summary of the Invention

[0004] In view of the problem that the existing path planning method for mining vehicles using a hybrid A* algorithm is difficult to generate a driving path that meets the posture constraints at the path endpoints, the present invention provides a driving path planning method for vehicles in a shoveling area and a readable storage medium.

[0005] The technical solution of the present invention provides a method for planning a vehicle driving path in a shovel loading area, comprising the following steps:

[0006] S1. Determine the starting point and end point of the path;

[0007] S2. Generate an exploration path: Use the hybrid A* algorithm to explore from the starting point to the end point, and record the optimal path obtained during the exploration as the exploration path. If the distance between the current point and the end point is not less than the distance threshold when the exploration is reached, continue the exploration; otherwise, go to S3.

[0008] S3. Generate a connection path: If the distance between the current point and the end point is less than the distance threshold, generate a connection path using a Dubins curve or a Reeds-Shepp curve based on the direction of the explored path at the current point and the orientation of the vehicle at the end point. If there are no obstacles on the connection path, proceed to S4; otherwise, proceed to S2.

[0009] S4. Global path generation step: connecting the exploration path and the connection path is the global path of the vehicle.

[0010] Preferably, in the step of generating an exploration path, the heuristic function used by the hybrid A* algorithm is H=max(d1, d2), where d1 is the Euclidean distance from the current point to the end point taking into account obstacle avoidance, and d2 is the dynamic distance from the current point to the end point without considering obstacles.

[0011] Preferably, in the step of generating an exploration path, a second threshold is preset. If the distance from the current point to the starting point does not exceed the second threshold, the first step length is used to advance; if the distance from the current point to the starting point is greater than the second threshold, the second step length is used to advance, and the first step length is smaller than the second step length.

[0012] Preferably, in the step of determining the path starting point and the path ending point, the main road is traversed to determine the point on the main road closest to the shovel loading point as the projection point; starting from the projection point, a meeting point that meets the requirements is searched along the main road in the opposite direction of the vehicle's travel direction;

[0013] If it is an incoming path, the intersection point is the starting point and the shovel point is the end point; if it is an outgoing path, the shovel point is the starting point and the intersection point is the end point.

[0014] Preferably, the intersection point is determined by advancing from the projection point in the opposite direction of the vehicle's travel direction along the main road with a preset step size; when the advancement reaches the end condition, the advancement is terminated, and the point reached at the termination is the intersection point.

[0015] Preferably, the advancement is terminated when the cut-off condition satisfies at least any one of the following conditions: the advancement curve distance is greater than a predetermined distance value D, and the advancement angle change is greater than a predetermined angle upper limit.

[0016] Preferably, the predetermined distance value Determined by the following formula:

[0017]

[0018] in, is the basic distance, To correct the increment; and They are the direction correction weight and the distance correction weight respectively; is the orientation of the shovel point and the angle to the projection point, is the distance from the shovel point to the projection point, It is the standard value of the distance from the shovel point to the projection point.

[0019] Preferably, in the step of generating a connection path,

[0020] If the first segment of the ReedsShepp curve is a forward route and the first segment is a left-turn path, then the path is discarded, and a new connecting path is generated after changing the current point;

[0021] If the first segment of the ReedsShepp curve is a backward route and the first segment is a right-turn path, then the path is discarded and a new connecting path is generated after changing the current point.

[0022] Preferably, in the step of generating the connection path, the lengths of the five segments of the reverse route of the ReedsShepp curve are added together to obtain the reverse distance ,like If the length is greater than the threshold, the path is discarded and the connection path is regenerated after changing the current point.

[0023] The technical solution of the present invention further provides a readable storage medium storing a computer program. When the computer program is executed by a processor, the processor executes the method for planning a vehicle driving path in a loading area as described in any one of the above items.

[0024] The present method for planning vehicle paths in loading areas combines a hybrid A* algorithm with the Dubins / Reeds-Shepp curve to rapidly generate paths that meet the required poses at both the starting and ending points. This method eliminates the need to use the hybrid A* algorithm to traverse the map and determine the optimal path. Instead, the Dubins / Reeds-Shepp method is used at the end of the path to rapidly generate connecting paths and then determine obstacles. This effectively improves the efficiency of the hybrid A* algorithm. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a schematic diagram of the shovel loading area of ​​the present invention;

[0026] Figure 2 is a schematic diagram of the global path of the present invention;

[0027] Figure 3 Schematic diagram of the propulsion angle change of the present invention. DETAILED DESCRIPTION

[0028] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. In this specification, the size ratios in the drawings do not represent the actual size ratios, but are only used to reflect the relative positional relationship and connection relationship between the various components. Components with the same name or the same number represent similar or identical structures and are only for illustrative purposes.

[0029] Figure 1 This is a typical vehicle driving path in the shoveling area of ​​a mine. The main road for mine vehicles to enter and exit the shoveling area is fixed. All vehicles enter the shoveling area from the outside via the main road, and then exit the shoveling area via the main road. During the entry process, the vehicle first drives off the main road to enter the shoveling area, and then when approaching the shoveling point, it reverses into the shoveling point, so that the vehicle is forward at the shoveling point, which is convenient for forward exit when the vehicle is full. When exiting, the vehicle drives forward in the shoveling area between the shoveling point and the main road, and cuts into the main road in the positive direction when about to enter the main road. In the process of entering the shoveling area, the point where the vehicle exits the main road is called the exit point; in the process of the vehicle exiting the shoveling area, the point where the vehicle enters the main road is called the entry point. In this application, the entry point and the exit point are also collectively referred to as the intersection point.

[0030] In real-world scenarios, the main road is pre-designed and typically leveled and compacted, ensuring vehicle safety. The loading point is also fixed for a given task. Therefore, the goal of global path planning is to design a route connecting the main road and the loading point. As shown in the figure, the route is divided into two types: an approach path and an exit path. For obstacle avoidance, the hybrid A* algorithm can be used for path planning. However, the hybrid A* algorithm can only be used when the starting and ending points of the path are both known. In this scenario, the intersection point is not known, so the hybrid A* algorithm cannot be directly applied. Furthermore, in this scenario, both the loading point and the intersection have requirements for the vehicle's orientation. If the vehicle's orientation deviates significantly at the intersection, it will be unable to successfully exit or enter the main road. In the loading area, incorrect vehicle orientation not only affects the planning of the exit path but also affects loading efficiency. Even if the hybrid A* algorithm can generate a driving path that matches the vehicle's orientation, the algorithm's traversal and advancement process takes a long time to calculate, resulting in low efficiency and inability to quickly generate a global path. Furthermore, even when the intersection point is determined, the hybrid A* algorithm cannot handle the directional constraints at the endpoint. Therefore, the path searched by the hybrid A* algorithm may not meet the required orientation at the endpoint (which may be a shovel point or an intersection point).

[0031] for Figure 1The entry and exit paths involved in the plan are: the entry path starts at the intersection (exit point) and ends at the loading point; the exit path starts at the loading point and ends at the intersection (entry point). Although the directions of the two paths are different, and thus the starting and ending points are different, the path planning methods for both are the same. In the following description, most of the time, only the path starting point and path ending point are discussed. Based on the above description, those skilled in the art will understand that the starting point and ending point have specific meanings in the entry and exit paths.

[0032] To address the issue of the hybrid A* algorithm failing to match the endpoint vehicle's orientation during loading area path planning, the present method for loading area vehicle path planning combines the hybrid A* algorithm with Dubins / ReedShepp curve path planning to ensure that the generated global path meets the required orientation at the target point. To achieve this goal, the specific steps of this loading area vehicle path planning method include:

[0033] S1. Determine the path start and end points. As previously mentioned, for an incoming path, the start point is the intersection point, which is the exit point of the incoming path, and the end point is the loading point. For an outgoing path, the start point is the loading point, and the end point is the intersection point, which is the entry point of the outgoing path.

[0034] S2. Use the hybrid A* algorithm to explore from the starting point toward the end point, recording the optimal path obtained during the exploration as the exploration path; if the distance between the current point and the end point is not less than the distance threshold when the exploration is reached, continue exploring; otherwise, proceed to S3. If the distance during this process is equal to the distance threshold, executing S2 or S3 is equivalent and therefore also falls within the scope of protection of this application.

[0035] S3. If the distance between the current point and the end point is less than the distance threshold, a connecting path is generated using a Dubins curve or a Reeds-Shepp curve based on the direction of the explored path at the current point and the orientation of the vehicle at the end point. If there are no obstacles on the connecting path, go to S4; otherwise, go to S2.

[0036] S4. Connecting the exploration path and the connection path is the global path of the vehicle.

[0037] The details are explained below.

[0038] In step S1, as mentioned above, the intersection point is uncertain during actual planning and should be included in the path planning content. The intersection point itself is the starting point or end point of the global path. The selection of the intersection point follows the following principles: 1. The intersection point (i.e., the entry point and exit point) should be near the excavator projection point, where the excavator projection point refers to the point on the main road closest to the shoveling point; 2. The entry point and exit point should be a certain distance apart along the main road, so as to avoid the intersection of the entry path and the exit path to the greatest extent. Reference Figure 2 , the intersection point can be determined as follows:

[0039] S11. Traverse the main road and determine the point on the main road closest to the shovel installation point as the projection point.

[0040] S12. Search for a meeting point along the main road in the opposite direction of the vehicle's travel direction. Figure 2 For example, for the incoming path, proceed from the projection point toward the bottom of the path in the diagram to find the intersection point, which is also the exit point. For the outgoing path, proceed from the projection point toward the top of the path in the diagram to find the intersection point, which is also the incoming point. In this step, since the incoming and outgoing points are placed on either side of the projection point on the main road, the path lengths for both incoming and outgoing paths are taken into account while ensuring that the incoming and outgoing paths are staggered as much as possible to avoid interference between the two paths during travel.

[0041] In the specific advancement process, the vehicle advances point by point along the main road in the aforementioned specific direction with a certain step length until the predetermined termination condition is met. The point reached by the advancement is the intersection point.

[0042] In the technical solution of the present application, the advancement process is terminated when any of the following conditions is met.

[0043] 1. The distance of the curve being advanced is greater than the predetermined distance value. The predetermined distance should be related to the distance from the shovel point to the projection point and the angular orientation of the shovel point. It is understandable that when the distance is closer and the orientation of the shovel point and the angle to the projection point are larger, the vehicle needs more adjustment space to complete the intersection, so a larger predetermined distance value should be set. In this regard, the predetermined distance value in this application is Determined by the following formula.

[0044]

[0045] in, As the basic distance, in the specific embodiment of the present application, 30m can be taken, that is, the preset distance of advancement is corrected based on the distance of 200m from the shovel loading point to the main road. To correct the increment; and They are the direction correction weight and distance correction weight respectively. is the orientation of the shovel point and the angle to the projection point, is the distance from the shovel point to the projection point, It is the standard value of the distance from the shovel point to the projection point.

[0046] In the above formula, (1+C angle ·sin(A diff )) is the orientation correction coefficient. When the orientation of the shovel point With the projection point

[0047] orientation Angle value When it is zero (due to the direction of the excavator in the shovel loading area The orientation of the vehicle, i.e. the orientation of the shovel point , it is vertical when working. At this time, it is actually equivalent to the excavator facing perpendicular to the line connecting the shovel point and the projection point). The direction correction coefficient is 1, which is the standard case. is the distance correction coefficient, where the standard value of the distance In this application, we take 200m, and the distance from the shovel point to the projection point is For a standard distance of 200m, the distance correction coefficient is set to 1. Since the direction correction coefficient and the shovel installation point, and the distance correction coefficient and the shovel installation point distance are positively correlated, the final adjusted It can dynamically adapt to the situation of the shovel loading point to determine the appropriate intersection point location.

[0048] 2. The propulsion angle change is greater than the preset angle limit. That is, the angle A between the tangent of the nearest point along the running direction T and the tangent of the intersection point along the running direction T is greater than the preset angle limit. This restriction condition is mainly used to limit the problem of excessively long paths and reduced efficiency caused by a large difference between the direction of the intersection point and the direction of the shoveling point. Figure 3 As shown in Figure 1, when A(t) is too large, the generated path will be excessively curved to match the direction of the intersection, which will cause the planned path to be too long, resulting in reduced vehicle operation efficiency.

[0049] 3. The step size of the advancement is greater than the predetermined number of steps. This ensures that the program can at least return acceptable results normally in extreme cases.

[0050] 4. Arriving at the endpoint of the main road. At this point, you should stop advancing and directly use the corresponding endpoint (entrance or exit of the main road) as the intersection point.

[0051] In S2, the heuristic function determines the speed at which the hybrid A* algorithm guides the target. The heuristic function used in this step is H = max(d1, d2). Here, d1 is the Euclidean distance from the current point to the target, taking into account obstacle avoidance, and d2 is the kinetic curve distance from the current point to the target, ignoring obstacles. The maximum of these two values ​​is used as the final heuristic function, which helps find the shortest obstacle-avoiding path that meets the kinetic constraints.

[0052] However, due to the large area of ​​the shoveling area and the long distance between the shoveling point and the main road, in order to compress the running time of the algorithm, this application adopts a variable step size design in S2. The following is a simplified scheme of variable step size. A second threshold is preset. During the advancement of the hybrid A* algorithm, if the distance from the current point to the starting point does not exceed the second threshold, the first step size is used to advance. If the distance from the current point to the starting point is greater than the second threshold, the second step size is used to advance. Here, the first step size is smaller than the second step size. The farther the current point is from the starting point, the more branches the hybrid A* algorithm needs to traverse. The above scheme of increasing the step size at long distances can reduce the number of branches that need to be traversed, which can effectively improve the running efficiency of the algorithm. In this application, the second threshold is 60m. In the hybrid A* algorithm, the step size is related to the change in vehicle orientation allowed at each step. The turning radius of the mine car is R = 12m. When it does not exceed the second threshold, the vehicle turning angle allowed at each step is θ = 7°, so the first step size is L1 = R·rad(θ) = 12·7·(π / 180) = 1.47m. After it is greater than the second threshold, the vehicle turning angle allowed at each step is θ = 15°. Therefore, the second step size is L1 = R·rad(θ) = 12·15·(π / 180) = 3.14m. It should also be noted that in this application, the expansion of the step size has an acceptable impact on the final path and will not affect the horizontal and vertical following of the vehicle. The reason is that only the upper-level global path is obtained through this application. After the path is sent to vehicles such as mine cars, the global path will be smoothed by interpolation processing of the global path locally in the vehicle. The overall design of the program is divided into two steps: route generation and path smoothing. In fact, although the points explored by hybridA* meet the dynamic constraints, they may be curved. If the vehicle is asked to follow directly, frequent left and right turns may occur, and the driving experience is very bad, so smoothing is needed. The usual practice is to convert the smoothing problem into a quadratic programming problem and solve it mathematically. There are many smoothing algorithms, which will not be described here. The step size of hybrid A* is calculated as angle * radius, and the turning range of the vehicle is -45 to 45 degrees. As long as the turning angle of the vehicle is within this range and the route is smoothed, the vehicle can theoretically follow completely. In each step of A* exploration, both the turning angle and the turning radius are smaller than the vehicle calibration value to ensure that the vehicle can follow. In practice, it has been proved that the path generated by the above scheme can be smoothed to achieve vehicle following without any problems. The method based on the hybrid A* algorithm of the present application and the combination of the dynamic path generates a solution for the planned path. On the one hand, the hybrid dynamic path planning at the end avoids the process of continuing to explore and solve the optimal path on the map when approaching the target point; on the other hand, through the reasonable variable step size design, the number of nodes that need to be explored during the A* algorithm exploration path is reduced exponentially compared to the number of nodes in the original solution, thereby improving the solution speed.In actual operation and comparison, in a path planning experiment based on Haibo's intelligent mine cart map, the original hybrid A* algorithm took approximately 39 seconds. The optimized path planning method for the loading area reduced this time to approximately 6 seconds. Further optimization combined with other methods can reduce path planning time to under 1 second, ensuring efficient and intelligent operation of mine carts within the mine.

[0053] In S3, the connection path from the current point to the end point can be generated using the Dubins curve or the Reeds-Shepp curve according to the actual situation. Figure 2 As shown, the exit path is fully forward-connected to the main road, and there is no reversing section. Therefore, either the Dubins or ReedsShepp curve can be used as the connecting path. As for the entry path, in order to ensure that the front of the vehicle faces outward at the shoveling point, the vehicle needs to reverse into the path. Therefore, the ReedsShepp curve must be used for connection. To ensure the smooth generation of the reversing section. However, both the Dubins curve and the ReedsShepp curve are paths obtained by the posture of the vehicle at the two end points of the curve and the dynamic conditions of the vehicle. Neither of them can consider the problem of obstacles on the path. The solution of this application is to first generate a path, and then determine whether there are obstacles on the path. If there are obstacles, then change the starting point and regenerate. That is, if there are obstacles, then discard the already generated connecting path, use the hybrid A* algorithm to continue moving forward one step, and then repeat the generation operation.

[0054] At the same time, if Figure 2 As shown in the figure, there are both entry and exit paths in the loading area. In order to avoid vehicle collisions, the optimal solution is to avoid path intersections during global path planning. Therefore, when using the ReedsShepp curve to generate connecting paths, the directionality of the ReedsShepp curve needs to be considered. If the first segment of the ReedsShepp curve is the forward route and the first segment is marked as L_SEG (steering wheel to the left), then the curve turns left during the forward process. Figure 2 If the curve is close to the exit path and there is a risk of intersection between the two, the curve will be discarded and the connecting path will be regenerated after changing the current point. Similarly, if the first segment of the ReedsShepp curve is the retreat route and the first segment is marked as R_SEG (steering wheel to the right), then the curve turns right during the retreat process. Figure 2 It also shows that it is close to the exit path and needs to be abandoned and the current point changed to regenerate the connecting path.

[0055] For some special shovel positions, the reverse route of the connection path generated by the ReedsShepp curve may be too long in engineering practice, resulting in a long time for the mining truck to enter the position. Therefore, a constraint condition is added to the generation of the ReedsShepp curve: the reverse distance is obtained by adding the lengths of the five reverse routes of the ReedsShepp curve. ,like If the value is >50m, the current route will be abandoned and exploration will continue; otherwise, the successful route will be returned.

[0056] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application may take the form of a computer-usable storage medium containing computer-usable program code in one or more of the embodiments. The present application is described with reference to computer program product diagrams and / or block diagrams implemented on the process materials (including but not limited to disk storage, CD-ROM, optical storage, etc.) of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, may be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the functions in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including the instruction device, which implements the function specified in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0057] The above content only describes the preferred embodiments of the present invention and does not limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solution of the present invention by ordinary technicians in this field should fall within the scope of protection determined by the claims of the present invention.

[0058] Although the embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and variations may be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents, and all should be included within the scope of protection of the present invention.

Claims

1. A method for planning a vehicle driving path in a shovel loading area, characterized in that: The steps include: S1. Determine the starting point and end point of the path. In the step of determining the starting point and end point of the path, traverse the main road to determine the point closest to the shovel loading point on the main road as the projection point; use the projection point as the starting point to search for a meeting point along the main road in the opposite direction of the vehicle's travel direction; If it is an incoming path, the intersection point is the starting point and the shoveling point is the end point; If it is a departure path, the shovel loading point is the starting point and the intersection point is the end point; The intersection point is determined by advancing along the main road from the projection point in the opposite direction of the vehicle's travel direction with a preset step length; when the advancement reaches a termination condition, the advancement is terminated, and the point reached at the termination is the intersection point; The advancement is terminated when the cut-off condition satisfies at least any of the following conditions: the advancement curve distance is greater than a predetermined distance value D, and the advancement angle change is greater than a predetermined angle upper limit; The predetermined distance value D t Determined by the following formula: in, is the basic distance, To correct the increment; and They are the direction correction weight and the distance correction weight respectively; is the orientation of the shovel point and the angle to the projection point, is the distance from the shovel point to the projection point, The standard value of the distance from the shovel point to the projection point S2. Generate an exploration path: Use the hybrid A* algorithm to explore from the starting point to the end point, and record the optimal path obtained during the exploration as the exploration path. If the distance between the current point and the end point is not less than the distance threshold when the exploration is reached, continue the exploration; otherwise, go to S3. S3. Generate a connection path: If the distance between the current point and the end point is less than the distance threshold, generate a connection path using a Dubins curve or a Reeds-Shepp curve based on the direction of the explored path at the current point and the orientation of the vehicle at the end point. If there are no obstacles on the connection path, proceed to S4; otherwise, proceed to S2. S4. Global path generation step: connecting the exploration path and the connection path is the global path of the vehicle.

2. The method for planning a vehicle driving path in a shovel loading area according to claim 1, wherein: In the step of generating an exploration path, the heuristic function used by the hybrid A* algorithm is H=max(d1,d2); where d1 is the Euclidean distance from the current point to the end point taking into account obstacle avoidance, and d2 is the dynamic distance from the current point to the end point without considering obstacles.

3. The method for planning a vehicle driving path in a shovel loading area according to claim 2, wherein: In the step of generating an exploration path, a second threshold is preset. If the distance from the current point to the starting point does not exceed the second threshold, the first step length is used to advance; if the distance from the current point to the starting point is greater than the second threshold, the second step length is used to advance, and the first step length is smaller than the second step length.

4. The method for planning a vehicle driving path in a shovel loading area according to claim 1, wherein: In the step of generating a connection path, If the first segment of the ReedsShepp curve is a forward route and the first segment is a left-turn path, then the path is discarded, and a new connecting path is generated after changing the current point; If the first segment of the ReedsShepp curve is a backward route and the first segment is a right-turn path, then the path is discarded and a new connecting path is generated after changing the current point.

5. The method for planning a vehicle driving path in a shovel loading area according to claim 1, wherein: In the step of generating the connection path, the lengths of the five reverse routes of the ReedsShepp curve are added together to obtain the reverse distance. ,like If the length is greater than the threshold, the path is discarded and the connection path is regenerated after changing the current point.

6. A readable storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a processor, the processor is caused to execute the method for planning a vehicle driving path in a loading area according to any one of claims 1 to 5.

Images