Path determination method and device, electronic equipment, storage medium and vehicle

Abstract

The invention relates to a path determination method and device, electronic equipment, a storage medium and a vehicle. Acquiring an environment image of an environment where the vehicle is located; the environment image comprises the vehicle and a target object; acquiring occupancy probabilities corresponding to a plurality of plane grids of the environment image; the occupancy probability represents the probability that the target object passes through the planar grid in a future time period; determining a path selection parameter corresponding to each candidate path in the plurality of candidate paths according to the occupancy probability; the plurality of candidate paths are determined according to operation parameters of the vehicle; determining a target path from the plurality of candidate paths according to the path selection parameters; according to the technical scheme, the target path can be selected based on the occupation probability of the plane grid, the path planning efficiency is improved, interference of other information is reduced, the path planning accuracy is improved, and the driving safety is ensured.

Description

Technical Field

[0001] The present disclosure relates to the field of vehicle control technology, and in particular to a path determination method, device, electronic device, storage medium, and vehicle. Background Art

[0002] The autonomous driving system can include an environmental perception module, a mapping and positioning module, a trajectory prediction module, and a planning and control module. As the vehicle is driving, the autonomous driving system collects information about the vehicle's surroundings and plans its path based on this information.

[0003] In related technologies, it is necessary to process the collected environmental information and then plan the path based on the processed environmental information. However, this processing process is prone to information loss, resulting in low accuracy of the planned path, which affects the driving safety of the vehicle. Summary of the Invention

[0004] To overcome the problems existing in the related art, the present disclosure provides a method, device, electronic device, storage medium and vehicle for determining a path.

[0005] According to a first aspect of an embodiment of the present disclosure, a method for determining a path is provided, the method comprising:

[0006] Acquire an environmental image of the environment in which the vehicle is located; the environmental image includes the vehicle and the target object;

[0007] Obtaining occupancy probabilities corresponding to a plurality of plane grids of the environment image; the occupancy probabilities represent probabilities that the target object will pass through the plane grid within a future time period;

[0008] Determining a path selection parameter corresponding to each candidate path among a plurality of candidate paths according to the occupancy probability; the plurality of candidate paths are determined according to the operating parameters of the vehicle;

[0009] A target path is determined from the multiple candidate paths according to the path selection parameters.

[0010] Optionally, acquiring occupancy probabilities corresponding to a plurality of plane grids of the environment image includes:

[0011] The occupancy probabilities corresponding to the multiple plane grids of the environmental image are obtained through a preset perception model; the preset perception model is used to divide the environmental area corresponding to the environmental image into multiple plane grids and predict the occupancy probability corresponding to each plane grid.

[0012] Optionally, obtaining occupancy probabilities corresponding to a plurality of plane grids of the environment image by using a preset perception model includes:

[0013] Determining the occupancy state and motion flow information of the target object in each of the plane grids using the preset perception model; the occupancy state includes occupied or unoccupied; and the motion flow information represents the speed of the target object in the plane grid;

[0014] The occupancy probability is determined according to the occupancy state and motion flow information.

[0015] Optionally, the path selection parameters include one or more of the following parameters:

[0016] The probability of overlap between the candidate path and the road guide line;

[0017] The probability of collision between the vehicle and the target object in the candidate path; and

[0018] The correct probability corresponding to the plane grid; the correct probability is the probability that the predicted occupancy probability of the plane grid is correct.

[0019] Optionally, the path selection parameter includes a probability of overlap between the candidate path and the road guide line; and determining the path selection parameter corresponding to each candidate path in the plurality of candidate paths according to the occupancy probability includes:

[0020] Using a preset planned path of the vehicle as the road guide line; the preset planned path is pre-set according to the departure position and arrival position of the vehicle;

[0021] The probability of overlap between the preset planned path and the road guide line is determined by a first preset function.

[0022] Optionally, the path selection parameter includes a collision probability between the vehicle and the target object in the candidate path. Determining the path selection parameter corresponding to each candidate path in the plurality of candidate paths according to the occupancy probability includes:

[0023] According to the occupancy probability, a collision probability between the vehicle and the target object in the candidate path is determined by a second preset function.

[0024] Optionally, the path selection parameter includes a correct probability corresponding to the plane grid; and determining the path selection parameter corresponding to each candidate path in the plurality of candidate paths according to the occupancy probability includes:

[0025] Determining a distance between each of the planar grids and a lane centerline; the lane centerline being the centerline of a lane in a preset planned path of the vehicle;

[0026] and determining an angle between the lane centerline and a preset plane coordinate axis; the preset plane coordinate axis is a coordinate axis established based on a plurality of the plane grids;

[0027] According to the distance and the angle, a correct probability of the plane grid corresponding to the grid is determined by a third preset function.

[0028] Optionally, the path selection parameters include a probability of overlap between the candidate path and a road guide line; a probability of collision between the vehicle and the target object in the candidate path; and a probability of correctness corresponding to the plane grid; and determining a target path from the plurality of candidate paths based on the path selection parameters includes:

[0029] Determining a parameter value for each candidate path according to the coincidence probability, a first preset weight value corresponding to the coincidence probability, the collision probability, a second preset weight value corresponding to the collision probability, the correct probability, and a third preset weight value corresponding to the correct probability;

[0030] The candidate path with the highest parameter value is used as the target path.

[0031] According to a second aspect of an embodiment of the present disclosure, a device for determining a path is provided, the device including:

[0032] A first acquisition module is configured to acquire an environmental image of an environment in which the vehicle is located; the environmental image includes the vehicle and a target object;

[0033] A second acquisition module is configured to acquire occupancy probabilities corresponding to a plurality of plane grids of the environment image; the occupancy probabilities represent probabilities that the target object passes through the plane grid in a future time period;

[0034] a first determining module configured to determine, based on the occupancy probability, a path selection parameter corresponding to each candidate path among a plurality of candidate paths; the plurality of candidate paths are determined based on operating parameters of the vehicle;

[0035] The second determining module is configured to determine a target path from the multiple candidate paths according to the path selection parameter.

[0036] Optionally, the second acquisition module is configured to obtain the occupancy probabilities corresponding to multiple plane grids of the environmental image through a preset perception model; the preset perception model is used to divide the environmental area corresponding to the environmental image into multiple plane grids and predict the occupancy probability corresponding to each plane grid.

[0037] Optionally, the second acquisition module is configured to determine the occupancy status and motion flow information of the target object in each of the plane grids through the preset perception model; the occupancy status includes occupied or unoccupied; the motion flow information represents the speed of the target object in the plane grid; and the occupancy probability is determined based on the occupancy status and motion flow information.

[0038] Optionally, the path selection parameters include one or more of the following parameters:

[0039] The probability of overlap between the candidate path and the road guide line;

[0040] The probability of collision between the vehicle and the target object in the candidate path; and

[0041] The correct probability corresponding to the plane grid; the correct probability is the probability that the predicted occupancy probability of the plane grid is correct.

[0042] Optionally, the path selection parameters include the probability of overlap between the candidate path and the road guide line; the first determination module is configured to use the preset planned path of the vehicle as the road guide line; the preset planned path is pre-set according to the departure position and arrival position of the vehicle; and the probability of overlap between the preset planned path and the road guide line is determined by a first preset function.

[0043] Optionally, the path selection parameter includes a collision probability between the vehicle and the target object in the candidate path; and the first determination module is configured to determine the collision probability between the vehicle and the target object in the candidate path through a second preset function according to the occupancy probability.

[0044] Optionally, the path selection parameters include the correct probability corresponding to the plane grid; the first determination module is configured to determine the distance between each of the plane grids and the lane centerline; the lane centerline is the centerline of the lane in the preset planned path of the vehicle; and determine the angle between the lane centerline and a preset plane coordinate axis; the preset plane coordinate axis is a coordinate axis established based on multiple plane grids; based on the distance and the angle, the correct probability corresponding to the plane grid is determined by a third preset function.

[0045] Optionally, the path selection parameters include the probability of overlap between the candidate path and the road guide line; the probability of collision between the vehicle and the target object in the candidate path; and the correct probability corresponding to the plane grid; the second determination module is configured to determine the parameter value of each candidate path based on the overlap probability, the first preset weight value corresponding to the overlap probability, the collision probability, the second preset weight value corresponding to the collision probability, the correct probability and the third preset weight value corresponding to the correct probability; and the candidate path with the highest parameter value is used as the target path.

[0046] According to a third aspect of an embodiment of the present disclosure, there is provided an electronic device, including:

[0047] processor;

[0048] a memory for storing processor-executable instructions;

[0049] The processor is configured to implement the steps of the path determination method provided in the first aspect of the present disclosure when executing.

[0050] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored. When the program instructions are executed by a processor, the steps of the path determination method provided in the first aspect of the present disclosure are implemented.

[0051] According to a fifth aspect of an embodiment of the present disclosure, a vehicle is provided, comprising the electronic device provided by the third aspect of the present disclosure.

[0052] The technical solution provided by the embodiments of the present disclosure may include the following beneficial effects: a target path can be determined from multiple candidate paths through environmental images and corresponding occupancy probabilities, and the target path can be selected based on the occupancy probability of the plane grid, thereby improving the efficiency of path planning, reducing interference from other information, improving the accuracy of path planning, and ensuring driving safety.

[0053] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0055] Figure 1 The figure is a flowchart of a method for determining a path according to an exemplary embodiment.

[0056] Figure 2 is based on Figure 1An exemplary embodiment is shown as a flow chart of a method for path determination.

[0057] Figure 3 is based on Figure 2 An exemplary embodiment is shown as a flow chart of a method for path determination.

[0058] Figure 4 is based on Figure 3 An exemplary embodiment is shown as a flow chart of a method for path determination.

[0059] Figure 5 The figure is a flowchart of a method for determining a path according to an exemplary embodiment.

[0060] Figure 6 It is a block diagram of a device for determining a path according to an exemplary embodiment.

[0061] Figure 7 It is a structural block diagram of a vehicle shown in an exemplary embodiment.

[0062] Figure 8 It is a block diagram of an electronic device according to an exemplary embodiment.

[0063] Figure 9 is a structural block diagram of another vehicle according to an exemplary embodiment. DETAILED DESCRIPTION

[0064] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible embodiments consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

[0065] First, let's introduce the application scenario of this disclosure. This disclosure is applied to the scenario of planning a driving route while a vehicle is in motion. For example, the vehicle can be equipped with an autonomous driving system. The autonomous driving system may include an environmental perception module, a mapping and positioning module, a trajectory prediction module, and a planning and control module.

[0066] While a vehicle is driving, the autonomous driving system collects information about the vehicle's surroundings and plans a route based on this information. Related technologies require processing this collected environmental information before planning a route. However, this processing can easily lead to information loss, resulting in inaccurate planned routes and potentially compromising vehicle safety.

[0067] In order to solve the above problems, the present disclosure provides a path determination method, device, electronic device, storage medium and vehicle; obtaining an environmental image of the vehicle's environment; the environmental image includes the vehicle and a target object; obtaining occupancy probabilities corresponding to multiple plane grids of the environmental image; the occupancy probability represents the probability of the target object passing through the plane grid in a future time period; determining a path selection parameter corresponding to each candidate path in multiple candidate paths based on the occupancy probability; the multiple candidate paths are determined based on the operating parameters of the vehicle; and determining a target path from the multiple candidate paths based on the path selection parameter; through the above technical solution, the target path can be determined from the multiple candidate paths through the environmental image and the corresponding occupancy probabilities, and the target path can be selected based on the occupancy probabilities of the plane grids, thereby improving the efficiency of path planning, reducing interference from other information, improving the accuracy of path planning, and ensuring driving safety.

[0068] Figure 1 FIG. 1 is a flow chart showing a method for determining a path according to an exemplary embodiment. Figure 1 As shown, the method can be applied to a vehicle, and the method can include the following steps.

[0069] S101: Acquire an environmental image of the vehicle's environment.

[0070] The environment image includes the vehicle and the target object. For example, the environment image may include static obstacle information and dynamic obstacle information around the vehicle. For example, the static obstacle information may include lane markings, road boundaries, or traffic signs; the dynamic obstacle information may include pedestrians, cyclists, or other vehicles. The target object may be the dynamic obstacle information.

[0071] In some embodiments, the environment image can be acquired by a vehicle sensor, for example, a camera, a video camera, a laser radar, or a millimeter wave radar, etc., which are not limited here.

[0072] S102: Obtain occupancy probabilities corresponding to multiple plane grids of the environment image.

[0073] The occupancy probability represents the probability of the target object passing through the plane grid in a future time period.

[0074] In some embodiments, the above-mentioned acquisition of the occupancy probabilities corresponding to the multiple plane grids of the environmental image may include: acquiring the occupancy probabilities corresponding to the multiple plane grids of the environmental image through a preset perception model; the preset perception model is used to divide the environmental area corresponding to the environmental image into multiple plane grids, and predict the occupancy probability corresponding to each plane grid.

[0075] For example, the preset perception model can be a model established based on the BEVNet perception architecture. The environmental area corresponding to the environmental image can be an area determined according to a preset boundary length. For example, the preset boundary length can be in the range of 10-50m, such as 10m, 20m, 40m or 50m, etc. The shape of the environmental area can be rectangular, square or diamond, etc., which is not limited here. Among them, the plane grid (Bird Eye View Grid) can be a square area determined based on the environmental area, and the boundary length of the square area can be in the range of 0-5m, such as 0.5m, 1m, 1.5m, 2m or 5m, etc., which is not limited here.

[0076] For example, the environmental area corresponding to the environmental image can be a 40m×20m rectangular area, and the plane grid can be a 0.5m×0.5m square area. In this way, the environmental area around the vehicle can be divided based on the preset perception model, and the environmental area can be refined into multiple plane grids, which facilitates the prediction of the occupancy probability of each plane grid and improves work efficiency.

[0077] In other embodiments, the above-mentioned acquisition of the occupancy probabilities corresponding to multiple plane grids of the environmental image through a preset perception model may include: determining the occupancy status and motion flow information of the target object in each of the plane grids through the preset perception model; the occupancy status includes occupied or unoccupied; the motion flow information represents the speed of the target object in the plane grid; and determining the occupancy probability based on the occupancy status and motion flow information.

[0078] For example, you can Characterizes the occupancy state of the target object in each plane grid; where c represents the target object, t represents time, and i represents the spatial index of the plane grid.

[0079] In some embodiments, the occupancy state of the plane grid can be determined based on the positional relationship between the target object and the plane grid. For example, if it is determined that the target object coincides with the plane grid, the plane grid is determined to be occupied; if it is determined that the target object does not coincide with the plane grid, the plane grid is determined to be unoccupied.

[0080] In other embodiments, the preset perception model may be used to determine the motion flow information of the target object at a preset number of frames in each plane grid.

[0081] For example, the motion flow information of the preset number of frames can be predicted by the preset perception model. The preset number of frames can be in the range of 6-15 frames, for example, 6 frames, 9 frames, 12 frames or 15 frames, etc., which is not limited here.

[0082] And, the formula Characterize the motion flow information of the target object in each plane grid. Indicates the speed of the target object in the x direction of the plane grid, Indicates the speed of the target object in the y direction of the plane grid, and n represents the number of frames of the environment image.

[0083] In some embodiments, the occupancy probability can be determined by a preset probability determination function based on the occupancy state and motion flow information. For example, the preset probability determination function can be obtained by the following method:

[0084]

[0085] in, represents the occupancy probability; Can be The motion flow information is the motion flow information from time i to time j at time t+1. In this way, the occupancy probability of the target object in each plane grid can be determined by the preset function, which can reduce the interference of other information and improve the accuracy of determining the occupancy probability.

[0086] S103: Determine a path selection parameter corresponding to each candidate path among the multiple candidate paths according to the occupancy probability.

[0087] The multiple candidate paths are determined according to the operating parameters of the vehicle.

[0088] In some embodiments, the path selection parameter may include one or more of the following parameters: the probability of overlap between the candidate path and the road guide line; the probability of collision between the vehicle and the target object in the candidate path; and the correct probability corresponding to the plane grid; the correct probability is the probability that the predicted occupancy probability of the plane grid is correct.

[0089] S104: Determine a target path from the multiple candidate paths according to the path selection parameter.

[0090] Through the above technical solution, the target path can be determined from multiple candidate paths through the environmental image and the corresponding occupancy probability. The target path can be selected based on the occupancy probability of the plane grid, which improves the efficiency of path planning, reduces the interference of other information, improves the accuracy of path planning, and ensures driving safety.

[0091] Figure 2 is based on Figure 1 FIG. 1 is a flow chart of a method for determining a path according to an exemplary embodiment of the present invention. Figure 2As shown, the path selection parameter may include the probability of the candidate path overlapping with the road guide line; the above step S103 may include:

[0092] S1031. Use the preset planned path of the vehicle as the road guide line.

[0093] The preset planned path is pre-set according to the departure position and arrival position of the vehicle.

[0094] In some embodiments, the user-set departure and arrival locations may be obtained and combined with preset map information to determine the preset planned route. For example, the preset map information may be electronic map information pre-set by the vehicle.

[0095] S1032: Determine the probability of overlap between the preset planned path and the road guide line using a first preset function.

[0096] For example, the first preset function can be obtained in the following manner:

[0097]

[0098] in, Indicates the vehicle trajectory point SDV on the road guide line i Coordinates of corresponding points; Indicates the vehicle trajectory point SDV on the road guide line i The angle of the corresponding point; θ i The vehicle trajectory point SDV i The angle at the point, m(SDV), represents the spatial index of the plane grid that coincides with the vehicle trajectory point. In this way, the probability of each candidate path coinciding with the road guide line can be determined using a first preset function, and a target path can be determined from the multiple candidate paths based on the probability of coincidence.

[0099] In some embodiments, the path selection parameter may include the collision probability between the vehicle and the target object in the candidate path: determining the path selection parameter corresponding to each candidate path in multiple candidate paths based on the occupancy probability includes: determining the collision probability between the vehicle and the target object in the candidate path through a second preset function based on the occupancy probability.

[0100] For example, the second preset function can be obtained by:

[0101]

[0102] in, Indicates the occupancy probability of the target object in each plane grid; SDV trepresents the speed, acceleration, and turning angle of the vehicle's trajectory point; m(SDV) represents the spatial index of the plane grid that coincides with the vehicle's trajectory point. In this way, the collision probability between the vehicle and the target object can be determined based on the second preset function, and the target path can be determined from multiple candidate paths based on this collision probability.

[0103] Figure 3 is based on Figure 2 FIG. 1 is a flow chart of a method for determining a path according to an exemplary embodiment of the present invention. Figure 3 As shown, the path selection parameter may include the correct probability corresponding to the plane grid; the above step S103 may further include:

[0104] S1033: Determine the distance between each plane grid and the lane centerline.

[0105] The lane centerline may be the centerline of a lane in a preset planned path of the vehicle. For example, the preset planned path may include multiple lanes, so there may be multiple lane centerlines.

[0106] S1034, and determining the angle between the lane centerline and the preset plane coordinate axis.

[0107] The preset plane coordinate axis is a coordinate axis established based on a plurality of the plane grids.

[0108] S1035: Determine the correct probability corresponding to the plane grid using a third preset function according to the distance and the angle.

[0109] For example, the third preset function can be obtained by:

[0110]

[0111] in, The squared difference of the Gaussian probability distribution representing the distance between each plane grid and the lane centerline; The concentration of the von Mises probability distribution representing the angle between the lane centerline and the preset plane coordinate axis; SDV v represents the velocity of the vehicle trajectory point; m(SDV) represents the spatial index of the plane grid that coincides with the vehicle trajectory point. Thus, based on the distance and the angle, a third preset function can be used to determine the correct probability of the plane grid corresponding to the vehicle trajectory point. The candidate paths can then be evaluated based on this correct probability to obtain the target path.

[0112] Figure 4 is based on Figure 3 FIG. 1 is a flow chart of a method for determining a path according to an exemplary embodiment of the present invention. Figure 4As shown, the path selection parameters include the probability of the candidate path overlapping with the road guide line; the probability of the vehicle colliding with the target object in the candidate path; and the correct probability of the plane grid corresponding to the above step S104 may include:

[0113] S1041. Determine the parameter value of each candidate path based on the overlap probability, the first preset weight value corresponding to the overlap probability, the collision probability, the second preset weight value corresponding to the collision probability, the correct probability, and the third preset weight value corresponding to the correct probability.

[0114] S1042: The candidate path with the highest parameter value is used as the target path.

[0115] For example, the parameter value of each candidate path can be determined by a preset path determination function. The preset path determination function can be obtained by linearly summing the overlap probability, the first preset weight value corresponding to the overlap probability, the collision probability, the second preset weight value corresponding to the collision probability, the correct probability, and the third preset weight value corresponding to the correct probability. For example, the preset path determination function can be obtained by:

[0116] f=w1*f1+w2*f2+w3*f3;

[0117] Among them, w1 represents the first preset weight value, f1 represents the coincidence probability, w2 represents the second preset weight value, f2 represents the collision probability, w3 represents the third preset weight value, and f3 represents the third preset function.

[0118] For example, the first, second, or third preset weight values ​​can be set by the user and are not limited herein. The parameter value can represent a score for each candidate path, which can be used to evaluate the quality of each candidate path. In this way, multiple candidate paths can be ranked based on the parameter value to determine a target path, thereby improving the efficiency of path determination.

[0119] Figure 5 FIG. 1 is a flow chart showing a method for determining a path according to an exemplary embodiment. Figure 5 As shown, the method may include the following steps:

[0120] S501: Acquire an environmental image of the vehicle's environment.

[0121] The environment image includes the vehicle and the target object.

[0122] S502: Obtain occupancy probabilities corresponding to multiple plane grids of the environment image through a preset perception model.

[0123] The preset perception model is used to divide the environment area corresponding to the environment image into multiple plane grids and predict the occupancy probability corresponding to each plane grid.

[0124] S503: Determine a path selection parameter corresponding to each candidate path among the multiple candidate paths according to the occupancy probability.

[0125] The path selection parameters include one or more of the following parameters: the probability of overlap between the candidate path and the road guide line; the probability of collision between the vehicle and the target object in the candidate path; and the correct probability corresponding to the plane grid; the correct probability is the probability that the predicted occupancy probability of the plane grid is correct.

[0126] S504. Determine the parameter value of each candidate path based on the overlap probability, the first preset weight value corresponding to the overlap probability, the collision probability, the second preset weight value corresponding to the collision probability, the correct probability, and the third preset weight value corresponding to the correct probability.

[0127] S505: The candidate path with the highest parameter value is used as the target path.

[0128] Through the above technical solution, the target path can be determined from multiple candidate paths through the environmental image and the corresponding occupancy probability. The target path can be selected based on the occupancy probability of the plane grid, which improves the efficiency of path planning, reduces the interference of other information, improves the accuracy of path planning, and ensures driving safety.

[0129] Figure 6 FIG. 1 is a block diagram of a device for determining a path according to an exemplary embodiment. Figure 6 , the apparatus 600 may include a first acquisition module 610, a second acquisition module 620, a first determination module 630 and a second determination module 640;

[0130] The first acquisition module 610 is configured to acquire an environmental image of the environment in which the vehicle is located; the environmental image includes the vehicle and the target object;

[0131] The second acquisition module 620 is configured to acquire occupancy probabilities corresponding to a plurality of plane grids of the environment image; the occupancy probabilities represent the probability that the target object passes through the plane grid in a future time period;

[0132] The first determination module 630 is configured to determine a path selection parameter corresponding to each candidate path in a plurality of candidate paths according to the occupancy probability; the plurality of candidate paths are determined according to the operating parameters of the vehicle;

[0133] The second determination module 640 is configured to determine a target path from the multiple candidate paths according to the path selection parameter.

[0134] Through the above technical solution, the target path can be determined from multiple candidate paths through the environmental image and the corresponding occupancy probability. The target path can be selected based on the occupancy probability of the plane grid, which improves the efficiency of path planning, reduces the interference of other information, improves the accuracy of path planning, and ensures driving safety.

[0135] Optionally, the second acquisition module 620 is configured to obtain the occupancy probabilities corresponding to multiple plane grids of the environmental image through a preset perception model; the preset perception model is used to divide the environmental area corresponding to the environmental image into multiple plane grids, and predict the occupancy probability corresponding to each plane grid.

[0136] Optionally, the second acquisition module 620 is configured to determine the occupancy status and motion flow information of the target object in each plane grid through the preset perception model; the occupancy status includes occupied or unoccupied; the motion flow information represents the speed of the target object in the plane grid; and the occupancy probability is determined based on the occupancy status and motion flow information.

[0137] Optionally, the path selection parameter includes one or more of the following parameters:

[0138] The probability of the candidate path overlapping with the road guide line;

[0139] The probability of collision between the vehicle and the target object in the candidate path; and

[0140] The correct probability corresponding to the plane grid; the correct probability is the probability that the predicted occupancy probability of the plane grid is correct.

[0141] Optionally, the path selection parameters include a probability of overlap between the candidate path and the road guide line; the first determination module 630 is configured to use the preset planned path of the vehicle as the road guide line; the preset planned path is pre-set based on the departure position and arrival position of the vehicle; and the probability of overlap between the preset planned path and the road guide line is determined by a first preset function.

[0142] Optionally, the path selection parameter includes a collision probability between the vehicle and the target object in the candidate path; the first determination module 630 is configured to determine the collision probability between the vehicle and the target object in the candidate path through a second preset function according to the occupancy probability.

[0143] Optionally, the path selection parameter includes the correct probability corresponding to the plane grid; the first determination module 630 is configured to determine the distance between each of the plane grids and the center line of the lane; the lane center line is the center line of the lane in the preset planned path of the vehicle; and, determine the angle between the lane center line and a preset plane coordinate axis; the preset plane coordinate axis is a coordinate axis established based on multiple plane grids; based on the distance and the angle, the correct probability corresponding to the plane grid is determined by a third preset function.

[0144] Optionally, the path selection parameters include the probability of overlap between the candidate path and the road guide line; the probability of collision between the vehicle and the target object in the candidate path; and the correct probability corresponding to the plane grid; the second determination module 640 is configured to determine the parameter value of each candidate path based on the overlap probability, the first preset weight value corresponding to the overlap probability, the collision probability, the second preset weight value corresponding to the collision probability, the correct probability and the third preset weight value corresponding to the correct probability; the candidate path with the highest parameter value is used as the target path.

[0145] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0146] In summary, the present disclosure provides a method, device, electronic device, storage medium and vehicle for path determination; obtaining an environmental image of the vehicle's environment; the environmental image includes the vehicle and a target object; obtaining occupancy probabilities corresponding to multiple plane grids of the environmental image; the occupancy probability represents the probability that the target object will pass through the plane grid in a future time period; determining a path selection parameter corresponding to each candidate path in multiple candidate paths based on the occupancy probability; the multiple candidate paths are determined based on the operating parameters of the vehicle; determining a target path from the multiple candidate paths based on the path selection parameter; through the above technical solution, the target path can be determined from the multiple candidate paths through the environmental image and the corresponding occupancy probabilities, and the target path can be selected based on the occupancy probabilities of the plane grids, thereby improving the efficiency of path planning, reducing interference from other information, improving the accuracy of path planning, and ensuring driving safety.

[0147] The present disclosure also provides a computer-readable storage medium having computer program instructions stored thereon. When the program instructions are executed by a processor, the steps of the path determination method provided by the present disclosure are implemented.

[0148] Figure 7FIG2 is a block diagram illustrating the structure of a vehicle 700 according to an exemplary embodiment. For example, vehicle 700 may be a hybrid vehicle, a non-hybrid vehicle, an electric vehicle, a fuel cell vehicle, or another type of vehicle. Vehicle 700 may be an autonomous vehicle, a semi-autonomous vehicle, or a non-autonomous vehicle.

[0149] Reference Figure 7 Vehicle 700 may include various subsystems, such as an infotainment system 710, a perception system 720, a decision-making control system 730, a drive system 740, and a computing platform 750. Vehicle 700 may also include more or fewer subsystems, and each subsystem may include multiple components. Furthermore, each subsystem and each component of vehicle 700 may be interconnected via wired or wireless means.

[0150] In some embodiments, the infotainment system 710 may include a communication system, an entertainment system, a navigation system, and the like.

[0151] The perception system 720 may include several sensors for sensing information about the environment surrounding the vehicle 700. For example, the perception system 720 may include a global positioning system (which may be a GPS system, a BeiDou system, or other positioning systems), an inertial measurement unit (IMU), a laser radar, a millimeter-wave radar, an ultrasonic radar, and a camera.

[0152] The decision control system 730 may include a computing system, a vehicle controller, a steering system, a throttle, and a braking system.

[0153] The drive system 740 may include components that provide power to the vehicle 700. In one embodiment, the drive system 740 may include an engine, a power source, a transmission system, and wheels. The engine may be an internal combustion engine, an electric motor, an air compression engine, or a combination thereof. The engine is capable of converting energy provided by the power source into mechanical energy.

[0154] Some or all functions of the vehicle 700 are controlled by a computing platform 750. The computing platform 750 may include at least one processor 751 and a memory 752. The processor 751 may execute instructions 753 stored in the memory 752.

[0155] The processor 751 can be any conventional processor, such as a commercially available CPU. The processor can also include a graphics processor (GPU), a field programmable gate array (FPGA), a system on chip (SOC), an application specific integrated circuit (ASIC), or a combination thereof.

[0156] The memory 752 can be implemented by any type of volatile or non-volatile memory device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0157] In addition to instructions 753 , memory 752 may also store data, such as road maps, route information, and vehicle location, direction, speed, etc. The data stored in memory 752 may be used by computing platform 750 .

[0158] In the embodiment of the present disclosure, the processor 751 may execute the instruction 753 to complete all or part of the steps of the above-mentioned path determination method.

[0159] Figure 8 8 is a block diagram of an electronic device 800 according to an exemplary embodiment. For example, the electronic device 800 can be provided as a server. Figure 8 The electronic device 800 includes a processing component 822, which further includes one or more processors, and a memory resource represented by a memory 832 for storing instructions executable by the processing component 822, such as an application. The application stored in the memory 832 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 822 is configured to execute the instructions to perform the above-mentioned path determination method.

[0160] The electronic device 800 may further include a power supply component 826 configured to perform power management of the electronic device 800, a wired or wireless network interface 850 configured to connect the electronic device 800 to a network, and an input / output interface 858. The electronic device 800 may operate based on an operating system stored in the memory 832.

[0161] In another exemplary embodiment, a computer program product is further provided. The computer program product includes a computer program executable by a programmable device, and the computer program has a code portion for executing the above-mentioned path determination method when executed by the programmable device.

[0162] Figure 9 FIG. 1 is a structural block diagram of another vehicle according to an exemplary embodiment. Figure 9 As shown, the vehicle 900 may include the electronic device 800 described above.

[0163] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the present disclosure. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the following claims.

[0164] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for determining a path, characterized in that: The method comprises: Acquire an environmental image of the environment in which the vehicle is located; the environmental image includes the vehicle and the target object; Obtaining occupancy probabilities corresponding to a plurality of plane grids of the environment image; the occupancy probabilities represent probabilities that the target object will pass through the plane grid within a future time period; Determining a path selection parameter corresponding to each candidate path among a plurality of candidate paths according to the occupancy probability; the plurality of candidate paths are determined according to the operating parameters of the vehicle; A target path is determined from the multiple candidate paths according to the path selection parameters.

2. The method according to claim 1, characterized in that The acquiring of occupancy probabilities corresponding to the plurality of plane grids of the environment image includes: The occupancy probabilities corresponding to the multiple plane grids of the environmental image are obtained through a preset perception model; the preset perception model is used to divide the environmental area corresponding to the environmental image into multiple plane grids and predict the occupancy probability corresponding to each plane grid.

3. The method according to claim 2, characterized in that The obtaining of occupancy probabilities corresponding to a plurality of plane grids of the environment image by using a preset perception model includes: Determining the occupancy state and motion flow information of the target object in each of the plane grids using the preset perception model; the occupancy state includes occupied or unoccupied; and the motion flow information represents the speed of the target object in the plane grid; The occupancy probability is determined according to the occupancy state and motion flow information.

4. The method according to claim 1, wherein The path selection parameters include one or more of the following parameters: The probability of overlap between the candidate path and the road guide line; The probability of collision between the vehicle and the target object in the candidate path; and The correct probability corresponding to the plane grid; the correct probability is the probability that the predicted occupancy probability of the plane grid is correct.

5. The method according to claim 4, characterized in that The path selection parameter includes a probability of overlap between the candidate path and the road guide line; and determining the path selection parameter corresponding to each candidate path in the plurality of candidate paths based on the occupancy probability includes: Using a preset planned path of the vehicle as the road guide line; the preset planned path is pre-set according to the departure position and arrival position of the vehicle; The probability of overlap between the preset planned path and the road guide line is determined by a first preset function.

6. The method according to claim 4, characterized in that The path selection parameter includes a collision probability between the vehicle and the target object in the candidate path; and determining the path selection parameter corresponding to each candidate path in the plurality of candidate paths according to the occupancy probability includes: According to the occupancy probability, a collision probability between the vehicle and the target object in the candidate path is determined by a second preset function.

7. The method according to claim 4, characterized in that The path selection parameter includes a correct probability corresponding to the plane grid; and determining the path selection parameter corresponding to each candidate path in the plurality of candidate paths according to the occupancy probability includes: Determining a distance between each of the planar grids and a lane centerline; the lane centerline being the centerline of a lane in a preset planned path of the vehicle; and determining an angle between the lane centerline and a preset plane coordinate axis; the preset plane coordinate axis is a coordinate axis established based on a plurality of the plane grids; According to the distance and the angle, a correct probability of the plane grid corresponding to the grid is determined by a third preset function.

8. The method according to claim 4, characterized in that The path selection parameters include a probability of overlap between the candidate path and a road guide line; a probability of collision between the vehicle and the target object in the candidate path; and a probability of correctness of the plane grid corresponding thereto; and determining a target path from the plurality of candidate paths based on the path selection parameters includes: Determining a parameter value for each candidate path according to the coincidence probability, a first preset weight value corresponding to the coincidence probability, the collision probability, a second preset weight value corresponding to the collision probability, the correct probability, and a third preset weight value corresponding to the correct probability; The candidate path with the highest parameter value is used as the target path.

9. A device for determining a path, characterized in that: The device comprises: A first acquisition module is configured to acquire an environmental image of an environment in which the vehicle is located; the environmental image includes the vehicle and a target object; A second acquisition module is configured to acquire occupancy probabilities corresponding to a plurality of plane grids of the environment image; the occupancy probabilities represent probabilities that the target object passes through the plane grid in a future time period; a first determining module configured to determine, based on the occupancy probability, a path selection parameter corresponding to each candidate path among a plurality of candidate paths; the plurality of candidate paths are determined based on operating parameters of the vehicle; The second determining module is configured to determine a target path from the multiple candidate paths according to the path selection parameter.

10. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to implement the steps of the method according to any one of claims 1 to 8 when executing.

11. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the program instructions are executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

12. A vehicle, characterized in that: The electronic device according to claim 10.

Images