Path planning method, device, electronic device and storage medium

Abstract

The present invention relates to the field of path planning, and specifically to a path planning method, device, electronic device and storage medium. It includes: obtaining the attribute information of the target obstacle corresponding to the target vehicle; determining the target collision buffer corresponding to the target obstacle according to the correspondence between the attribute information and the collision buffer corresponding to the obstacle; adding a target collision buffer to the target obstacle to generate a buffered target obstacle; constructing a boundary collision constraint according to the buffered target obstacle, and running a preset path planning algorithm to solve the driving path; when the driving path is solved successfully, outputting the target path corresponding to the driving path. The above method ensures the accuracy of the target collision buffer corresponding to the determined target obstacle, and thus can ensure the accuracy of the planned target path.

Description

Technical Field

[0001] The present invention relates to the field of path planning, and in particular to a path planning method, device, electronic equipment and storage medium. Background Art

[0002] In unmanned driving systems, trajectory planning often adopts a path-speed decoupling planning strategy. Among them, path planning combines the smart bicycle's own information and the surrounding environment to provide itself with a spatially continuous local driving path as the spatial basis of the final output product - a spatiotemporal continuous driving trajectory.

[0003] In the process of path planning, it is necessary to consider avoiding obstacles in the environment to ensure the safety of the output path. In order to improve safety redundancy and consider the errors in the perceived position and size of obstacles, it is necessary to add a certain collision buffer for obstacles to ensure that the output path must avoid obstacles in the environment, that is, to ensure safety.

[0004] However, the existing technical solution expands the obstacle by a fixed value, and the fixed value is calculated by the outer contour of the vehicle. Therefore, the value is fixed for the vehicle and has no adaptive function, which leads to inaccurate collision buffer zone corresponding to the calculated obstacle, and further leads to inaccurate path planning. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides a path planning method, which aims to solve the problem in the prior art that the calculated collision buffer corresponding to the obstacle is inaccurate, which in turn leads to inaccurate path planning.

[0006] According to a first aspect, an embodiment of the present invention provides a path planning method, including:

[0007] Acquire attribute information of a target obstacle corresponding to the target vehicle; the attribute information includes at least one of a target longitudinal distance, a target relative speed, a target lateral distance of the target obstacle relative to the target vehicle, a target perception tracking time for tracking the target obstacle, a target height of the target obstacle, and a target perception confidence of the target obstacle;

[0008] Determine a target collision buffer zone corresponding to the target obstacle according to a correspondence between the attribute information and the collision buffer zone corresponding to the obstacle;

[0009] Add a target collision buffer zone to the target obstacle to generate a buffer target obstacle;

[0010] Construct boundary collision constraints based on buffer target obstacles, and run the preset path planning algorithm to solve the driving path;

[0011] When the driving path is solved successfully, the target path corresponding to the driving path is output.

[0012] The path planning method provided by the embodiment of the present invention obtains the attribute information of the target obstacle corresponding to the target vehicle, and then determines the target collision buffer corresponding to the target obstacle according to the corresponding relationship between the attribute information and the collision buffer corresponding to the obstacle, thereby ensuring the accuracy of the target collision buffer corresponding to the determined target obstacle. Then, a target collision buffer is added to the target obstacle to generate a buffer target obstacle, thereby ensuring the accuracy of the generated buffer target obstacle. A boundary collision constraint is constructed according to the buffer target obstacle, and a preset path planning algorithm is run to solve the driving path, thereby ensuring the accuracy of the solution result. When the driving path is solved successfully, the target path corresponding to the driving path is output, thereby ensuring the accuracy of the output target path. The above method does not add a fixed collision buffer to the target obstacle, but determines the target collision buffer corresponding to the target obstacle according to the corresponding relationship between the attribute information and the collision buffer corresponding to the obstacle, thereby realizing the adaptive calculation of the target collision buffer corresponding to the target obstacle, taking into account the attribute information corresponding to the target obstacle, thereby ensuring the accuracy of the target collision buffer corresponding to the determined target obstacle. In addition, the accuracy of the planned target path can be guaranteed.

[0013] In combination with the first aspect, in a first implementation of the first aspect, the method further includes:

[0014] When the driving path solution fails, the target collision buffer corresponding to the target obstacle is reduced by a preset reduction factor to generate a reduced collision buffer;

[0015] Add a reduced collision buffer for the target obstacle and generate a buffer to reduce the target obstacle;

[0016] According to the buffering and shrinking of the target obstacle, the boundary collision constraint is constructed, and the preset path planning algorithm is run to solve the driving path again;

[0017] After a preset number of times, if the solution fails, the parking path is output.

[0018] The path planning method provided by the embodiment of the present invention, when the solution of the driving path fails, reduces the target collision buffer corresponding to the target obstacle according to a preset reduction multiple to generate a reduced collision buffer, thereby ensuring the accuracy of the generated reduced collision buffer. A reduced collision buffer is added to the target obstacle to generate a buffered reduced target obstacle; a boundary collision constraint is constructed based on the buffered reduced target obstacle, and the preset path planning algorithm is run to solve the driving path again, thereby avoiding the failure of path planning due to the target buffer being too large. After a preset number of times, if the solution fails, the parking path is output, thereby ensuring the accuracy of path planning. The above method avoids the failure of path planning due to the target buffer being too large, and also avoids the failure of path planning due to the reduced collision buffer being too small, thereby ensuring the accuracy of the planned path when the buffer corresponding to the target obstacle is appropriate.

[0019] In combination with the first aspect, in a second implementation manner of the first aspect, the attribute information includes a target longitudinal distance of the target obstacle relative to the target vehicle, a target relative speed, and a target height of the target obstacle, and determining a target collision buffer zone corresponding to the target obstacle according to a correspondence between the attribute information and a collision buffer zone corresponding to the obstacle includes:

[0020] Obtain a three-dimensional interpolation table corresponding to the longitudinal distance, relative speed, obstacle height and collision buffer zone;

[0021] According to the values ​​of the target longitudinal distance, the target relative speed and the target height, a first longitudinal distance and a second longitudinal distance adjacent to the target longitudinal distance, a first relative speed and a second relative speed adjacent to the target relative speed, and a first obstacle height and a second obstacle height adjacent to the target height are determined in sequence in the three-dimensional interpolation table;

[0022] Calculating a first longitudinal distance, a first relative speed, and a first collision buffer zone corresponding to the target height according to a correlation between the target height and the first obstacle height and the second obstacle height;

[0023] Calculating the second longitudinal distance, the first relative speed, and the second collision buffer zone corresponding to the target height according to the correlation between the target height and the first obstacle height and the second obstacle height;

[0024] Calculating a third collision buffer area corresponding to the target longitudinal distance, the first relative speed, and the target height according to the correlation between the first collision buffer area and the second collision buffer area;

[0025] Calculating the first longitudinal distance, the second relative speed, and a fourth collision buffer zone corresponding to the target height according to a correlation between the target height and the first obstacle height and the second obstacle height;

[0026] Calculating a second longitudinal distance, a second relative speed, and a fifth collision buffer zone corresponding to the target height according to a correlation between the target height and the first obstacle height and the second obstacle height;

[0027] Calculating a sixth collision buffer area corresponding to the target longitudinal distance, the second relative speed, and the target height according to the correlation between the fourth collision buffer area and the fifth collision buffer area;

[0028] According to the correlation between the third collision buffer area and the sixth collision buffer area, a target collision buffer area corresponding to the attribute information corresponding to the target longitudinal distance, the target relative speed, and the target height is calculated.

[0029] The path planning method provided by the embodiment of the present invention obtains a three-dimensional interpolation table corresponding to the longitudinal distance, relative speed, obstacle height and collision buffer zone; then, according to the values ​​of the target longitudinal distance, target relative speed and target height, the first longitudinal distance and the second longitudinal distance adjacent to the target longitudinal distance, the first relative speed and the second relative speed adjacent to the target relative speed, and the first obstacle height and the second obstacle height adjacent to the target height are determined in the three-dimensional interpolation table in sequence, thereby ensuring the accuracy of the determined first longitudinal distance, second longitudinal distance, first relative speed, second relative speed, first obstacle height and second obstacle height. Then, according to the correlation between the target height and the first obstacle height and the second obstacle height, the first longitudinal distance, the first relative speed and the first collision buffer zone corresponding to the target height are calculated, thereby ensuring the accuracy of the calculated first collision buffer zone; according to the correlation between the target height and the first obstacle height and the second obstacle height, the second longitudinal distance, the first relative speed and the second collision buffer zone corresponding to the target height are calculated, thereby ensuring the accuracy of the calculated second collision buffer zone; according to the correlation between the first collision buffer zone and the second collision buffer zone, the target longitudinal distance, the first relative speed and the third collision buffer zone corresponding to the target height are calculated, thereby ensuring the accuracy of the calculated third collision buffer zone. According to the correlation between the target height and the first obstacle height and the second obstacle height, the first longitudinal distance, the second relative speed and the fourth collision buffer area corresponding to the target height are calculated, thereby ensuring the accuracy of the calculated fourth collision buffer area; according to the correlation between the target height and the first obstacle height and the second obstacle height, the second longitudinal distance, the second relative speed and the fifth collision buffer area corresponding to the target height are calculated, thereby ensuring the accuracy of the calculated fifth collision buffer area; according to the correlation between the fourth collision buffer area and the fifth collision buffer area, the target longitudinal distance, the second relative speed and the sixth collision buffer area corresponding to the target height are calculated, thereby ensuring the accuracy of the calculated sixth collision buffer area; according to the correlation between the third collision buffer area and the sixth collision buffer area, the target longitudinal distance, the target relative speed and the target collision buffer area corresponding to the attribute information corresponding to the target height are calculated, thereby ensuring the accuracy of the calculated target collision buffer area.

[0030] In combination with the second implementation of the first aspect, in the third implementation of the first aspect, according to the correlation between the target height and the first obstacle height and the second obstacle height, calculating the first longitudinal distance, the first relative speed, and the first collision buffer zone corresponding to the target height includes:

[0031] Searching a first preset collision buffer zone corresponding to a first longitudinal distance, a first relative speed, and a first obstacle height from a three-dimensional interpolation table;

[0032] Searching the second preset collision buffer zone corresponding to the first longitudinal distance, the first relative speed, and the second obstacle height from the three-dimensional interpolation table;

[0033] An interpolation calculation is performed on the first preset collision buffer area and the second preset collision buffer area to obtain a first collision buffer area corresponding to the first longitudinal distance, the first relative speed, and the target height.

[0034] The path planning method provided by the embodiment of the present invention searches for a first preset collision buffer zone corresponding to a first longitudinal distance, a first relative speed, and a first obstacle height from a three-dimensional interpolation table; searches for a second preset collision buffer zone corresponding to the first longitudinal distance, a first relative speed, and a second obstacle height from a three-dimensional interpolation table; interpolates the first preset collision buffer zone and the second preset collision buffer zone to obtain a first collision buffer zone corresponding to the first longitudinal distance, the first relative speed, and the target height, thereby ensuring the accuracy of the calculated first collision buffer zone.

[0035] In combination with the second implementation of the first aspect, in a fourth implementation of the first aspect, according to the correlation between the first collision buffer area and the second collision buffer area, calculating the third collision buffer area corresponding to the target longitudinal distance, the first relative speed, and the target height includes:

[0036] Interpolation calculation is performed on the first collision buffer area and the second collision buffer area to obtain a third collision buffer area corresponding to the target longitudinal distance, the first relative speed, and the target height.

[0037] The path planning method provided by the embodiment of the present invention performs interpolation calculation on the first collision buffer zone and the second collision buffer zone to obtain a third collision buffer zone corresponding to the target longitudinal distance, the first relative speed, and the target height, thereby ensuring the accuracy of the calculated third collision buffer zone.

[0038] In combination with the second implementation of the first aspect, in the fifth implementation of the first aspect, according to the correlation between the third collision buffer zone and the sixth collision buffer zone, calculating the target collision buffer zone corresponding to the attribute information corresponding to the target longitudinal distance, the target relative speed, and the target height includes:

[0039] Interpolation calculation is performed on the third collision buffer area and the sixth collision buffer area to obtain a target collision buffer area corresponding to the attribute information corresponding to the target longitudinal distance, the target relative speed, and the target height.

[0040] The path planning method provided by the embodiment of the present invention performs interpolation calculation on the third collision buffer zone and the sixth collision buffer zone to obtain a target collision buffer zone corresponding to the attribute information corresponding to the target longitudinal distance, the target relative speed, and the target height, thereby ensuring the accuracy of the calculated target collision buffer zone.

[0041] In combination with the first aspect, in a sixth implementation of the first aspect, the attribute information includes a target longitudinal distance and a target relative speed of the target obstacle relative to the target vehicle, and acquiring the attribute information of the target obstacle corresponding to the target vehicle includes:

[0042] Acquire first position information and first speed information corresponding to the target obstacle;

[0043] Acquire second position information and second speed information corresponding to the target vehicle;

[0044] Determining a longitudinal distance of the target according to a relationship between the first position information and the second position information;

[0045] The target relative speed is determined according to the relationship between the first speed information and the second speed information.

[0046] The path planning method provided by the embodiment of the present invention obtains the first position information and the first speed information corresponding to the target obstacle; obtains the second position information and the second speed information corresponding to the target vehicle; determines the target longitudinal distance according to the relationship between the first position information and the second position information, thereby ensuring the accuracy of the determined target longitudinal distance; determines the target relative speed according to the relationship between the first speed information and the second speed information, thereby ensuring the accuracy of the determined target relative speed.

[0047] According to the second aspect, an embodiment of the present invention further provides a path planning device, including:

[0048] an acquisition module, configured to acquire attribute information of a target obstacle corresponding to the target vehicle; the attribute information includes at least one of a target longitudinal distance, a target relative speed, a target lateral distance of the target obstacle relative to the target vehicle, a target perception tracking time for tracking the target obstacle, a target height of the target obstacle, and a target perception confidence of the target obstacle;

[0049] A determination module, used to determine a target collision buffer zone corresponding to a target obstacle according to a correspondence between the attribute information and the collision buffer zone corresponding to the obstacle;

[0050] The first generating module is used to add a target collision buffer zone to the target obstacle to generate a buffer target obstacle;

[0051] The first solving module is used to construct a boundary collision constraint according to the buffer target obstacle and run a preset path planning algorithm to solve the driving path;

[0052] The first output module is used to output a target path corresponding to the driving path when the driving path is solved successfully.

[0053] The path planning device provided by the embodiment of the present invention obtains the attribute information of the target obstacle corresponding to the target vehicle, and then determines the target collision buffer corresponding to the target obstacle according to the corresponding relationship between the attribute information and the collision buffer corresponding to the obstacle, thereby ensuring the accuracy of the target collision buffer corresponding to the determined target obstacle. Then, a target collision buffer is added to the target obstacle to generate a buffer target obstacle, thereby ensuring the accuracy of the generated buffer target obstacle. A boundary collision constraint is constructed according to the buffer target obstacle, and a preset path planning algorithm is run to solve the driving path, thereby ensuring the accuracy of the solution result. When the driving path is solved successfully, the target path corresponding to the driving path is output, thereby ensuring the accuracy of the output target path. The above device does not add a fixed collision buffer to the target obstacle, but determines the target collision buffer corresponding to the target obstacle according to the corresponding relationship between the attribute information and the collision buffer corresponding to the obstacle, thereby realizing adaptive calculation of the target collision buffer corresponding to the target obstacle, taking into account the attribute information corresponding to the target obstacle, thereby ensuring the accuracy of the target collision buffer corresponding to the determined target obstacle. In addition, the accuracy of the planned target path can be guaranteed.

[0054] According to the third aspect, an embodiment of the present invention provides an electronic device, including a memory and a processor, the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor executes the path planning method in the first aspect or any one of the embodiments of the first aspect by executing the computer instructions.

[0055] According to a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to execute the path planning method in the first aspect or any one of the embodiments of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0057] Figure 1 is a flow chart of a path planning method provided by an embodiment of the present invention;

[0058] Figure 2 is a flow chart of a path planning method provided by another embodiment of the present invention;

[0059] Figure 3is a flow chart of a path planning method provided by another embodiment of the present invention;

[0060] FIG4(a) is a schematic diagram of a two-dimensional interpolation table with a speed of Vrel0 provided by another embodiment of the present invention;

[0061] FIG4( b ) is a schematic diagram of a two-dimensional interpolation table with a speed of Vrel1 provided by another embodiment of the present invention;

[0062] FIG4( c ) is a schematic diagram of a two-dimensional interpolation table with a velocity of Vrelk provided by another embodiment of the present invention;

[0063] Figure 5 is a flow chart of a path planning method provided by another embodiment of the present invention;

[0064] Figure 6 It is a functional module diagram of a path planning device provided by an embodiment of the present invention;

[0065] Figure 7 It is a functional module diagram of a path planning device provided by an embodiment of the present invention;

[0066] Figure 8 It is a schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0067] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0068] It should be noted that the execution subject of the path planning method provided in the embodiment of the present application can be a path planning device, and the path planning device can be implemented as part or all of an electronic device through software, hardware, or a combination of software and hardware, wherein the electronic device can be the main controller of the autonomous driving vehicle, or a server or terminal independent of the autonomous driving vehicle. Among them, the server in the embodiment of the present application can be a single server, or a server cluster composed of multiple servers, and the terminal in the embodiment of the present application can be a smart phone, a personal computer, a tablet computer, an intelligent robot, and other intelligent hardware devices. In the following method embodiments, the execution subject is an electronic device as an example for explanation.

[0069] In one embodiment of the present application, Figure 1As shown, a path planning method is provided, which is described by taking the method applied to an electronic device as an example, and includes the following steps:

[0070] S11. Obtain attribute information of a target obstacle corresponding to the target vehicle.

[0071] The attribute information includes at least one of a target longitudinal distance, a target relative speed, a target lateral distance of the target obstacle relative to the target vehicle, a target perception tracking time of the target obstacle, a target height of the target obstacle, and a target perception confidence of the target obstacle.

[0072] In an optional implementation of the present application, the electronic device can receive attribute information of the target obstacle corresponding to the target vehicle input by the user, and can also receive attribute information of the target obstacle corresponding to the target vehicle sent by other devices. The electronic device can also perceive the attribute information of the target obstacle corresponding to the target vehicle through a perception module.

[0073] Exemplarily, the electronic device can use the perception module to perceive attribute information such as the target perception tracking time of the target obstacle, the target height of the target obstacle, and the target perception confidence of the target obstacle. It can also perceive the first position information and the first speed information corresponding to the target obstacle, and then obtain the second position information corresponding to the target vehicle through the positioning module on the target vehicle, and obtain the second speed information corresponding to the target vehicle through the chassis module on the target vehicle, and then calculate the target longitudinal distance, target relative speed, target lateral distance and other attribute information of the target obstacle relative to the target vehicle.

[0074] This step will be described in detail below.

[0075] S12. Determine a target collision buffer zone corresponding to the target obstacle according to a correspondence between the attribute information and the collision buffer zone corresponding to the obstacle.

[0076] In an optional implementation of the present application, the electronic device may obtain a correlation function between a collision buffer zone corresponding to an obstacle and each attribute information, and then determine a collision buffer zone corresponding to an obstacle corresponding to each attribute information, and average the calculated collision buffer zones corresponding to each obstacle to determine a target collision buffer zone corresponding to the target obstacle.

[0077] In another optional implementation of the present application, the electronic device may obtain at least one-dimensional interpolation table composed of various attribute information, and then search the target collision buffer zone corresponding to the target obstacle in the one-dimensional interpolation table according to the attribute information of the target obstacle corresponding to the target vehicle.

[0078] Exemplarily, the electronic device can obtain a five-dimensional interpolation table consisting of five attribute information: the height of the obstacle, the longitudinal distance between the obstacle and the vehicle, the relative speed between the vehicle and the obstacle, the obstacle perception confidence, and the perception tracking time; and then calculate the target collision buffer corresponding to the target obstacle based on the target height of the target obstacle, the target longitudinal distance of the target obstacle relative to the target vehicle, the target relative speed, the target perception tracking time for tracking the target obstacle, and the target perception confidence of the target obstacle, and the relationship between the data in the five-dimensional interpolation table, using a preset interpolation calculation method.

[0079] S13. Add a target collision buffer zone to the target obstacle to generate a buffer target obstacle.

[0080] Specifically, after determining the target collision buffer area corresponding to the target obstacle, the electronic device may expand the contour corresponding to the target obstacle according to the target collision buffer area, thereby adding a target collision buffer area to the target obstacle and generating a buffered target obstacle.

[0081] For example, assuming that the obstacle is a cylindrical obstacle with a diameter of 1 meter, the electronic device calculates that the target collision buffer zone corresponding to the cylindrical obstacle is 0.5 meters expanded along the outline of the obstacle. The electronic device then adds 0.5 meters to the diameter of the cylindrical obstacle to generate a buffer target obstacle, and the diameter of the buffer target obstacle is 1.5 meters.

[0082] S14. Constructing boundary collision constraints according to the buffer target obstacles, and running a preset path planning algorithm to solve the driving path.

[0083] Specifically, after obtaining the buffer target obstacle, the electronic device can construct a boundary collision constraint for the buffer target obstacle and run a preset path planning algorithm to solve the driving path.

[0084] Among them, the preset path planning algorithm can be a segmented acceleration path planning algorithm, a hybrid A-star path planning algorithm, etc.

[0085] S15. When the driving path is solved successfully, the target path corresponding to the driving path is output.

[0086] Specifically, when the driving path is solved successfully, the electronic device outputs a target path corresponding to the driving path.

[0087] The path planning method provided by the embodiment of the present invention obtains the attribute information of the target obstacle corresponding to the target vehicle, and then determines the target collision buffer corresponding to the target obstacle according to the corresponding relationship between the attribute information and the collision buffer corresponding to the obstacle, thereby ensuring the accuracy of the target collision buffer corresponding to the determined target obstacle. Then, a target collision buffer is added to the target obstacle to generate a buffer target obstacle, thereby ensuring the accuracy of the generated buffer target obstacle. A boundary collision constraint is constructed according to the buffer target obstacle, and a preset path planning algorithm is run to solve the driving path, thereby ensuring the accuracy of the solution result. When the driving path is solved successfully, the target path corresponding to the driving path is output, thereby ensuring the accuracy of the output target path. The above method does not add a fixed collision buffer to the target obstacle, but determines the target collision buffer corresponding to the target obstacle according to the corresponding relationship between the attribute information and the collision buffer corresponding to the obstacle, thereby realizing the adaptive calculation of the target collision buffer corresponding to the target obstacle, taking into account the attribute information corresponding to the target obstacle, thereby ensuring the accuracy of the target collision buffer corresponding to the determined target obstacle. In addition, the accuracy of the planned target path can be guaranteed.

[0088] In one embodiment of the present application, Figure 2 As shown, a path planning method is provided, which is described by taking the method applied to an electronic device as an example, and includes the following steps:

[0089] S21. Obtain attribute information of a target obstacle corresponding to the target vehicle.

[0090] The attribute information includes at least one of a target longitudinal distance, a target relative speed, a target lateral distance of the target obstacle relative to the target vehicle, a target perception tracking time of the target obstacle, a target height of the target obstacle, and a target perception confidence of the target obstacle.

[0091] For more information about this step, see Figure 1 The introduction of S11 will not be elaborated here.

[0092] S22. Determine a target collision buffer zone corresponding to the target obstacle according to a correspondence between the attribute information and the collision buffer zone corresponding to the obstacle.

[0093] For more information about this step, see Figure 1 The introduction of S12 will not be elaborated here.

[0094] S23. Add a target collision buffer zone to the target obstacle to generate a buffer target obstacle.

[0095] For more information about this step, see Figure 1 The introduction of S13 will not be elaborated here.

[0096] S24. Constructing boundary collision constraints according to the buffer target obstacles, and running a preset path planning algorithm to solve the driving path.

[0097] For more information about this step, see Figure 1 The introduction of S14 will not be elaborated here.

[0098] S25. When the driving path is solved successfully, the target path corresponding to the driving path is output.

[0099] For more information about this step, see Figure 1 The introduction of S15 will not be elaborated here.

[0100] S26. When the driving path solution fails, the target collision buffer area corresponding to the target obstacle is reduced according to a preset reduction factor to generate a reduced collision buffer area.

[0101] Specifically, when the driving path solution fails, the electronic device may multiply the target collision buffer area corresponding to the target obstacle by a preset reduction factor, thereby reducing the target collision buffer area corresponding to the target obstacle according to the preset reduction factor to generate a reduced collision buffer area.

[0102] The preset reduction factor may be 0.9, 0.85, or 0.8. The embodiment of the present application does not specifically limit the preset reduction factor.

[0103] S27. Add a reduced collision buffer for the target obstacle to generate a buffered reduced target obstacle.

[0104] Specifically, after calculating and obtaining the reduced collision buffer zone, the electronic device adds the reduced collision buffer zone to the target obstacle to generate a buffered reduced target obstacle.

[0105] S28, constructing a boundary collision constraint based on buffering and reducing the target obstacle, and running a preset path planning algorithm to solve the driving path again.

[0106] Specifically, after obtaining the buffered and reduced target obstacle, the electronic device can construct a boundary collision constraint according to the buffered and reduced target obstacle, and run a preset path planning algorithm to solve the driving path.

[0107] Among them, the preset path planning algorithm can be a segmented acceleration path planning algorithm, a hybrid A-star path planning algorithm, etc.

[0108] S29: After a preset number of times, if the solution fails, output the parking path.

[0109] When the driving path is solved successfully, the electronic device outputs the target path corresponding to the driving path.

[0110] When the driving path solution fails, the electronic device reduces the buffer and reduces the target obstacle according to a preset reduction factor, and repeats this cycle until the preset number of times. If the solution fails, the parking path is output.

[0111] The preset number may be 3 or 4, and the embodiment of the present application does not specifically limit the preset number.

[0112] For example, the formula is as follows:

[0113] B i =B i *reduction_ratio (1)

[0114] count+=1 (2)

[0115] Among them, B i is the target collision buffer, reduction_ratio is the preset reduction multiple; Count is initially 0. Due to computing power limitations, the upper limit is generally set to 3, that is, a maximum of 3 cycles. If the solution is still not found, the parking path is output.

[0116] The path planning method provided by the embodiment of the present invention, when the solution of the driving path fails, reduces the target collision buffer corresponding to the target obstacle according to a preset reduction multiple to generate a reduced collision buffer, thereby ensuring the accuracy of the generated reduced collision buffer. A reduced collision buffer is added to the target obstacle to generate a buffered reduced target obstacle; a boundary collision constraint is constructed based on the buffered reduced target obstacle, and the preset path planning algorithm is run to solve the driving path again, thereby avoiding the failure of path planning due to the target buffer being too large. After a preset number of times, if the solution fails, the parking path is output, thereby ensuring the accuracy of path planning. The above method avoids the failure of path planning due to the target buffer being too large, and also avoids the failure of path planning due to the reduced collision buffer being too small, thereby ensuring the accuracy of the planned path when the buffer corresponding to the target obstacle is appropriate.

[0117] In one embodiment of the present application, Figure 3 As shown, a path planning method is provided, which is described by taking the method applied to an electronic device as an example, and includes the following steps:

[0118] S31. Obtain attribute information of a target obstacle corresponding to the target vehicle.

[0119] The attribute information includes at least one of a target longitudinal distance, a target relative speed, a target lateral distance of the target obstacle relative to the target vehicle, a target perception tracking time of the target obstacle, a target height of the target obstacle, and a target perception confidence of the target obstacle.

[0120] For more information about this step, see Figure 2 The introduction of S21 will not be elaborated here.

[0121] S32. Determine a target collision buffer zone corresponding to the target obstacle according to the corresponding relationship between the attribute information and the collision buffer zone corresponding to the obstacle.

[0122] In an optional implementation manner of the present application, the attribute information includes a target longitudinal distance of the target obstacle relative to the target vehicle, a target relative speed, and a target height of the target obstacle. The above S32 "determining a target collision buffer zone corresponding to the target obstacle according to a correspondence between the attribute information and the collision buffer zone corresponding to the obstacle" may include the following steps;

[0123] S321, obtaining a three-dimensional interpolation table corresponding to the longitudinal distance, relative speed, obstacle height and collision buffer zone.

[0124] Specifically, the electronic device can receive a three-dimensional interpolation table corresponding to the longitudinal distance, relative speed, and obstacle height and the collision buffer zone input by the user, and can also receive a three-dimensional interpolation table corresponding to the longitudinal distance, relative speed, and obstacle height and the collision buffer zone sent by other devices. The embodiment of the present application does not specifically limit the manner in which the electronic device obtains the three-dimensional interpolation table corresponding to the longitudinal distance, relative speed, and obstacle height and the collision buffer zone.

[0125] For example, as shown in FIG4 , the first dimension of the three-dimensional interpolation table is the obstacle height (column) divided into n segments, the second dimension is the longitudinal distance (row) divided into m segments, and the third dimension is the relative speed (table) divided into k segments (there are k two-dimensional interpolation tables). Among them, FIG4 (a) is a two-dimensional interpolation table with a speed of Vrel0; FIG4 (b) is a two-dimensional interpolation table with a speed of Vrel1; and FIG4 (c) is a two-dimensional interpolation table with a speed of Vrelk.

[0126] S322. According to the values ​​of the target longitudinal distance, the target relative speed, and the target height, determine in the three-dimensional interpolation table in sequence a first longitudinal distance and a second longitudinal distance adjacent to the target longitudinal distance, a first relative speed and a second relative speed adjacent to the target relative speed, and a first obstacle height and a second obstacle height adjacent to the target height.

[0127] Specifically, according to the values ​​of the target longitudinal distance, the target relative speed and the target height, the first longitudinal distance and the second longitudinal distance adjacent to the target longitudinal distance, the first relative speed and the second relative speed adjacent to the target relative speed, and the first obstacle height and the second obstacle height adjacent to the target height are determined in sequence in the three-dimensional interpolation table.

[0128] For example, assuming the target height is h i, the target longitudinal distance is L i , the target relative speed is v reli , the electronic device determines the first longitudinal distance and the second longitudinal distance adjacent to the target longitudinal distance, the first relative speed and the second relative speed adjacent to the target relative speed, and the first obstacle height and the second obstacle height adjacent to the target height in the three-dimensional interpolation table according to the values ​​of the target longitudinal distance, the target relative speed and the target height, then h 1 <h i <h 2 ; L 3 <L i <L 4 ;v rel0 <v reli <v rel1 ;h 1 is the height of the first obstacle, h 2 is the height of the second obstacle, L 3 is the first relative speed, L 4 is the second relative velocity, v rel0 is the first longitudinal distance, v rel1 is the second longitudinal distance.

[0129] S323: Calculate a first longitudinal distance, a first relative speed, and a first collision buffer zone corresponding to the target height according to a correlation between the target height and the first obstacle height and the second obstacle height.

[0130] In an optional implementation of the present application, the above S323 "calculating the first longitudinal distance, the first relative speed, and the first collision buffer zone corresponding to the target height according to the correlation between the target height and the first obstacle height and the second obstacle height" may include the following steps:

[0131] (1) Searching a first preset collision buffer zone corresponding to a first longitudinal distance, a first relative speed, and a first obstacle height from a three-dimensional interpolation table.

[0132] (2) searching, from the three-dimensional interpolation table, a second preset collision buffer zone corresponding to the first longitudinal distance, the first relative speed, and the second obstacle height;

[0133] (3) performing interpolation calculation on the first preset collision buffer zone and the second preset collision buffer zone to obtain a first collision buffer zone corresponding to the first longitudinal distance, the first relative speed, and the target height.

[0134] Specifically, the electronic device can search the first preset collision buffer zone corresponding to the first longitudinal distance, the first relative speed, and the first obstacle height in the three-dimensional interpolation table. Then, search the second preset collision buffer zone corresponding to the first longitudinal distance, the first relative speed, and the second obstacle height from the three-dimensional interpolation table. Then, interpolation calculation is performed on the first preset collision buffer zone and the second preset collision buffer zone to obtain the first collision buffer zone corresponding to the first longitudinal distance, the first relative speed, and the target height.

[0135] Among them, the interpolation calculation method can use Newton interpolation, Lagrange polynomial interpolation, or quadratic interpolation. The embodiment of the present application does not specifically limit the interpolation calculation method.

[0136] Exemplarily, the electronic device may calculate the first collision buffer area using the following formula:

[0137]

[0138] in, is the first collision buffer, is the first preset collision buffer zone, Preset collision buffer for the second one.

[0139] S324: Calculate the second longitudinal distance, the first relative speed, and the second collision buffer zone corresponding to the target height according to the correlation between the target height and the first obstacle height and the second obstacle height.

[0140] Specifically, a third preset collision buffer zone corresponding to the second longitudinal distance, the first relative speed, and the first obstacle height is searched from the three-dimensional interpolation table; a fourth preset collision buffer zone corresponding to the second longitudinal distance, the first relative speed, and the second obstacle height is searched from the three-dimensional interpolation table; and the third preset collision buffer zone and the fourth preset collision buffer zone are interpolated to obtain a second collision buffer zone corresponding to the second longitudinal distance, the first relative speed, and the target height.

[0141] Among them, the interpolation calculation method can use Newton interpolation, Lagrange polynomial interpolation, or quadratic interpolation. The embodiment of the present application does not specifically limit the interpolation calculation method.

[0142] Exemplarily, the electronic device may calculate the second collision buffer area using the following formula:

[0143]

[0144] in, is the second collision buffer, For the third preset collision buffer, Preset collision buffer for the fourth.

[0145] S325 . Calculate a third collision buffer area corresponding to the target longitudinal distance, the first relative speed, and the target height according to the correlation between the first collision buffer area and the second collision buffer area.

[0146] In an optional implementation manner of the present application, the above S325 "calculating the third collision buffer area corresponding to the target longitudinal distance, the first relative speed, and the target height according to the correlation between the first collision buffer area and the second collision buffer area" may include the following steps:

[0147] (1) Interpolation calculation is performed on the first collision buffer zone and the second collision buffer zone to obtain a third collision buffer zone corresponding to the target longitudinal distance, the first relative speed, and the target height.

[0148] Specifically, the electronic device may perform interpolation calculation on the first collision buffer area and the second collision buffer area to obtain a third collision buffer area corresponding to the target longitudinal distance, the first relative speed, and the target height.

[0149] Among them, the interpolation calculation method can use Newton interpolation, Lagrange polynomial interpolation, or quadratic interpolation. The embodiment of the present application does not specifically limit the interpolation calculation method.

[0150] Exemplarily, the electronic device may calculate the third collision buffer zone using the following formula:

[0151]

[0152] in, is the third collision buffer zone, is the first collision buffer, The second collision buffer.

[0153] S326: Calculate the first longitudinal distance, the second relative speed, and a fourth collision buffer zone corresponding to the target height according to the correlation between the target height and the first obstacle height and the second obstacle height.

[0154] Specifically, a fifth preset collision buffer zone corresponding to the first longitudinal distance, the second relative speed, and the first obstacle height is searched from the three-dimensional interpolation table; a sixth preset collision buffer zone corresponding to the first longitudinal distance, the second relative speed, and the second obstacle height is searched from the three-dimensional interpolation table; the fifth preset collision buffer zone and the sixth preset collision buffer zone are interpolated to calculate a fourth collision buffer zone corresponding to the first longitudinal distance, the second relative speed, and the target height.

[0155] Among them, the interpolation calculation method can use Newton interpolation, Lagrange polynomial interpolation, or quadratic interpolation. The embodiment of the present application does not specifically limit the interpolation calculation method.

[0156] Exemplarily, the electronic device may calculate the fourth collision buffer area using the following formula:

[0157]

[0158] in, is the fourth collision buffer zone, For the fifth preset collision buffer, Preset collision buffer for the sixth.

[0159] S327: Calculate the second longitudinal distance, the second relative speed, and a fifth collision buffer area corresponding to the target height according to the correlation between the target height and the first obstacle height and the second obstacle height.

[0160] Specifically, searching the third preset collision buffer zone corresponding to the second longitudinal distance, the second relative speed, and the first obstacle height from the three-dimensional interpolation table; searching the third preset collision buffer zone corresponding to the second longitudinal distance, the second relative speed, and the second obstacle height from the three-dimensional interpolation table;

[0161] An interpolation calculation is performed on the seventh preset collision buffer area and the eighth preset collision buffer area to obtain a fifth collision buffer area corresponding to the first longitudinal distance, the first relative speed, and the target height.

[0162] Among them, the interpolation calculation method can use Newton interpolation, Lagrange polynomial interpolation, or quadratic interpolation. The embodiment of the present application does not specifically limit the interpolation calculation method.

[0163] Exemplarily, the electronic device may calculate the fifth collision buffer zone using the following formula:

[0164]

[0165] in, is the fifth collision buffer zone, For the seventh preset collision buffer, Preset collision buffer for the eighth.

[0166] S328. Calculate a sixth collision buffer area corresponding to the target longitudinal distance, the second relative speed, and the target height according to the correlation between the fourth collision buffer area and the fifth collision buffer area.

[0167] Specifically, the electronic device may perform interpolation calculation on the fourth collision buffer area and the fifth collision buffer area to obtain a sixth collision buffer area corresponding to the target longitudinal distance, the first relative speed, and the target height.

[0168] Among them, the interpolation calculation method can use Newton interpolation, Lagrange polynomial interpolation, or quadratic interpolation. The embodiment of the present application does not specifically limit the interpolation calculation method.

[0169] Exemplarily, the electronic device may calculate the sixth collision buffer zone using the following formula:

[0170]

[0171] in, is the sixth collision buffer zone, is the fourth collision buffer zone, It is the fifth collision buffer zone.

[0172] S329: Calculate the target collision buffer area corresponding to the attribute information corresponding to the target longitudinal distance, the target relative speed, and the target height according to the correlation between the third collision buffer area and the sixth collision buffer area.

[0173] In an optional implementation of the present application, the above S329 "calculating the target collision buffer area corresponding to the attribute information corresponding to the target longitudinal distance, the target relative speed, and the target height according to the correlation between the third collision buffer area and the sixth collision buffer area" may include the following steps:

[0174] (1) Interpolation calculation is performed on the third collision buffer zone and the sixth collision buffer zone to obtain a target collision buffer zone corresponding to attribute information corresponding to the target longitudinal distance, the target relative speed, and the target height.

[0175] Specifically, the electronic device may perform interpolation calculation on the third collision buffer zone and the sixth collision buffer zone to obtain the target collision buffer zone corresponding to the attribute information of the target longitudinal distance, the target relative speed and the target height.

[0176] Among them, the interpolation calculation method can use Newton interpolation, Lagrange polynomial interpolation, or quadratic interpolation. The embodiment of the present application does not specifically limit the interpolation calculation method.

[0177] Exemplarily, the electronic device may calculate the target collision buffer zone using the following formula:

[0178]

[0179] in, is the target collision buffer, is the third collision buffer zone, It is the sixth collision buffer zone.

[0180] It should be noted that the above embodiment only provides a specific implementation method for calculating the target collision buffer area. The electronic device can also calculate the target collision buffer area in the following manner.

[0181] Specifically, according to the correlation between the target longitudinal distance and the first longitudinal distance and the second longitudinal distance, the first target height, the first relative speed and the first collision buffer zone corresponding to the target longitudinal distance are calculated;

[0182] Calculating a second target height, a first relative speed, and a second collision buffer zone corresponding to the target longitudinal distance according to a correlation between the target longitudinal distance and the first longitudinal distance and the second longitudinal distance;

[0183] Calculating a third collision buffer area corresponding to the target longitudinal distance, the first relative speed, and the target height according to the correlation between the first collision buffer area and the second collision buffer area;

[0184] Calculating the first target height, the second relative speed, and a fourth collision buffer zone corresponding to the target longitudinal distance according to the correlation between the target longitudinal distance and the first longitudinal distance and the second longitudinal distance;

[0185] Calculating a fifth collision buffer zone corresponding to a second target height, a second relative speed, and the target longitudinal distance according to a correlation between the target longitudinal distance and the first longitudinal distance and the second longitudinal distance;

[0186] Calculating a sixth collision buffer area corresponding to the target longitudinal distance, the second relative speed, and the target height according to the correlation between the fourth collision buffer area and the fifth collision buffer area;

[0187] According to the correlation between the third collision buffer area and the sixth collision buffer area, a target collision buffer area corresponding to the attribute information corresponding to the target longitudinal distance, the target relative speed, and the target height is calculated.

[0188] Other methods evolved from this method are also within the protection scope of this application, and this application will not list them one by one.

[0189] S33: adding a target collision buffer zone to the target obstacle to generate a buffer target obstacle.

[0190] For more information about this step, see Figure 2 The introduction of S23 will not be elaborated here.

[0191] S34: constructing boundary collision constraints according to the buffer target obstacles, and running a preset path planning algorithm to solve the driving path.

[0192] For more information about this step, see Figure 2 The introduction of S24 will not be elaborated here.

[0193] S35. When the driving path is solved successfully, the target path corresponding to the driving path is output.

[0194] For more information about this step, see Figure 2 The introduction of S25 will not be elaborated here.

[0195] The path planning method provided by the embodiment of the present invention obtains a three-dimensional interpolation table corresponding to the longitudinal distance, relative speed, obstacle height and collision buffer zone; then, according to the values ​​of the target longitudinal distance, target relative speed and target height, the first longitudinal distance and the second longitudinal distance adjacent to the target longitudinal distance, the first relative speed and the second relative speed adjacent to the target relative speed, and the first obstacle height and the second obstacle height adjacent to the target height are determined in the three-dimensional interpolation table in turn, thereby ensuring the accuracy of the determined first longitudinal distance, second longitudinal distance, first relative speed, second relative speed, first obstacle height and second obstacle height. Then, from the three-dimensional interpolation table, the first preset collision buffer zone corresponding to the first longitudinal distance, the first relative speed and the first obstacle height is searched; from the three-dimensional interpolation table, the second preset collision buffer zone corresponding to the first longitudinal distance, the first relative speed and the second obstacle height is searched; the first preset collision buffer zone and the second preset collision buffer zone are interpolated and calculated to obtain the first collision buffer zone corresponding to the first longitudinal distance, the first relative speed and the target height, thereby ensuring the accuracy of the calculated first collision buffer zone. According to the correlation between the target height and the first obstacle height and the second obstacle height, the second longitudinal distance, the first relative speed and the second collision buffer zone corresponding to the target height are calculated, thereby ensuring the accuracy of the calculated second collision buffer zone. Then, the first collision buffer zone and the second collision buffer zone are interpolated to obtain the third collision buffer zone corresponding to the target longitudinal distance, the first relative speed and the target height, thereby ensuring the accuracy of the calculated third collision buffer zone.

[0196] According to the correlation between the target height and the first obstacle height and the second obstacle height, the first longitudinal distance, the second relative speed and the fourth collision buffer corresponding to the target height are calculated, thereby ensuring the accuracy of the calculated fourth collision buffer; according to the correlation between the target height and the first obstacle height and the second obstacle height, the second longitudinal distance, the second relative speed and the fifth collision buffer corresponding to the target height are calculated, thereby ensuring the accuracy of the calculated fifth collision buffer; according to the correlation between the fourth collision buffer and the fifth collision buffer, the target longitudinal distance, the second relative speed and the sixth collision buffer corresponding to the target height are calculated, thereby ensuring the accuracy of the calculated sixth collision buffer. Then, the third collision buffer and the sixth collision buffer are interpolated to obtain the target collision buffer corresponding to the attribute information corresponding to the target longitudinal distance, the target relative speed and the target height, thereby ensuring the accuracy of the calculated target collision buffer.

[0197] In one embodiment of the present application, Figure 5 As shown, a path planning method is provided, which is described by taking the method applied to an electronic device as an example, and includes the following steps:

[0198] S41. Obtain attribute information of a target obstacle corresponding to the target vehicle.

[0199] The attribute information includes at least one of a target longitudinal distance, a target relative speed, a target lateral distance of the target obstacle relative to the target vehicle, a target perception tracking time of the target obstacle, a target height of the target obstacle, and a target perception confidence of the target obstacle.

[0200] In an optional implementation manner of the present application, the attribute information includes a target longitudinal distance and a target relative speed of the target obstacle relative to the target vehicle. The “obtaining attribute information of the target obstacle corresponding to the target vehicle” in the above S41 may include the following steps:

[0201] S411. Obtain first position information and first speed information corresponding to the target obstacle.

[0202] Specifically, the electronic device can receive the first position information and the first speed information corresponding to the target obstacle input by the user; it can also receive the first position information and the first speed information corresponding to the target obstacle sent by other devices; the electronic device can also obtain the first position information and the first speed information corresponding to the target obstacle based on the connection with the perception module on the target vehicle.

[0203] The embodiment of the present application does not specifically limit the manner in which the electronic device obtains the first position information and the first speed information corresponding to the target obstacle.

[0204] S412: Obtain second position information and second speed information corresponding to the target vehicle.

[0205] Specifically, the electronic device can receive the second position information and second speed information corresponding to the target vehicle input by the user; it can also receive the second position information and second speed information corresponding to the target vehicle sent by other devices; the electronic device can also obtain the second position information corresponding to the target vehicle based on the connection with the positioning module of the target vehicle, and obtain the second speed information corresponding to the target vehicle based on the connection with the chassis module of the target vehicle.

[0206] The embodiment of the present application does not specifically limit the manner in which the electronic device obtains the second position information and the second speed information corresponding to the target vehicle.

[0207] S413: Determine a longitudinal distance of the target according to a relationship between the first position information and the second position information.

[0208] Specifically, the electronic device may determine the longitudinal distance of the target according to the relationship between the first position information and the second position information.

[0209] In an optional implementation of the present application, the first position information may include coordinate position information corresponding to the target obstacle and a navigation angle corresponding to the target obstacle. For example, the heading angle of the target obstacle may be θ obs , the location information of the target obstacle is (x obs ,y obs ).

[0210] The second position information may include the coordinate position information corresponding to the target vehicle and the heading angle corresponding to the target vehicle. For example, the heading angle of the target vehicle may be θ r_ego , the location information of the target vehicle is (x r_ego ,y r_ego ).

[0211] Exemplarily, the electronic device may calculate the target longitudinal distance of the target obstacle type to the target vehicle using the following formula:

[0212]

[0213] S414: Determine the target relative speed according to the relationship between the first speed information and the second speed information.

[0214] Specifically, the electronic device can obtain the heading angle of the target obstacle and the heading angle of the target vehicle, and then determine the target relative speed according to the relationship between the first speed information and the second speed information and the relationship between the heading angle of the target obstacle and the heading angle of the target vehicle.

[0215] Exemplarily, the electronic device may calculate the target relative speed using the following formula:

[0216] v reli =|v obs cos(θ obs -θ r_ego )-v ego | (11)

[0217] S42: Determine a target collision buffer zone corresponding to the target obstacle according to the corresponding relationship between the attribute information and the collision buffer zone corresponding to the obstacle.

[0218] For more information about this step, see Figure 3 The introduction of S32 will not be elaborated here.

[0219] S43: Add a target collision buffer zone to the target obstacle to generate a buffer target obstacle.

[0220] For more information about this step, see Figure 3 The introduction of S33 will not be elaborated here.

[0221] S44, constructing a boundary collision constraint according to the buffer target obstacle, and running a preset path planning algorithm to solve the driving path.

[0222] For more information about this step, see Figure 3 The introduction of S34 will not be elaborated here.

[0223] S45. When the driving path is solved successfully, output the target path corresponding to the driving path.

[0224] For more information about this step, see Figure 3 The introduction of S35 will not be elaborated here.

[0225] The path planning method provided by the embodiment of the present invention obtains the first position information and the first speed information corresponding to the target obstacle; obtains the second position information and the second speed information corresponding to the target vehicle; determines the target longitudinal distance according to the relationship between the first position information and the second position information, thereby ensuring the accuracy of the determined target longitudinal distance; determines the target relative speed according to the relationship between the first speed information and the second speed information, thereby ensuring the accuracy of the determined target relative speed.

[0226] It should be understood that although Figure 1-3 as well as Figure 5 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1-3 as well as Figure 5 At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0227] like Figure 6 As shown, this embodiment provides a path planning device, including:

[0228] An acquisition module 51 is used to acquire attribute information of a target obstacle corresponding to the target vehicle; the attribute information includes at least one of a target longitudinal distance, a target relative speed, a target lateral distance of the target obstacle relative to the target vehicle, a target perception tracking time for tracking the target obstacle, a target height of the target obstacle, and a target perception confidence of the target obstacle;

[0229] A determination module 52, configured to determine a target collision buffer zone corresponding to a target obstacle according to a correspondence between the attribute information and the collision buffer zone corresponding to the obstacle;

[0230] A first generating module 53 is used to add a target collision buffer zone to a target obstacle to generate a buffer target obstacle;

[0231] A first solving module 54 is used to construct a boundary collision constraint according to the buffer target obstacle and run a preset path planning algorithm to solve the driving path;

[0232] The first output module 55 is used to output a target path corresponding to the driving path when the driving path is solved successfully.

[0233] like Figure 7 As shown, this embodiment provides a path planning device, further comprising:

[0234] A reduction module 56 is used to reduce the target collision buffer area corresponding to the target obstacle according to a preset reduction factor to generate a reduced collision buffer area when the driving path solution fails;

[0235] The second generating module 57 is used to add a reduced collision buffer for the target obstacle and generate a buffered reduced target obstacle;

[0236] The second solving module 58 is used to construct a boundary collision constraint according to the buffered and reduced target obstacle, and run a preset path planning algorithm to solve the driving path again;

[0237] The second output module 59 is used to output the parking path if the solution fails after a preset number of times.

[0238] In one embodiment of the present application, the attribute information includes a target longitudinal distance, a target relative speed, and a target height of the target obstacle relative to the target vehicle. The above-mentioned determination module 52 is specifically used to obtain a three-dimensional interpolation table corresponding to the longitudinal distance, the relative speed, and the obstacle height and the collision buffer zone; according to the values ​​of the target longitudinal distance, the target relative speed, and the target height, the first longitudinal distance and the second longitudinal distance adjacent to the target longitudinal distance, the first relative speed and the second relative speed adjacent to the target relative speed, and the first obstacle height and the second obstacle height adjacent to the target height are determined in the three-dimensional interpolation table in sequence; according to the correlation between the target height and the first obstacle height and the second obstacle height, the first collision buffer zone corresponding to the first longitudinal distance, the first relative speed, and the target height is calculated; according to the correlation between the target height and the first obstacle height and the second obstacle height, the second longitudinal distance, the first relative speed, and the first collision buffer zone corresponding to the target height are calculated. and a second collision buffer area corresponding to the target height; according to the correlation between the first collision buffer area and the second collision buffer area, the target longitudinal distance, the first relative speed and the third collision buffer area corresponding to the target height are calculated; according to the correlation between the target height and the first obstacle height and the second obstacle height, the first longitudinal distance, the second relative speed and the fourth collision buffer area corresponding to the target height are calculated; according to the correlation between the target height and the first obstacle height and the second obstacle height, the second longitudinal distance, the second relative speed and the fifth collision buffer area corresponding to the target height are calculated; according to the correlation between the fourth collision buffer area and the fifth collision buffer area, the target longitudinal distance, the second relative speed and the sixth collision buffer area corresponding to the target height are calculated; according to the correlation between the third collision buffer area and the sixth collision buffer area, the target longitudinal distance, the target relative speed and the target collision buffer area corresponding to the attribute information corresponding to the target height are calculated.

[0239] In one embodiment of the present application, the above-mentioned determination module 52 is specifically used to search for a first preset collision buffer zone corresponding to the first longitudinal distance, the first relative speed and the first obstacle height from a three-dimensional interpolation table; search for a second preset collision buffer zone corresponding to the first longitudinal distance, the first relative speed and the second obstacle height from the three-dimensional interpolation table; and perform interpolation calculation on the first preset collision buffer zone and the second preset collision buffer zone to obtain a first collision buffer zone corresponding to the first longitudinal distance, the first relative speed and the target height.

[0240] In one embodiment of the present application, the determination module 52 is specifically configured to perform interpolation calculation on the first collision buffer zone and the second collision buffer zone to obtain a third collision buffer zone corresponding to the target longitudinal distance, the first relative speed, and the target height.

[0241] In one embodiment of the present application, the determination module 52 is specifically used to perform interpolation calculations on the third collision buffer zone and the sixth collision buffer zone to obtain a target collision buffer zone corresponding to the attribute information corresponding to the target longitudinal distance, target relative speed and target height.

[0242] In one embodiment of the present application, the attribute information includes a target longitudinal distance and a target relative speed of the target obstacle relative to the target vehicle. The acquisition module 51 is specifically used to obtain the first position information and the first speed information corresponding to the target obstacle; obtain the second position information and the second speed information corresponding to the target vehicle; determine the target longitudinal distance based on the relationship between the first position information and the second position information; and determine the target relative speed based on the relationship between the first speed information and the second speed information.

[0243] For the specific limitations and beneficial effects of the path planning device, please refer to the limitations of the path planning method above, which will not be repeated here. Each module in the above-mentioned path planning device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the electronic device in the form of hardware, or can be stored in the memory of the electronic device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0244] The embodiment of the present invention also provides an electronic device having the above Figure 8 The path planning device shown.

[0245] like Figure 8 As shown, Figure 8 is a schematic diagram of the structure of an electronic device provided by an optional embodiment of the present invention, such as Figure 8 As shown, the electronic device may include: at least one processor 61, such as a CPU (Central Processing Unit), at least one communication interface 63, a memory 64, and at least one communication bus 62. The communication bus 62 is used to realize the connection and communication between these components. The communication interface 63 may include a display screen (Display), a keyboard (Keyboard), and the optional communication interface 63 may also include a standard wired interface and a wireless interface. The memory 64 may be a high-speed RAM memory (Random Access Memory) or a non-volatile memory (non-volatile memory), such as at least one disk storage. The memory 64 may optionally be at least one storage device located away from the aforementioned processor 61. The processor 61 may be combined with Figure 6 or / and Figure 7In the described device, the memory 64 stores an application program, and the processor 61 calls the program code stored in the memory 64 to execute any of the above method steps.

[0246] The communication bus 62 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The communication bus 62 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 8 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0247] Among them, the memory 64 may include a volatile memory (English: volatile memory), such as a random access memory (English: random-access memory, abbreviated: RAM); the memory may also include a non-volatile memory (English: non-volatile memory), such as a flash memory (English: flash memory), a hard disk drive (English: hard disk drive, abbreviated: HDD) or a solid-state drive (English: solid-state drive, abbreviated: SSD); the memory 64 may also include a combination of the above types of memory.

[0248] The processor 61 may be a central processing unit (CPU), a network processor (NP), or a combination of a CPU and a NP.

[0249] The processor 61 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0250] Optionally, the memory 64 is also used to store program instructions. The processor 61 can call the program instructions to implement the present application Figures 1 to 3 as well as Figure 5 The path planning method shown in the embodiment.

[0251] The embodiment of the present invention also provides a non-transitory computer storage medium, wherein the computer storage medium stores computer executable instructions, and the computer executable instructions can execute the path planning method in any of the above method embodiments. The storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk (HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above types of memory.

[0252] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A path planning method, characterized in that: include: Obtaining attribute information of the target obstacle corresponding to the target vehicle; The attribute information includes at least one of a target longitudinal distance, a target relative speed, a target lateral distance of the target obstacle relative to the target vehicle, a target perception tracking time for tracking the target obstacle, a target height of the target obstacle, and a target perception confidence of the target obstacle; Determining a target collision buffer zone corresponding to the target obstacle according to a correspondence between the attribute information and the collision buffer zone corresponding to the obstacle; Adding the target collision buffer zone to the target obstacle to generate a buffer target obstacle; Constructing boundary collision constraints according to the buffer target obstacle, and running a preset path planning algorithm to solve the driving path; When the driving path is solved successfully, outputting a target path corresponding to the driving path; When the attribute information includes the target longitudinal distance of the target obstacle relative to the target vehicle, the target relative speed, and the target height of the target obstacle, determining the target collision buffer zone corresponding to the target obstacle according to the corresponding relationship between the attribute information and the collision buffer zone corresponding to the obstacle includes: Obtain a three-dimensional interpolation table corresponding to the longitudinal distance, relative speed, obstacle height and collision buffer zone; According to the values ​​of the target longitudinal distance, the target relative speed and the target height, determine in the three-dimensional interpolation table in sequence a first longitudinal distance and a second longitudinal distance adjacent to the target longitudinal distance, a first relative speed and a second relative speed adjacent to the target relative speed, and a first obstacle height and a second obstacle height adjacent to the target height; Calculating the first longitudinal distance, the first relative speed, and a first collision buffer zone corresponding to the target height according to a correlation between the target height and the first obstacle height and the second obstacle height; Calculating the second longitudinal distance, the first relative speed, and a second collision buffer zone corresponding to the target height according to a correlation between the target height and the first obstacle height and the second obstacle height; Calculating a third collision buffer area corresponding to the target longitudinal distance, the first relative speed, and the target height according to a correlation between the first collision buffer area and the second collision buffer area; Calculating the first longitudinal distance, the second relative speed, and a fourth collision buffer zone corresponding to the target height according to a correlation between the target height and the first obstacle height and the second obstacle height; Calculating the second longitudinal distance, the second relative speed, and a fifth collision buffer zone corresponding to the target height according to a correlation between the target height and the first obstacle height and the second obstacle height; Calculating a sixth collision buffer area corresponding to the target longitudinal distance, the second relative speed, and the target height according to a correlation between the fourth collision buffer area and the fifth collision buffer area; The target collision buffer area corresponding to the target longitudinal distance, the target relative speed, and the target height corresponding to the attribute information is calculated according to the correlation between the third collision buffer area and the sixth collision buffer area.

2. The method according to claim 1, characterized in that The method further comprises: When the driving path solution fails, the target collision buffer area corresponding to the target obstacle is reduced by a preset reduction factor to generate a reduced collision buffer area; Adding the reduced collision buffer zone to the target obstacle to generate a buffered reduced target obstacle; Constructing a boundary collision constraint according to the buffered target obstacle reduction, and running the preset path planning algorithm to solve the driving path again; After a preset number of times, if the solution fails, the parking path is output.

3. The method according to claim 1, characterized in that The calculating, according to the correlation between the target height and the first obstacle height and the second obstacle height, the first longitudinal distance, the first relative speed, and a first collision buffer zone corresponding to the target height includes: Searching, from the three-dimensional interpolation table, a first preset collision buffer zone corresponding to the first longitudinal distance, the first relative speed, and the first obstacle height; Searching, from the three-dimensional interpolation table, a second preset collision buffer zone corresponding to the first longitudinal distance, the first relative speed, and the second obstacle height; An interpolation calculation is performed on the first preset collision buffer area and the second preset collision buffer area to obtain a first collision buffer area corresponding to the first longitudinal distance, the first relative speed, and the target height.

4. The method according to claim 1, characterized in that The calculating, according to the correlation between the first collision buffer zone and the second collision buffer zone, a third collision buffer zone corresponding to the target longitudinal distance, the first relative speed, and the target height comprises: An interpolation calculation is performed on the first collision buffer area and the second collision buffer area to obtain a third collision buffer area corresponding to the target longitudinal distance, the first relative speed, and the target height.

5. The method according to claim 1, characterized in that The step of calculating the target collision buffer area corresponding to the attribute information corresponding to the target longitudinal distance, the target relative speed, and the target height according to the correlation between the third collision buffer area and the sixth collision buffer area comprises: An interpolation calculation is performed on the third collision buffer area and the sixth collision buffer area to obtain the target collision buffer area corresponding to the attribute information corresponding to the target longitudinal distance, the target relative speed, and the target height.

6. The method according to claim 1, characterized in that The attribute information includes a target longitudinal distance and a target relative speed of the target obstacle relative to the target vehicle, and acquiring the attribute information of the target obstacle corresponding to the target vehicle includes: Acquire first position information and first speed information corresponding to the target obstacle; Acquire second position information and second speed information corresponding to the target vehicle; determining the target longitudinal distance according to the relationship between the first position information and the second position information; The target relative speed is determined according to the relationship between the first speed information and the second speed information.

7. A path planning device, characterized in that: include: An acquisition module, used to acquire attribute information of a target obstacle corresponding to a target vehicle; The attribute information includes at least one of a target longitudinal distance, a target relative speed, a target lateral distance of the target obstacle relative to the target vehicle, a target perception tracking time for tracking the target obstacle, a target height of the target obstacle, and a target perception confidence of the target obstacle; A determination module, configured to determine a target collision buffer zone corresponding to the target obstacle according to a correspondence between the attribute information and the collision buffer zone corresponding to the obstacle; When the attribute information includes the target longitudinal distance, the target relative speed, and the target height of the target obstacle of the target obstacle relative to the target vehicle, determining the target collision buffer zone corresponding to the target obstacle according to the correspondence between the attribute information and the collision buffer zone corresponding to the obstacle includes: obtaining a three-dimensional interpolation table corresponding to the longitudinal distance, the relative speed, and the obstacle height and the collision buffer zone; determining, in the three-dimensional interpolation table, a first longitudinal distance and a second longitudinal distance adjacent to the target longitudinal distance, a first relative speed and a second relative speed adjacent to the target relative speed, and a first obstacle height and a second obstacle height adjacent to the target height according to the values ​​of the target longitudinal distance, the target relative speed, and the target height; calculating, according to the correlation between the target height and the first obstacle height and the second obstacle height, a first collision buffer zone corresponding to the first longitudinal distance, the first relative speed, and the target height; calculating, according to the correlation between the target height and the first obstacle height and the second obstacle height, a second longitudinal distance and a second longitudinal distance adjacent to the target longitudinal distance, a first relative speed and a second relative speed adjacent to the target relative speed, and a first obstacle height and a second obstacle height adjacent to the target height. a second collision buffer area corresponding to the target longitudinal distance, the first relative speed and the target height; a third collision buffer area corresponding to the target longitudinal distance, the first relative speed and the target height is calculated according to the correlation between the first collision buffer area and the second collision buffer area; a fourth collision buffer area corresponding to the first longitudinal distance, the second relative speed and the target height is calculated according to the correlation between the target height and the first obstacle height and the second obstacle height; a fifth collision buffer area corresponding to the second longitudinal distance, the second relative speed and the target height is calculated according to the correlation between the target height and the first obstacle height and the second obstacle height; a sixth collision buffer area corresponding to the target longitudinal distance, the second relative speed and the target height is calculated according to the correlation between the fourth collision buffer area and the fifth collision buffer area; a target collision buffer area corresponding to the attribute information corresponding to the target longitudinal distance, the target relative speed and the target height is calculated according to the correlation between the third collision buffer area and the sixth collision buffer area; A first generating module, configured to add the target collision buffer zone to the target obstacle to generate a buffer target obstacle; A first solving module, used for constructing a boundary collision constraint according to the buffer target obstacle, and running a preset path planning algorithm to solve the driving path; The first output module is used to output a target path corresponding to the driving path when the driving path is solved successfully.

8. An electronic device, characterized in that: It comprises a memory and a processor, wherein the memory stores computer instructions, and the processor executes the path planning method according to any one of claims 1 to 6 by executing the computer instructions.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the path planning method according to any one of claims 1 to 6.

Images