Two-way planning method and device for parking path, computer equipment

Abstract

The application relates to a parking path bidirectional planning method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: obtaining a target forward pose point and a target reverse pose point, determining a forward intermediate pose point between a current pose point and the target reverse pose point according to a preset first path search strategy, and determining a reverse intermediate pose point between the target pose point and the target forward pose point according to a preset second path search strategy. Whether a collision-free path exists between the forward intermediate pose point and the reverse intermediate pose point is determined, and if the collision-free path exists, a parking path is generated according to a collision-free path from the current pose point to the forward intermediate pose point, a collision-free path from the forward intermediate pose point to the reverse intermediate pose point and a collision-free path from the reverse intermediate pose point to the target pose point. The method can improve the parking path planning efficiency in a parking scene.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of path planning, in particular to a bidirectional planning method and device for a parking path, and a computer device. BACKGROUND

[0002] With the development of automatic driving technology, path planning technology has emerged. The most widely used path planning technology is the path planning strategy based on A* algorithm. The path planning strategy based on hybrid A* algorithm further improves the path planning strategy based on A* algorithm, and the planned path is more consistent with the kinematics of the vehicle. In the process of planning the path based on the hybrid A* algorithm, the search pose points are gradually expanded from the current pose point to the front, forming a travel path.

[0003] However, in actual application, in the scenario of parking, the number of obstacles near the parking point is often more. In the above-mentioned path planning strategy based on hybrid A* algorithm, the search difficulty is greatly improved, and the efficiency of path planning is low. SUMMARY

[0004] Therefore, it is necessary to provide a bidirectional planning method, device, computer device, computer readable storage medium and computer program product for a parking path, which can improve the efficiency of path planning.

[0005] In a first aspect, the present application provides a bidirectional planning method for a parking path. The method comprises:

[0006] obtaining a target forward pose point and a target reverse pose point;

[0007] determining a forward intermediate pose point between the current pose point and the target reverse pose point according to a preset first path search strategy, and determining a reverse intermediate pose point between the target pose point and the target forward pose point according to a preset second path search strategy;

[0008] determining whether there is a collision-free path between the forward intermediate pose point and the reverse intermediate pose point;

[0009] if there is, generating a parking path according to the collision-free path from the current pose point to the forward intermediate pose point, the collision-free path from the forward intermediate pose point to the reverse intermediate pose point, and the collision-free path from the reverse intermediate pose point to the target pose point.

[0010] In one of the embodiments, the method further comprises:

[0011] if there is no collision-free path between the forward intermediate pose point and the reverse intermediate pose point, performing the step of obtaining a target forward pose point and a target reverse pose point.

[0012] In one of the embodiments, the method further comprises:

[0013] obtaining each forward pose point in a forward open set; the forward open set comprises the forward pose points searched according to the first path searching strategy;

[0014] for each forward pose point, determining a forward travel cost value corresponding to the forward pose point;

[0015] determining the forward pose point with the minimum forward travel cost value in the forward open set as the forward intermediate pose point.

[0016] In one of the embodiments, the method further comprises:

[0017] obtaining a first forward travel cost value between the forward pose point and the target pose point, and a second forward travel cost value between the forward pose point and the reverse intermediate pose point;

[0018] determining the forward travel cost value corresponding to the forward pose point according to the first forward travel cost value and the second forward travel cost value.

[0019] In one of the embodiments, the method further comprises:

[0020] obtaining each reverse pose point in a reverse open set; the reverse open set comprises the reverse pose points searched according to the second path searching strategy;

[0021] for each reverse pose point, determining a reverse travel cost value corresponding to the reverse pose point;

[0022] determining the reverse pose point with the minimum reverse travel cost value in the reverse open set as the reverse intermediate pose point.

[0023] In one of the embodiments, the method further comprises:

[0024] obtaining a first reverse travel cost value between the reverse pose point and the target pose point, and a second reverse travel cost value between the reverse pose point and the forward intermediate pose point;

[0025] determining the reverse travel cost value corresponding to the reverse pose point according to the first reverse travel cost value and the second reverse travel cost value.

[0026] In a second aspect, the present application provides a parking path bidirectional planning device. The device comprises:

[0027] an acquisition module, configured to acquire a target forward pose point and a target reverse pose point;

[0028] a first determination module, configured to determine a forward intermediate pose point between a current pose point and the target reverse pose point according to a preset first path search strategy, and determine a reverse intermediate pose point between the target pose point and the target forward pose point according to a preset second path search strategy;

[0029] a second determination module, configured to determine whether there is a collision-free path between the forward intermediate pose point and the reverse intermediate pose point;

[0030] a path generation module, configured to, if there is, generate a parking path according to a collision-free path from the current pose point to the forward intermediate pose point, a collision-free path from the forward intermediate pose point to the reverse intermediate pose point, and a collision-free path from the reverse intermediate pose point to the target pose point.

[0031] In one of the embodiments, the device further comprises:

[0032] a loop module, configured to, if there is no collision-free path between the forward intermediate pose point and the reverse intermediate pose point, execute the acquisition module.

[0033] In one of the embodiments, the first determination module is specifically configured to:

[0034] acquire each forward pose point in a forward open set; the forward open set comprises forward pose points searched according to the first path search strategy; for each forward pose point, determine a forward driving cost value corresponding to the forward pose point; determine a forward pose point with a minimum forward driving cost value in the forward open set as the forward intermediate pose point; and determine a reverse intermediate pose point between the target pose point and the target forward pose point according to the preset second path search strategy.

[0035] In one of the embodiments, the first determination module is specifically configured to:

[0036] obtaining each forward pose point in a forward open set, the forward open set comprising the forward pose points searched according to the first path searching strategy, for each forward pose point, obtaining a first forward travel cost value between the forward pose point and the target pose point, and a second forward travel cost value between the forward pose point and the reverse intermediate pose point, determining a forward travel cost value corresponding to the forward pose point according to the first forward travel cost value and the second forward travel cost value, determining a forward intermediate pose point with a minimum forward travel cost value in the forward open set as the reverse intermediate pose point, and determining a reverse intermediate pose point between the target pose point and the target forward pose point according to a preset second path searching strategy.

[0037] In one of the embodiments, the first determining module is specifically configured to:

[0038] obtaining a forward intermediate pose point between the current pose point and the target reverse pose point according to a preset first path searching strategy, obtaining each reverse pose point in a reverse open set, the reverse open set comprising the reverse pose points searched according to the second path searching strategy, for each reverse pose point, determining a reverse travel cost value corresponding to the reverse pose point, and determining a reverse intermediate pose point with a minimum reverse travel cost value in the reverse open set as the reverse intermediate pose point.

[0039] In one of the embodiments, the first determining module is specifically configured to:

[0040] obtaining a forward intermediate pose point between the current pose point and the target reverse pose point according to a preset first path searching strategy, obtaining each reverse pose point in a reverse open set, the reverse open set comprising the reverse pose points searched according to the second path searching strategy, for each reverse pose point, obtaining a first reverse travel cost value between the reverse pose point and the target pose point, and a second reverse travel cost value between the reverse pose point and the forward intermediate pose point, determining a reverse travel cost value corresponding to the reverse pose point according to the first reverse travel cost value and the second reverse travel cost value, and determining a reverse intermediate pose point with a minimum reverse travel cost value in the reverse open set as the reverse intermediate pose point.

[0041] In a third aspect, the present application provides a computer device. The computer device comprises a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0042] obtaining a target forward pose point and a target reverse pose point;

[0043] determine a forward intermediate pose point between the current pose point and the target reverse pose point according to a preset first path searching strategy, and determine a reverse intermediate pose point between the target pose point and the target forward pose point according to a preset second path searching strategy;

[0044] determine whether there is a collision-free path between the forward intermediate pose point and the reverse intermediate pose point;

[0045] if there is, generate a parking path according to the collision-free path from the current pose point to the forward intermediate pose point, the collision-free path from the forward intermediate pose point to the reverse intermediate pose point, and the collision-free path from the reverse intermediate pose point to the target pose point.

[0046] In a fourth aspect, the present application further provides a computer readable storage medium. The computer readable storage medium has a computer program stored thereon, and the computer program is executed by a processor to implement the following steps:

[0047] obtain a target forward pose point and a target reverse pose point;

[0048] determine a forward intermediate pose point between the current pose point and the target reverse pose point according to a preset first path searching strategy, and determine a reverse intermediate pose point between the target pose point and the target forward pose point according to a preset second path searching strategy;

[0049] determine whether there is a collision-free path between the forward intermediate pose point and the reverse intermediate pose point;

[0050] if there is, generate a parking path according to the collision-free path from the current pose point to the forward intermediate pose point, the collision-free path from the forward intermediate pose point to the reverse intermediate pose point, and the collision-free path from the reverse intermediate pose point to the target pose point.

[0051] In a fifth aspect, the present application further provides a computer program product. The computer program product comprises a computer program, and the computer program is executed by a processor to implement the following steps:

[0052] obtain a target forward pose point and a target reverse pose point;

[0053] determine a forward intermediate pose point between the current pose point and the target reverse pose point according to a preset first path searching strategy, and determine a reverse intermediate pose point between the target pose point and the target forward pose point according to a preset second path searching strategy;

[0054] determine whether there is a collision-free path between the forward intermediate pose point and the reverse intermediate pose point;

[0055] If the collision-free path exists, a parking path is generated according to the collision-free path from the current pose point to the forward intermediate pose point, the collision-free path from the forward intermediate pose point to the reverse intermediate pose point, and the collision-free path from the reverse intermediate pose point to the target pose point.

[0056] The parking path bidirectional planning method, device, computer device, storage medium and computer program product accelerate the efficiency of finding a collision-free path and effectively improve the planning efficiency of the parking path in the scenario of parking path planning. BRIEF DESCRIPTION OF DRAWINGS

[0057] Figure 1 A basic flowchart of a hybrid A* algorithm path planning strategy in an embodiment is shown in FIG. 1.

[0058] Figure 2 A flowchart of a parking path bidirectional planning method in an embodiment is shown in FIG. 2.

[0059] Figure 3 A schematic diagram of the orientation angle of Node1 pointing to Node2 in an embodiment is shown in FIG. 3.

[0060] Figure 4 A flowchart of a parking path bidirectional planning method in another embodiment is shown in FIG. 4.

[0061] Figure 5 A structural block diagram of a parking path bidirectional planning device in an embodiment is shown in FIG. 5.

[0062] Figure 6 An internal structure diagram of a computer device in an embodiment is shown in FIG. 6. DETAILED DESCRIPTION

[0063] To make the objects, technical solutions and advantages of the present application clearer, the present application is further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0064] In the related art, the path planning strategy based on the hybrid A* algorithm considers the actual motion constraints of the object on the basis of the A* algorithm path planning strategy. The basic flow of the hybrid A* algorithm path planning strategy is shown in FIG. 1. Figure 1

[0065] 1. First, determine the current pose point and the target pose point to which the vehicle travels in the path planning, and initialize the open set as the current pose point and the closed set as empty.

[0066] 2. Determine whether the open set is empty. If it is empty, it means that the path search fails; if it is not empty, continue to step 3.​

[0067] 3. Determine the total cost f of each pose point in the open set, and select the pose point with the minimum cost in the open set as the intermediate pose point, and add the intermediate pose point to the closed set. The total cost f of each pose point includes two parts, a motion cost term g and a heuristic cost term h, the motion cost term g is used to represent the driving cost from the current pose point to the pose point, and the heuristic cost h is used to represent the heuristic cost from the pose point to the target pose point.

[0068] 4. Detect whether there is a collision-free path between the intermediate pose point and the target pose point. If there is, then the planned path from the current pose point to the intermediate pose point and the collision-free path from the intermediate pose point to the target pose point are taken as the final planned path; if not, then step 5 is continued.

[0069] 5. Determine and select a neighboring pose point of the intermediate pose point according to the kinematic formula.

[0070] 6. Determine whether there is a collision-free path between the neighboring pose point and the intermediate pose point. If there is, then step 7 is continued; if not, then step 5 is returned.

[0071] 7. Determine whether the neighboring pose point is in the closed set. If yes, then step 5 is returned; if not, then step 8 is continued.

[0072] 8. Calculate the motion cost g from the current pose point to the neighboring pose point according to the motion cost from the current pose point to the intermediate pose point and the motion cost from the intermediate pose point to the neighboring pose point.

[0073] 9. Determine whether the neighboring pose point is in the open set. If yes, then step 10 is executed; if not, then step 12 is executed.

[0074] 10. Determine the size of the motion cost g of the neighboring pose point and the motion cost g of the neighboring pose point saved in the open set. If the motion cost g of the neighboring pose point is not less than the motion cost g of the neighboring pose point saved in the open set, then step 2 is directly returned. If the motion cost g of the neighboring pose point is less than the motion cost g of the neighboring pose point saved in the open set, then step 11 is executed.

[0075] 11. Update the motion cost g of the neighboring pose point, the parent node of the neighboring pose point and the total cost f of the neighboring pose point in the open set, and return to step 2.

[0076] 12. Calculate the heuristic cost h of the neighboring pose point, and calculate the total cost f of the neighboring pose point according to the motion cost g and the heuristic cost h of the neighboring pose point, record its parent node as the intermediate pose point, and add the neighboring pose point to the open set. Return to step 2.

[0077] According to the basic process of the hybrid A* algorithm path planning strategy described above, when approaching the target pose point, the hybrid A* algorithm will try to find a path without considering obstacles in order to connect to the target pose as closely as possible and improve the search speed. Therefore, if there are many obstacles near the target pose point, especially U-shaped obstacles like those in parking scenarios, the difficulty of searching for nearby pose points near the target pose point increases greatly, and the efficiency is also greatly reduced.

[0078] Based on this, the present application shows a path planning method for complex obstacles near the target pose point based on a path planning strategy based on a hybrid A* algorithm, that is, a two-way parking path planning method. The target forward pose point and the target reverse pose point are obtained, and the forward intermediate pose point between the current pose point and the target reverse pose point is determined according to a preset first path search strategy, and the reverse intermediate pose point between the target pose point and the target forward pose point is determined according to a preset second path search strategy. Determine whether there is a collision-free path from the forward intermediate pose point to the reverse intermediate pose point. If so, generate a parking path based on the collision-free path from the current pose point to the forward intermediate pose point, the collision-free path from the forward intermediate pose point to the reverse intermediate pose point, and the collision-free path from the reverse intermediate pose point to the target pose point.

[0079] The bidirectional parking path planning method proposed in this application performs path search from the current position point and the target position point respectively, thereby improving the parking path planning efficiency in parking scenarios.

[0080] First, the parking path planning method illustrated in this application is described in detail. The parking path planning method provided in the embodiments of this application can be applied to, but not limited to, personal computers, laptops, smartphones, tablet computers, IoT devices, portable wearable devices, independent servers, or server clusters consisting of multiple servers.

[0081] In one embodiment, Figure 2 FIG. 1 is a flow chart of a method for bidirectional parking path planning according to an embodiment of the present application.

[0082] Step 201: Obtain target forward pose points and target reverse pose points.

[0083] The target forward pose point can be the current pose point or an intermediate forward pose point. The target reverse pose point can be the target pose point or an intermediate reverse pose point. The current pose point is the starting pose point of the parking path to be planned, and the target pose point is the final parking pose point of the parking path to be planned.

[0084] In one embodiment, the device initializes the target forward pose point as the current pose point and the target inverse pose point as the target pose point before performing the path search. When the device needs to obtain the target forward pose point during the path search, the device can obtain the current pose point as the target forward pose point or obtain the current forward intermediate pose point as the target forward pose point. Similarly, when the device needs to obtain the target inverse pose point during the path search, the device can obtain the target pose point as the target inverse pose point or obtain the current inverse intermediate pose point as the target inverse pose point.

[0085] In one embodiment, each pose point includes three information, i.e., the horizontal coordinate in the map, the vertical coordinate in the map, and the orientation of the vehicle. That is, the same position with the horizontal coordinate and the vertical coordinate can have multiple pose points. For example, a pose point can include three dimensions (x, y, θ), which respectively represent the position (x, y) in the plane xOy coordinate system and the vehicle orientation angle θ.

[0086] In step 203, the device determines the forward intermediate pose point between the current pose point and the target inverse pose point according to a preset first path search strategy and determines the inverse intermediate pose point between the target pose point and the target forward pose point according to a preset second path search strategy.

[0087] The first path search strategy and the second path search strategy can be the same path search strategy or different path search strategies. The device can use the path planning strategy based on the hybrid A* algorithm as the first path planning strategy or the second path planning strategy, or use the path planning strategy based on the A* algorithm as the first path planning strategy or the second path planning strategy, which is not limited in the present application.

[0088] In one embodiment, the device obtains the target pose point as the target inverse pose point and obtains the current pose point as the target forward pose point, and then searches the forward intermediate pose point between the current pose point and the target pose point according to the preset first path search strategy and searches the inverse intermediate pose point between the target pose point and the current pose point according to the preset second path search strategy.

[0089] Specifically, the device gradually searches for corresponding forward pose points to the target pose point according to the preset first path search strategy, and adds the searched forward pose points to the forward open set, and selects one forward pose point in the forward open set as the forward intermediate pose point according to the forward driving cost value between each forward pose point and the target pose point. The device gradually searches for corresponding reverse pose points to the current pose point according to the preset second path search strategy, and adds the searched reverse pose points to the reverse open set, and selects one reverse pose point in the reverse open set as the reverse intermediate pose point according to the reverse driving cost value between each reverse pose point and the current pose point.

[0090] In one embodiment, the device can also obtain the target pose point as the target reverse pose point, obtain the current forward intermediate pose point as the target forward pose point, then search for a forward intermediate pose point between the current pose point and the target pose point according to the preset first path search strategy, and search for a reverse intermediate pose point between the target pose point and the current forward intermediate pose point according to the preset second path search strategy.

[0091] Specifically, the device gradually searches for corresponding forward pose points to the target pose point according to the preset first path search strategy, and adds the searched forward pose points to the forward open set, and selects one forward pose point in the forward open set as the forward intermediate pose point according to the forward driving cost value between each forward pose point and the target pose point. The device gradually searches for corresponding reverse pose points to the current pose point according to the preset second path search strategy, and adds the searched reverse pose points to the reverse open set, and selects one reverse pose point in the reverse open set as the reverse intermediate pose point according to the reverse driving cost value between each reverse pose point and the current pose point.

[0092] In one embodiment, the device can also obtain the target pose point as the target reverse pose point, obtain the current forward intermediate pose point as the target forward pose point, then search for a forward intermediate pose point between the current pose point and the target pose point according to the preset first path search strategy, and search for a reverse intermediate pose point between the target pose point and the current forward intermediate pose point according to the preset second path search strategy.

[0093] Specifically, the device searches for a plurality of forward pose points to the current reverse intermediate pose point according to the preset first path search strategy, adds the searched forward pose points to the forward open set, and selects one forward pose point in the forward open set as the forward intermediate pose point according to the forward driving cost value between each forward pose point and the current reverse intermediate pose point. The device gradually searches for corresponding reverse pose points to the current pose point according to the preset second path search strategy, adds the searched reverse pose points to the reverse open set, and selects one reverse pose point in the reverse open set as the reverse intermediate pose point according to the reverse driving cost value between each reverse pose point and the current pose point.

[0094] In one embodiment, the device can also acquire the current reverse intermediate pose point as a target reverse pose point, acquire the current forward intermediate pose point as a target forward pose point, then search for a forward intermediate pose point between the current pose point and the current reverse intermediate pose point according to the preset first path search strategy, and search for a reverse intermediate pose point between the target pose point and the current forward intermediate pose point according to the preset second path search strategy.

[0095] Specifically, the device searches for a plurality of forward pose points to the current reverse intermediate pose point according to the preset first path search strategy, adds the searched forward pose points to the forward open set, and selects one forward pose point in the forward open set as the forward intermediate pose point according to the forward driving cost value between each forward pose point and the current reverse intermediate pose point. The device searches for a plurality of reverse pose points to the current forward intermediate pose point according to the preset second path search strategy, adds the searched reverse pose points to the reverse open set, and selects one reverse pose point in the reverse open set as the reverse intermediate pose point according to the reverse driving cost value between each reverse pose point and the current forward intermediate pose point.

[0096] Step 205, determining whether there is a collision-free path between the forward intermediate pose point and the reverse intermediate pose point.

[0097] In one embodiment, the device stores map data containing obstacle information, and obtains the current pose point and the target pose point of the parking path planning, and obtains the basic parameters of the actual driving vehicle, such as the length and width of the actual driving vehicle, and the kinematic parameters of the vehicle, such as the wheelbase, the distance between the rear axle and the front end, and the minimum turning radius. Therefore, when determining whether there is a collision-free path between the forward intermediate pose point and the reverse intermediate pose point, the device can generate a driving path according to the preset path generation strategy and the kinematic parameters of the vehicle (such as the minimum turning radius), and then determine whether the vehicle will collide along the generated path according to the basic parameters of the vehicle, such as the length and width of the vehicle. If there is a collision, the device determines that there is no collision-free path between the forward intermediate pose point and the reverse intermediate pose point; if there is no collision, the device determines that there is a collision-free path between the forward intermediate pose point and the reverse intermediate pose point.

[0098] The preset path generation strategy can be an RS curve path generation strategy or a Dubins curve path generation strategy. The RS curve and the Dubins curve are similar, both of which are circular + straight line paths, and the difference lies in that the RS curve allows the vehicle to reverse, and the Dubins curve only allows the vehicle to move forward.

[0099] Step 207, if there is, generating the parking path according to the collision-free path from the current pose point to the forward intermediate pose point, the collision-free path from the forward intermediate pose point to the reverse intermediate pose point, and the collision-free path from the reverse intermediate pose point to the target pose point.

[0100] In one embodiment, after the device determines that there is a collision-free path between the forward intermediate pose point and the reverse intermediate pose point, the device generates a parking path according to the collision-free path from the current pose point to the forward intermediate pose point, the collision-free path from the forward intermediate pose point to the reverse intermediate pose point, and the collision-free path from the reverse intermediate pose point to the target pose point. The parking path planned by the device from the current pose point to the target pose point includes three parts. The first part is the path from the current pose point to the forward intermediate pose point planned according to the preset first path search strategy. The second part is the path from the target pose point to the reverse intermediate pose point planned according to the preset second path search strategy. The third part is the collision-free path from the forward intermediate pose point to the reverse intermediate pose point generated according to the preset path generation strategy. The device combines the paths of the three parts to generate the parking path planned from the current pose point to the target pose point. For example, the current pose point is A, the forward intermediate pose point is D, the reverse intermediate pose point is X, and the target pose point is Z. The device plans the path from the current pose point A to the forward intermediate pose point D as A-B-C-D according to the preset first path search strategy, and determines that there is a collision-free path D-X between the forward intermediate pose point D and the reverse intermediate pose point X. The device plans the path from the target pose point Z to the reverse intermediate pose point X as Z-Y-X according to the preset second path search strategy. Therefore, the path generated by the device is A-B-C-D-X-Y-Z.

[0101] The bidirectional planning method of the parking path provided in the present application increases the efficiency of path search in the scenario of parking, thereby improving the efficiency of generating the parking path.

[0102] In one embodiment, the bidirectional planning method of the parking path described above can further include:

[0103] In step 209, if there is no collision-free path between the forward intermediate pose point and the reverse intermediate pose point, the device returns to step 201.

[0104] In one embodiment, if the device determines that there is no collision-free path between the forward intermediate pose point and the reverse intermediate pose point, it means that the forward intermediate pose point needs to be determined again according to the first search path strategy, and the reverse intermediate pose point needs to be determined according to the second path search strategy. The device returns to step 201 to reacquire the target forward pose point and the target reverse pose point, and then determines the forward intermediate pose point again according to the reacquired target forward pose point and the preset first path search strategy, and determines the reverse intermediate pose point again according to the reacquired target reverse pose point and the preset second path search strategy.

[0105] In one embodiment, if the target forward pose point is the current pose point and the target inverse pose point is the target pose point, the device determines that there is no collision-free path from the forward intermediate pose point to the inverse intermediate pose point, and directly returns to perform step 203 to re-determine the intermediate pose point according to the first path search strategy and re-determine the inverse intermediate pose point according to the second path search strategy.

[0106] In addition, if the target forward pose point is the current pose point and the target inverse pose point is the target pose point, the device determines that there is no collision-free path from the forward intermediate pose point to the inverse intermediate pose point, and can only perform the step of re-determining the intermediate pose point according to the first path search strategy or only perform the step of re-determining the inverse intermediate pose point according to the second path search strategy, and then perform steps 205 and 207.

[0107] In this embodiment, the forward search and the inverse search are performed simultaneously, which speeds up the process of obtaining the collision-free path from the inverse intermediate pose point to the forward intermediate pose point, thereby improving the efficiency of path planning.

[0108] In one embodiment, the above-mentioned determination of the forward intermediate pose point between the current pose point and the target inverse pose point according to the preset first path search strategy comprises:

[0109] Step A1, obtaining each forward pose point in the forward open set.

[0110] The forward open set comprises the forward pose points searched according to the first path search strategy.

[0111] In one embodiment, after the device determines that there is no collision-free path from the forward intermediate pose point to the inverse intermediate pose point, the device searches for a plurality of forward pose points to the target inverse pose point according to the preset first path search strategy and adds them to the forward open set.

[0112] Specifically, the device determines and selects a forward adjacent pose point of the forward intermediate pose point according to the kinematic formula, and determines whether there is a collision-free path from the forward adjacent pose point to the forward intermediate pose point. If the device determines that there is a collision-free path from the forward adjacent pose point to the forward intermediate pose point, it continues to determine whether the forward adjacent pose point is in the forward closed set. If the device determines that the forward adjacent pose point is in the forward closed set, it re-determines and selects a forward adjacent pose point of the forward intermediate pose point according to the kinematic formula; if the device determines that the forward adjacent pose point is not in the forward closed set, it continues to determine whether the forward adjacent pose point is in the forward open set, and if not, it adds the forward adjacent pose point to the forward open set. If the device determines that there is no collision-free path from the forward adjacent pose point to the forward intermediate pose point, it re-determines and selects a forward adjacent pose point of the forward intermediate pose point according to the kinematic formula.

[0113] In one embodiment, if the device acquires no forward pose point in the forward open set, it means that all the pose points in the current map have been searched and no collision-free parking path has been found, and the search path fails.

[0114] Step A2, for each forward pose point, determine the forward driving cost value corresponding to the forward pose point.

[0115] In one embodiment, for each forward pose point in the forward open set, the device can acquire the actual driving cost value of the current pose point driving to the forward pose point and the predicted driving cost value of the forward pose point driving to the target pose point and / or the reverse intermediate pose point, and then determine the forward driving cost value of the forward pose point according to the actual driving cost value and the predicted driving cost value.

[0116] Step A3, determine the forward pose point with the minimum forward driving cost value in the forward open set as the forward intermediate pose point.

[0117] In one embodiment, after the device determines the forward driving cost value of each forward pose point in the forward open set, it selects the forward pose point with the minimum forward driving cost value in the forward open set as the forward intermediate pose point, and deletes the selected forward pose point from the forward open set and adds it to the forward closed set.

[0118] In this embodiment, each time the forward pose point with the minimum driving cost value is selected as the forward intermediate pose point, so that the path finally planned is the optimal path as much as possible.

[0119] In one embodiment, step A2 specifically comprises:

[0120] Step A201, acquire the first forward driving cost value between the forward pose point and the target pose point, and the second forward driving cost value between the forward pose point and the reverse intermediate pose point.

[0121] In one embodiment, the device can acquire the Voronoi potential integral value on the collision-free path from the forward pose point to the target pose point as the first forward driving cost value of the forward pose point, or calculate the difference of the orientation angle between the forward pose point and the target pose point as the first forward driving cost value of the forward pose point. Similarly, the device can acquire the Voronoi potential integral value on the collision-free path from the forward pose point to the reverse intermediate pose point as the second forward driving cost value of the forward pose point, or calculate the difference of the orientation angle between the forward pose point and the reverse intermediate pose point as the second forward driving cost value of the forward pose point.

[0122] Step A203, determining the forward driving cost value corresponding to the forward pose point according to the first forward driving cost value and the second forward driving cost value.

[0123] In one embodiment, the weight parameters can be set in advance for the first forward driving cost value and the second forward driving cost value, and the device calculates the forward driving cost value corresponding to the forward pose point according to the first forward driving cost value and the second forward driving cost value, and the weight parameters corresponding to the first forward driving cost value and the second forward driving cost value respectively.

[0124] Wherein, the higher the weight corresponding to the second forward driving cost value is, the faster the connection of the forward search and the reverse search can be accelerated, that is, the faster the no-collision pose point between the forward intermediate pose point and the reverse intermediate pose point can be obtained.

[0125] In one embodiment, the device can also obtain a third forward driving cost value from the current pose point to the forward pose point, then determine the expected driving cost value of the forward pose point according to the first forward driving cost value and the second forward driving cost value, determine the actual driving cost value of the forward pose point according to the third forward driving cost value, and then obtain the forward driving cost value of the forward pose point according to the actual driving cost value and the expected driving cost value.

[0126] In this embodiment, when determining the forward driving cost value of the forward pose point, the driving cost value from the forward pose point to the target pose point and the driving cost value from the forward pose point to the reverse intermediate pose point are considered, which on the one hand makes the search path gradually close to the target pose point, and on the other hand makes the search path gradually close to the reverse search path.

[0127] In one embodiment, the above-mentioned determination of the reverse intermediate pose point between the target pose point and the target forward pose point according to the preset second path search strategy comprises:

[0128] Step B1, obtaining each reverse pose point in the reverse open set.

[0129] Wherein, the reverse open set comprises the reverse pose points searched according to the second path search strategy.

[0130] In one embodiment, after the device determines that there is no no-collision path from the forward intermediate pose point to the reverse intermediate pose point, it will search a plurality of reverse pose points to the target forward pose point according to the preset second path search strategy and add them to the reverse open set.

[0131] Specifically, the device determines and selects one inverse neighboring pose point of the inverse intermediate pose point according to the kinematic formula, and judges whether there is a collision-free path from the inverse neighboring pose point to the inverse intermediate pose point. If the device determines that there is a collision-free path from the inverse neighboring pose point to the inverse intermediate pose point, it continues to judge whether the inverse neighboring pose point is in the inverse closed set. If the device determines that the inverse neighboring pose point is in the inverse closed set, it re-determines and selects one inverse neighboring pose point of the inverse intermediate pose point according to the kinematic formula; if the device determines that the inverse neighboring pose point is not in the inverse closed set, it continues to judge whether the inverse neighboring pose point is in the inverse open set, and if not, it adds the inverse neighboring pose point to the inverse open set. If the device determines that there is no collision-free path from the inverse neighboring pose point to the inverse intermediate pose point, it re-determines and selects one inverse neighboring pose point of the inverse intermediate pose point according to the kinematic formula.

[0132] In one embodiment, if the device acquires that the inverse open set is empty, i.e., no inverse pose point in the inverse open set is acquired, it indicates that the inverse search of each pose point in the current map has been completed, and no collision-free parking path is searched, and the search path fails.

[0133] Step B2, for each inverse pose point, determine the inverse driving cost value corresponding to the inverse pose point.

[0134] In one embodiment, for each forward pose point in the forward open set, the device can acquire the actual driving cost value of the target pose point driving to the inverse pose point, and the predicted driving cost value of the inverse pose point driving to the current pose point and / or the forward intermediate pose point, and then determine the inverse driving cost value of the inverse pose point according to the actual driving cost value and the predicted driving cost value.

[0135] Step B3, determine the inverse pose point with the minimum inverse driving cost value in the inverse open set as the inverse intermediate pose point.

[0136] In one embodiment, after the device determines the inverse driving cost value of each inverse pose point in the inverse open set, it selects the inverse pose point with the minimum inverse driving cost value in the inverse open set as the inverse intermediate pose point, and deletes the selected inverse pose point from the inverse open set and adds it to the inverse closed set.

[0137] In this embodiment, each time the inverse pose point with the minimum driving cost value is selected as the inverse intermediate pose point, so that the path finally planned is the optimal path as much as possible.

[0138] In one embodiment, the above step B2 specifically comprises:

[0139] Step B201, obtaining a first reverse driving cost value between the reverse pose point and the target pose point, and a second reverse driving cost value between the reverse pose point and the forward intermediate pose point.

[0140] In one embodiment, the device can obtain a Voronoi potential integral value on a collision-free path from the reverse pose point to the current pose point as the first reverse driving cost value of the reverse pose point, or calculate a difference value of the orientation angle between the reverse pose point and the current pose point as the first reverse driving cost value of the reverse pose point. Similarly, the device can obtain a Voronoi potential integral value on a collision-free path from the reverse pose point to the forward intermediate pose point as the second reverse driving cost value of the reverse pose point, or calculate a difference value of the orientation angle between the reverse pose point and the forward intermediate pose point as the second reverse driving cost value of the reverse pose point.

[0141] In one embodiment, the device can obtain the second reverse driving cost value between the reverse pose point and the forward intermediate pose point by the following method:

[0142] 1. Obtain the coordinates of the reverse pose point and the forward intermediate pose point in the map respectively, and calculate the straight-line distance between the reverse pose point and the forward intermediate pose point according to the coordinates of the reverse pose point and the forward intermediate pose point, and take the straight-line distance between the reverse pose point and the forward intermediate pose point as the second reverse driving cost value between the reverse pose point and the forward intermediate pose point.

[0143] For example, the coordinates of the reverse pose point in the map are (x1, y1), and the coordinates of the forward intermediate pose point in the map are (x2, y2), then the second reverse driving cost value between the reverse pose point and the forward intermediate pose point is

[0144] 2. Obtain the orientation angles of the reverse pose point and the forward intermediate pose point in the map respectively, and take the difference value of the orientation angles between the reverse pose point and the forward intermediate pose point as the second reverse driving cost value between the reverse pose point and the forward intermediate pose point.

[0145] For example, the orientation angle of the reverse pose point is θ1, and the orientation angle of the forward intermediate pose point in the map is θ2, then the second reverse driving cost value between the reverse pose point and the forward intermediate pose point is f1 = (|θ1-θ2|-π) 2 . Wherein θ1, θ2 ∈ (-π, π], therefore, the orientation angle included angle needs to be measured by |θ1-θ2|-π, such as θ1=π, θ2=0, one is facing positive left and one is facing positive right, the orientation angle is actually parallel, the included angle is 0, but the value of the two cannot be directly subtracted.

[0146] 3. obtain the heading angle of the reverse pose point and the direction angle from the forward intermediate pose point to the reverse pose point, and take the difference between the heading angle of the reverse pose point and the direction angle from the forward intermediate pose point to the reverse pose point as the second reverse driving cost value between the reverse pose point and the forward intermediate pose point.

[0147] For example, the heading angle of the reverse pose point is θ1, and the direction angle from the forward intermediate pose point to the reverse pose point is heading (Node1, Node2), then the second reverse driving cost value f1 between the reverse pose point and the forward intermediate pose point is f1 = (|θ1 - (heading (Node1, Node2))| - π) 2 . Wherein, heading (Node1, Node2) is the heading angle from the forward intermediate pose point Node1 to the reverse pose point Node2, as shown in Figure 3

[0148] Step B203, determine the reverse driving cost value corresponding to the reverse pose point according to the first reverse driving cost value and the second reverse driving cost value.

[0149] In an embodiment, the weight parameters of the first reverse driving cost value and the second reverse driving cost value can be set in advance, and the device calculates the reverse driving cost value corresponding to the reverse pose point according to the first reverse driving cost value and the second reverse driving cost value, and the weight parameters corresponding to the first reverse driving cost value and the second reverse driving cost value respectively.

[0150] Wherein, the higher the weight corresponding to the second reverse driving cost value is, the faster the connection of the forward search and the reverse search can be accelerated, that is, the no-collision pose point between the forward intermediate pose point and the reverse intermediate pose point can be obtained faster.

[0151] In an embodiment, the device can also obtain a third reverse driving cost value between the target pose point and the reverse pose point, then determine the expected driving cost value of the reverse pose point according to the first reverse driving cost value and the second reverse driving cost value, determine the actual driving cost value of the reverse pose point according to the third reverse driving cost value, and further obtain the reverse driving cost value of the reverse pose point according to the actual driving cost value and the expected driving cost value.

[0152] In this embodiment, when determining the reverse driving cost value of the reverse pose point, the driving cost value from the reverse pose point to the current pose point and the driving cost value from the reverse pose point to the forward intermediate pose point are considered at the same time, on the one hand, the search path gradually approaches the current pose point, and on the other hand, the search path gradually approaches the path of the forward search.

[0153] ​Next, a specific embodiment of the bidirectional planning method of the parking path provided by the present application is described in detail, as shown in Figure 4 FIG. 1 is a flowchart of the bidirectional planning method of the parking path according to a specific embodiment of the present application.

[0154] 1. First, the current pose point and the target pose point of the vehicle driving to which the path planning is performed are determined, and the forward open set is initialized as the current pose point, the forward closed set is empty, the reverse open set is the target pose point, and the reverse closed set is empty.

[0155] 2. It is determined whether the forward open set and the reverse open set are empty. If the forward open set or the reverse open set is empty, it is indicated that each pose point of the current map has been searched and no collision-free parking path is searched, and the path planning fails. If neither the forward open set nor the reverse open set is empty, step 3 is continued.

[0156] 3. The forward pose point with the minimum total heuristic value F1 in the forward open set is selected as the forward intermediate pose point, and the reverse pose point with the minimum total heuristic value F2 in the reverse open set is selected as the reverse intermediate pose point.

[0157] 4. It is determined whether there is a collision-free path between the forward intermediate pose point and the reverse intermediate pose point. If yes, the path planning is successful, and the final parking path is generated according to the collision-free path from the current pose point to the forward intermediate pose point, the collision-free path from the forward intermediate pose point to the reverse intermediate pose point, and the collision-free path from the reverse intermediate pose point to the target pose point. If no, step 5 or step 13 is continued.

[0158] 5. A forward adjacent pose point of the forward intermediate pose point is determined and selected according to the kinematic formula.

[0159] 6. It is determined whether there is a collision-free path from the forward intermediate pose point to the forward adjacent pose point. If no, step 5 is returned to and a forward adjacent pose point is reselected. If yes, step 7 is continued.

[0160] 7. It is determined whether the forward adjacent pose point is in the forward closed set. If the forward adjacent pose point is in the forward closed set, it is indicated that the forward adjacent pose point has been traversed and it is unnecessary to recompute the forward adjacent pose point, and step 5 is returned to and a forward adjacent pose point is reselected. If the forward adjacent pose point is not in the forward closed set, step 8 is continued.

[0161] 8. The motion cost g1 from the current pose point to the forward adjacent pose point is calculated according to the motion cost from the current pose point to the forward intermediate pose point and the motion cost from the forward intermediate pose point to the forward adjacent pose point.

[0162] 9. Determine whether the forward adjacent pose point is in the forward open set. If yes, go to step 10; if no, go to step 12.

[0163] 10. Determine whether the motion cost gl of the forward adjacent pose point is less than the motion cost gl of the forward adjacent pose point stored in the forward open set. If the motion cost gl of the forward adjacent pose point is not less than the motion cost gl of the forward adjacent pose point stored in the open set, go directly to step 2. If the motion cost gl of the forward adjacent pose point is less than the motion cost gl of the forward adjacent pose point stored in the open set, go to step 11.

[0164] 11. Update the motion cost gl of the forward adjacent pose point, the parent node of the forward adjacent pose point, and the total cost Fl of the forward adjacent pose point in the open set, and go to step 2.

[0165] 12. Calculate the heuristic cost hi of the forward adjacent pose point, and calculate the total cost Fl of the forward adjacent pose point according to the motion cost gl and the heuristic cost hi of the forward adjacent pose point, record its parent node as the forward intermediate pose point, and add the forward adjacent pose point to the forward open set. Go to step 2.

[0166] 13. Determine and select a reverse adjacent pose point of the reverse intermediate pose point according to the kinematic formula.

[0167] 14. Determine whether there is a collision-free path from the reverse intermediate pose point to the reverse adjacent pose point. If there is no collision-free path, go to step 13 to reselect a reverse adjacent pose point. If there is a collision-free path, go to step 15.

[0168] 15. Determine whether the reverse adjacent pose point is in the reverse closed set. If the reverse adjacent pose point is in the reverse closed set, it means that the reverse adjacent pose point has been traversed and does not need to be calculated again, go to step 13 to reselect a reverse adjacent pose point. If the reverse adjacent pose point is not in the closed set, go to step 16.

[0169] 16. Calculate the motion cost g2 of the target pose point to the reverse adjacent pose point according to the motion cost of the target pose point to the reverse intermediate pose point and the motion cost of the reverse intermediate pose point to the reverse adjacent pose point.

[0170] 17. Determine whether the reverse adjacent pose point is in the reverse open set. If yes, go to step 18; if no, go to step 20.

[0171] 18. Determine the difference between the motion cost g2 of the reverse adjacent pose point and the motion cost g2 of the reverse adjacent pose point stored in the reverse open set. If the motion cost g2 of the reverse adjacent pose point is not less than the motion cost g2 of the reverse adjacent pose point stored in the open set, return directly to step 2. If the motion cost g2 of the reverse adjacent pose point is less than the motion cost g2 of the reverse adjacent pose point stored in the reverse open set, execute step 19.

[0172] 19. Update the motion cost g2 of the reverse adjacent pose point in the reverse open set, the parent node of the reverse adjacent pose point, and the total cost F2 of the reverse adjacent pose point, and return to step 2.

[0173] 20. Calculate the heuristic cost h2 of the reverse neighboring pose point. Calculate the total cost F2 of the reverse neighboring pose point based on the motion cost g2, the heuristic cost h2, and the second travel cost f1. Denote its parent node as the reverse intermediate pose point and add the reverse neighboring pose point to the reverse open set. Return to step 2.

[0174] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0175] Based on the same inventive concept, embodiments of the present application also provide a bidirectional parking path planning device for implementing the aforementioned bidirectional parking path planning method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more bidirectional parking path planning device embodiments provided below can be found in the above-described limitations of the bidirectional parking path planning method and are not further elaborated here.

[0176] In one embodiment, Figure 5 As shown, a parking path two-way planning device is provided, comprising:

[0177] An acquisition module 501 is used to acquire a target forward pose point and a target reverse pose point;

[0178] The first determining module 503 is configured to determine a forward intermediate pose point between the current pose point and the target reverse pose point according to a preset first path searching strategy, and determine a reverse intermediate pose point between the target pose point and the target forward pose point according to a preset second path searching strategy.

[0179] The second determining module 505 is configured to determine whether there is a collision-free path between the forward intermediate pose point and the reverse intermediate pose point.

[0180] The path generating module 507 is configured to generate a parking path according to the collision-free path from the current pose point to the forward intermediate pose point, the collision-free path from the forward intermediate pose point to the reverse intermediate pose point, and the collision-free path from the reverse intermediate pose point to the target pose point if the collision-free paths exist.

[0181] In an embodiment, the apparatus further includes:

[0182] The loop module 509 (not shown in the figure) is configured to perform the steps of obtaining the target forward pose point and the target reverse pose point if there is no collision-free path between the forward intermediate pose point and the reverse intermediate pose point.

[0183] In an embodiment, the first determining module 503 is specifically configured to:

[0184] obtain each forward pose point in a forward open set; the forward open set includes the forward pose points searched according to the first path searching strategy; for each forward pose point, determine a forward driving cost value corresponding to the forward pose point; determine the forward intermediate pose point as the forward pose point with the minimum forward driving cost value in the forward open set; and determine the reverse intermediate pose point between the target pose point and the target forward pose point according to the preset second path searching strategy.

[0185] In an embodiment, the first determining module 503 is specifically configured to:

[0186] obtain each forward pose point in a forward open set; the forward open set includes the forward pose points searched according to the first path searching strategy; for each forward pose point, obtain a first forward driving cost value between the forward pose point and the target pose point, and a second forward driving cost value between the forward pose point and the reverse intermediate pose point; determine a forward driving cost value corresponding to the forward pose point according to the first forward driving cost value and the second forward driving cost value; determine the forward intermediate pose point as the forward pose point with the minimum forward driving cost value in the forward open set; and determine the reverse intermediate pose point between the target pose point and the target forward pose point according to the preset second path searching strategy.

[0187] In one embodiment, the first determining module 503 is specifically configured to:

[0188] According to the preset first path search strategy, a forward intermediate pose point between the current pose point and the target reverse pose point is determined; each reverse pose point in a reverse open set is obtained; the reverse open set includes the reverse pose points searched according to the second path search strategy; for each reverse pose point, a reverse driving cost value corresponding to the reverse pose point is determined; and a reverse pose point with the minimum reverse driving cost value in the reverse open set is determined as a reverse intermediate pose point.

[0189] In one embodiment, the first determining module 503 is specifically configured to:

[0190] According to the preset first path search strategy, a forward intermediate pose point between the current pose point and the target reverse pose point is determined; each reverse pose point in a reverse open set is obtained; the reverse open set includes the reverse pose points searched according to the second path search strategy; for each reverse pose point, a reverse driving cost value corresponding to the reverse pose point is determined; and a reverse pose point with the minimum reverse driving cost value in the reverse open set is determined as a reverse intermediate pose point.

[0191] The modules in the above-described parking path bidirectional planning device can be all or partially implemented by software, hardware, or a combination thereof. The modules can be embedded in or independent of a processor in a computer device in hardware form, or stored in a memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to the modules.

[0192] In one embodiment, a computer device is provided, which can be a terminal, and an internal structure diagram thereof can be as shown in Figure 6 The computer device includes a processor, a memory, and a communication interface connected through a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The communication interface of the computer device is configured to perform wired or wireless communication with an external terminal. The wireless communication can be achieved through WIFI, mobile cellular network, NFC (near field communication), or other technologies. The computer program is executed by the processor to implement a kind of parking path bidirectional planning method.

[0193] Those skilled in the art can understand that Figure 6 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0194] In one embodiment, a computer device is also provided, including a memory and a processor, the memory storing a computer program, and the processor implementing the steps in the above method embodiments when executing the computer program.

[0195] In one embodiment, a computer readable storage medium is provided, storing a computer program, and the computer program implements the steps in the above method embodiments when executed by a processor.

[0196] In one embodiment, a computer program product is provided, including a computer program, and the computer program implements the steps in the above method embodiments when executed by a processor.

[0197] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties.

[0198] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0199] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0200] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A bidirectional parking path planning method, characterized in that, The method comprises: obtaining a target forward pose point and a target reverse pose point; the pose point comprises three dimensions (x, y, θ), representing the position (x, y) in the plane xOy coordinate system and the vehicle orientation angle θ respectively; determining a forward intermediate pose point between the current pose point and the target reverse pose point according to a preset first path search strategy, and determining a reverse intermediate pose point between the target pose point and the target forward pose point according to a preset second path search strategy; the target pose point is the final parking pose point of the parking path to be planned; determining whether there is a collision-free path between the forward intermediate pose point and the reverse intermediate pose point; if there is, generating a parking path according to the collision-free path from the current pose point to the forward intermediate pose point, the collision-free path from the forward intermediate pose point to the reverse intermediate pose point, and the collision-free path from the reverse intermediate pose point to the target pose point; wherein, determining a forward intermediate pose point between the current pose point and the target reverse pose point according to a preset first path search strategy comprises: obtaining each forward pose point in a forward open set; the forward open set comprises the forward pose points searched according to the first path search strategy; the difference between the orientation angle of the forward pose point and the target pose point is taken as the first forward driving cost value of the forward pose point, and the difference between the orientation angle of the forward pose point and the reverse intermediate pose point is taken as the second forward driving cost value of the forward pose point; calculating the forward driving cost value corresponding to the forward pose point according to the first forward driving cost value and the second forward driving cost value, and the respective weight parameters of the first forward driving cost value and the second forward driving cost value; the higher the weight corresponding to the second forward driving cost value is, the faster the connection between the forward search and the reverse search is; determining the forward pose point with the minimum forward driving cost value in the forward open set as the forward intermediate pose point.

2. The method of claim 1, wherein, The method further comprises: if there is no collision-free path between the forward intermediate pose point and the reverse intermediate pose point, performing the step of obtaining a target forward pose point and a target reverse pose point.

3. The method of claim 1, wherein, determining a reverse intermediate pose point between the target pose point and the target forward pose point according to a preset second path search strategy comprises: obtaining each reverse pose point in a reverse open set; the reverse open set comprises the reverse pose points searched according to the second path search strategy; for each reverse pose point, determining the reverse driving cost value corresponding to the reverse pose point; determining the reverse pose point with the minimum reverse driving cost value in the reverse open set as the reverse intermediate pose point.

4. The method of claim 3, wherein, determining the reverse driving cost value corresponding to the reverse pose point comprises: obtaining a first reverse driving cost value between the reverse pose point and the target pose point, and a second reverse driving cost value between the reverse pose point and the forward intermediate pose point; determining the reverse driving cost value corresponding to the reverse pose point according to the first reverse driving cost value and the second reverse driving cost value.

5. A parking path two-way planning device, characterized in that: The device comprises: The acquisition module is configured to acquire a target forward pose point and a target reverse pose point; The first determination module is configured to determine a forward intermediate pose point between the current pose point and the target reverse pose point according to a preset first path search strategy, and determine a reverse intermediate pose point between the target pose point and the target forward pose point according to a preset second path search strategy; the target pose point is a final parking pose point of a parking path to be planned; The second determination module is configured to determine whether there is a collision-free path between the forward intermediate pose point and the reverse intermediate pose point; The path generation module is configured to, if there is, generate a parking path according to a collision-free path from the current pose point to the forward intermediate pose point, a collision-free path from the forward intermediate pose point to the reverse intermediate pose point, and a collision-free path from the reverse intermediate pose point to the target pose point. The first determination module is configured to, when determining the forward intermediate pose point between the current pose point and the target reverse pose point according to the preset first path search strategy, specifically: acquire each forward pose point in a forward open set; the forward open set includes forward pose points searched according to the first path search strategy; a difference between the forward pose point and an orientation angle of the target pose point is taken as a first forward driving cost value of the forward pose point, and a difference between the forward pose point and an orientation angle of the reverse intermediate pose point is taken as a second forward driving cost value of the forward pose point; calculate a forward driving cost value corresponding to the forward pose point according to the first forward driving cost value and the second forward driving cost value, and weights of the first forward driving cost value and the second forward driving cost value respectively; the higher the weight corresponding to the second forward driving cost value is, the higher the acceleration of the connection between forward search and reverse search is; determine the forward pose point with the smallest forward driving cost value in the forward open set as the forward intermediate pose point.

6. The apparatus of claim 5, wherein, The device further includes: The loop module is configured to, if there is no collision-free path between the forward intermediate pose point and the reverse intermediate pose point, execute the acquisition module.

7. The apparatus of claim 5, wherein, The first determination module is configured to: acquire each reverse pose point in a reverse open set; the reverse open set includes reverse pose points searched according to the second path search strategy; determine, for each reverse pose point, a reverse driving cost value corresponding to the reverse pose point; determine the reverse pose point with the smallest reverse driving cost value in the reverse open set as the reverse intermediate pose point.

8. The apparatus of claim 7, wherein, The first determination module is configured to: acquire a first reverse driving cost value between the reverse pose point and the target pose point, and a second reverse driving cost value between the reverse pose point and the forward intermediate pose point; determine the reverse driving cost value corresponding to the reverse pose point according to the first reverse driving cost value and the second reverse driving cost value. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-8 when the computer program is executed by the processor. The processor, when executing the computer program, implements the steps of the method in any one of claims 1 to 4.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program, when executed by the processor, implements the steps of the method in any one of claims 1 to 4.

Images