Path planning method and device, unmanned vehicle

Abstract

The present disclosure relates to a path planning method and device, an unmanned vehicle, and a computer storable medium. The path planning method includes: determining a guide line for assisting the driving of the unmanned vehicle according to the navigation path of the unmanned vehicle; determining multiple sampling lines for assisting multi-layer position point sampling according to the guide line, each sampling line corresponding to a layer of position point sampling; based on the current position point of the unmanned vehicle, using vehicle dynamics related information, sampling at least one candidate position point from each sampling line; from multiple candidate position points located on multiple sampling lines, screening multiple target position points that are sequentially reached from the current position point; determining the current frame path of the unmanned vehicle according to the current position point and the multiple target position points. According to the present disclosure, the stability of the planned path can be improved.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, in particular to the field of unmanned driving, and more particularly to a path planning method and device, an unmanned vehicle, and a computer storable medium. Background Art

[0002] At present, autonomous driving equipment is used to automatically transport people or objects from one location to another. The autonomous driving equipment collects environmental information through sensors on the equipment and completes automatic transportation. Unmanned delivery vehicles controlled by autonomous driving technology for logistics transportation have greatly improved the convenience of production and life and saved labor costs. In the field of autonomous driving, path planning is a basic task.

[0003] In the related technology, in the path planning process in the field of autonomous driving, a uniform sampling method is used to obtain candidate position points, and multiple target position points are screened from the candidate position points, and then the current frame path of the autonomous driving device is determined based on the current position point of the autonomous driving device and the multiple target position points. Summary of the invention

[0004] The present disclosure proposes a solution that can improve the stability of the planned path.

[0005] According to a first aspect of the present disclosure, a path planning method for autonomous driving is provided, comprising: determining, based on a navigation path of an unmanned vehicle, a guide line for assisting the driving of the unmanned vehicle; determining, based on the guide line, a plurality of sampling lines for assisting in multi-layer position point sampling, each sampling line corresponding to a layer of position point sampling; based on a current position point of the unmanned vehicle, using vehicle dynamics-related information, sampling at least one candidate position point from each sampling line; screening, from a plurality of candidate position points located on the plurality of sampling lines, a plurality of target position points that are sequentially reached from the current position point; and determining a current frame path of the unmanned vehicle based on the current position point and the plurality of target position points.

[0006] In some embodiments, based on the current position point, using vehicle dynamics related information, sampling from each sampling line to obtain at least one candidate position point includes: for each sampling line, using vehicle dynamics related information, determining at least one reference path with a reference position point corresponding to each sampling line as a starting point, wherein, when each sampling line is a sampling line closest to the current position point, the reference position point is the current position point, and when each sampling line is another sampling line, the reference position point is each candidate position point on a sampling line adjacent to each sampling line and close to the direction of the current position point; and determining at least one candidate position point on each sampling line based on the intersection of each sampling line and the at least one reference path.

[0007] In some embodiments, for the sampling line closest to the current position point, at least one reference path with the current position point as the starting point is determined using vehicle dynamics related information; at least one candidate position point located on the sampling line closest to the current position point is determined based on the intersection of the sampling line closest to the current position point and at least one reference path with the current position point as the starting point; for each other sampling line, at least one reference path with each candidate position point located on the sampling line adjacent to each other sampling line and closest to the current position point as the starting point is determined using the vehicle dynamics related information; at least one candidate position point located on each other sampling line is determined based on the intersection of each other sampling line and at least one reference path with each candidate position point located on the sampling line adjacent to each other sampling line and closest to the current position point as the starting point.

[0008] In some embodiments, the vehicle dynamics related information includes vehicle dynamics attribute information or vehicle motion trajectory information, and using the vehicle dynamics related information to determine at least one reference path with the reference position point corresponding to each sampling line as the starting point includes: using the vehicle dynamics attribute information or the vehicle motion trajectory information to determine at least one reference path with the reference position point corresponding to each sampling line as the starting point.

[0009] In some embodiments, the path planning method further includes: sampling the turning angle range of the unmanned vehicle to obtain multiple reference turning angles, wherein the reference path includes paths under the multiple reference turning angles.

[0010] In some embodiments, based on the current position point of the unmanned vehicle and using vehicle dynamics related information, sampling from each sampling line to obtain at least one candidate position point also includes: for each sampling line, determining the intersection of the previous frame path of the unmanned vehicle and each sampling line as a candidate position point located on each sampling line.

[0011] In some embodiments, the candidate position point on each sampling line is an intersection that satisfies a first preset motion condition, wherein the first preset motion condition includes that the unmanned vehicle orientation difference between the reference position point corresponding to each sampling line and the candidate position point on each sampling line is less than or equal to an unmanned vehicle orientation difference threshold.

[0012] In some embodiments, screening multiple target location points that are reached in sequence from the current location point from multiple candidate location points located on multiple sampling lines includes: determining the multiple target location points using a pathfinding algorithm based on the current location point, the multiple candidate location points located on the multiple sampling lines and preset driving costs, wherein a stopping condition of the pathfinding algorithm includes that the mileage from the current location point to the last target location point is greater than or equal to a mileage threshold.

[0013] In some embodiments, the preset driving cost includes at least one of a smoothness cost and a safety cost, wherein the smoothness cost is positively correlated with the difference in orientation of the unmanned vehicle between the position point currently processed by the pathfinding algorithm and the candidate position point, and the safety cost is negatively correlated with the shortest distance from the line segment between the position point currently processed by the pathfinding algorithm and the candidate position point to an obstacle, and the position point currently processed by the pathfinding algorithm is the current position point or the candidate position point.

[0014] In some embodiments, when the candidate position point includes the intersection of the previous frame path of the unmanned vehicle and each sampling line, the preset driving cost also includes a path similarity cost, and the path similarity cost represents the similarity between the path starting from the position point currently processed by the path finding algorithm and the previous frame path.

[0015] In some embodiments, the path similarity cost is positively correlated with the shortest distance of the path segments between the position point currently processed by the path-finding algorithm and each adjacent position point on the path of the previous frame, or the shortest distance of the path segments between the previous position point of the position point currently processed by the path-finding algorithm and each adjacent position point on the path of the previous frame.

[0016] In some embodiments, screening multiple target location points that are reached in sequence from the current location point from multiple candidate location points located on multiple sampling lines includes: selecting multiple candidate location points that meet a second preset motion condition from multiple candidate location points located on multiple sampling lines, the second preset motion condition including at least one of no collision between location points and candidate location points being within a preset map range; selecting the multiple target location points from the multiple candidate location points that meet the second preset motion condition.

[0017] According to a second aspect of the present disclosure, a path planning device for autonomous driving is provided, comprising: a first determination module, configured to determine a guide line for assisting the driving of the unmanned vehicle according to the navigation path of the unmanned vehicle; a second determination module, configured to determine a plurality of sampling lines for assisting multi-layer sampling according to the guide line, each sampling line corresponding to a layer of sampling; a sampling module, configured to obtain at least one candidate position point from each sampling line by sampling based on the current position point of the unmanned vehicle and using vehicle dynamics-related information; a screening module, configured to screen a plurality of target position points that are sequentially reached from the current position point from a plurality of candidate position points located on the plurality of sampling lines; and a third determination module, configured to determine the current frame path of the unmanned vehicle according to the current position point and the plurality of target position points.

[0018] According to a third aspect of the present disclosure, a path planning device for autonomous driving is provided, comprising: a memory; and a processor coupled to the memory, wherein the processor is configured to execute the path planning method described in any of the above embodiments based on instructions stored in the memory.

[0019] According to a fourth aspect of the present disclosure, there is provided an unmanned vehicle, comprising: a path planning device for autonomous driving as described in any of the above embodiments.

[0020] In some embodiments, the unmanned vehicle further includes: at least one of a positioning module, a navigation module, a perception module and a map module, wherein the positioning module is configured to send the speed of the unmanned vehicle, the position coordinates of the current position point and the direction of the unmanned vehicle to the path planning device; the navigation module is configured to send the navigation path of the unmanned vehicle to the path planning device; the perception module is configured to sense obstacles around the unmanned vehicle and send the sensed obstacle information to the path planning device; the map module is configured to provide map data to the path planning device.

[0021] In some embodiments, the unmanned vehicle further includes: a control module configured to receive a current frame path from the path planning device and control the unmanned vehicle to travel according to the current frame path.

[0022] According to a fifth aspect of the present disclosure, a computer storable medium is provided, on which computer program instructions are stored, and when the instructions are executed by a processor, the path planning method described in any of the above embodiments is implemented.

[0023] In the above embodiment, the stability of the planned path can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The accompanying drawings, which constitute a part of the specification, illustrate embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0025] The present disclosure may be more clearly understood from the following detailed description with reference to the accompanying drawings, in which:

[0026] Figure 1 is a flow chart illustrating a path planning method according to some embodiments of the present disclosure;

[0027] Figure 2 is a schematic diagram illustrating determination of a sampling line according to some embodiments of the present disclosure;

[0028] Figure 3A is a schematic diagram showing the result of path planning according to the path planning method based on uniform sampling;

[0029] Figure 3B is a schematic diagram showing the result of path planning performed by the path planning method according to some embodiments of the present disclosure;

[0030] Figure 4 is a block diagram showing a path planning device according to some embodiments of the present disclosure;

[0031] Figure 5 is a block diagram showing a path planning device according to some other embodiments of the present disclosure;

[0032] Figure 6 is a block diagram illustrating an unmanned vehicle according to some embodiments of the present disclosure;

[0033] Figure 7 is a block diagram showing an unmanned vehicle according to other embodiments of the present disclosure;

[0034] Figure 8 is a side view showing an unmanned vehicle according to some embodiments of the present disclosure;

[0035] Fig. 9 is a block diagram illustrating a computer system for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0036] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present disclosure unless otherwise specifically stated.

[0037] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0038] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present disclosure, its application, or uses.

[0039] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.

[0040] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0041] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0042] Figure 1 is a flow chart illustrating a path planning method according to some embodiments of the present disclosure.

[0043] like Figure 1 As shown, the path planning method for autonomous driving includes: step S110, determining a guide line for assisting the driving of the unmanned vehicle according to the navigation path of the unmanned vehicle; step S120, determining multiple sampling lines for assisting multi-layer position point sampling according to the guide line, wherein each sampling line corresponds to a layer of sampling; step S130, based on the current position point of the unmanned vehicle, using vehicle dynamics related information, sampling at least one candidate position point from each sampling line; step S140, screening multiple target position points that are sequentially reached from the current position point from multiple candidate position points located on multiple sampling lines; step S150, determining the current frame path of the unmanned vehicle according to the current position point and multiple target position points. In some embodiments, the path planning method is performed by a path planning device for autonomous driving.

[0044] In the above embodiment, the guide line matching the navigation path is used as a reference, and the vehicle dynamics related information is used to perform multi-layer sampling of candidate position points from multiple sampling lines. The multi-layer sampling method combining the guide line with the vehicle dynamics related information takes into account the accessibility of the candidate position points by the unmanned vehicle, thereby further improving the stability of the planned path.

[0045] In step S110, according to the navigation path of the unmanned vehicle, a guide line for assisting the driving of the unmanned vehicle is determined. The direction of the guide line is consistent with that of the navigation path, and is used to guide the driving direction of the unmanned vehicle. In some embodiments, the navigation path is a lane-level navigation path, and the guide line matching the navigation path is determined according to the lane indicated by the navigation path. For example, the coordinate points of the center line of the lane indicated by the navigation path are smoothed to obtain the guide line. In some embodiments, the guide line can be constructed based on the Frenet coordinate system. The Frenet coordinate system describes the position of the unmanned vehicle relative to the road. In the Frenet coordinate system, s represents the distance along the road, which is called the ordinate, and d represents the displacement from the longitudinal line, which is called the abscissa.

[0046] In some embodiments, the navigation path can be obtained from a navigation module of the unmanned vehicle.

[0047] In step S120, multiple sampling lines for assisting multi-layer position point sampling are determined based on the guide line, wherein each sampling line corresponds to a layer of sampling. For example, multiple sampling lines start from the current position point of the unmanned vehicle and are arranged in sequence along the direction of the guide line. Multiple sampling lines are perpendicular to the guide line. In some embodiments, adjacent sampling lines have the same spacing in the direction of the guide line.

[0048] Figure 2 is a schematic diagram illustrating determination of a sampling line according to some embodiments of the present disclosure.

[0049] like Figure 2 As shown, after the current position point c of the unmanned vehicle is projected onto the guide line, the mileage value curr_s of the projection point is obtained, thereby determining the position of the projection point on the guide line. According to the preset step length, the mileage value next_s of the sampling reference point with a preset step length from the projection point of the current position point on the guide line can be determined, thereby determining the position of the sampling reference point with a preset step length from the projection point of the current position point on the guide line on the guide line. Figure 2 Only one sampling reference point is shown. Usually, multiple sampling reference points need to be determined, and the mileage values ​​between adjacent sampling reference points differ by a preset step size.

[0050] After the position of the reference sampling point on the guide line is determined, a vertical line that is perpendicular to the guide line and intersects the guide line at the reference sampling point is determined as the sampling line. Figure 2 Only one sampling line is shown, and generally, multiple sampling lines need to be determined to achieve multi-layer sampling.

[0051] In step S130, based on the current position of the unmanned vehicle, at least one candidate position is sampled from each sampling line using vehicle dynamics related information. For example, the current position of the unmanned vehicle can be obtained from a positioning module of the unmanned vehicle.

[0052] In some embodiments, the above step S130 may be implemented as follows.

[0053] First, for each sampling line, at least one reference path starting from the reference position point corresponding to each sampling line is determined using vehicle dynamics related information. When each sampling line is the sampling line closest to the current position point, the reference position point is the current position point. When each sampling line is another sampling line, the reference position point is each candidate position point on the sampling line adjacent to each sampling line and close to the direction of the current position point.

[0054] Then, at least one candidate position point located on each sampling line is determined according to the intersection point between each sampling line and at least one reference path.

[0055] In the above embodiment, the reference path that the unmanned vehicle may travel is determined by using the information related to vehicle dynamics, and the intersection of the reference path and the sampling line is used to implement the process of sampling candidate position nodes from the sampling line. In this way, the path accessibility of the unmanned vehicle in the path planning process is further considered, thereby further improving the stability of the planned path. By improving the path stability, the traffic capacity of unmanned vehicles or autonomous driving vehicles can be improved, which facilitates the downstream control module to track the trajectory, avoid the dragon drawing phenomenon, reduce the misjudgment of other traffic participants, reduce traffic congestion or collisions, and improve the safety of autonomous driving.

[0056] In some embodiments, the above process of sampling candidate position points may be implemented in the following manner.

[0057] First, for the sampling line closest to the current position point, at least one reference path starting from the current position point is determined using vehicle dynamics related information. Then, based on the intersection of the sampling line closest to the current position point and the at least one reference path starting from the current position point, at least one candidate position point located on the sampling line closest to the current position point is determined.

[0058] Then, for each other sampling line, at least one reference path starting from each candidate position point on the sampling line adjacent to each other sampling line and closest to the current position point is determined using vehicle dynamics related information. Further, at least one candidate position point on each other sampling line is determined based on the intersection of each other sampling line and at least one reference path starting from each candidate position point on the sampling line adjacent to each other sampling line and closest to the current position point.

[0059] In some embodiments, the candidate position point on each sampling line is an intersection that satisfies a first preset motion condition. The first preset motion condition includes that the unmanned vehicle orientation difference between the reference position point corresponding to each sampling line and the candidate position point on each sampling line is less than or equal to the unmanned vehicle orientation difference threshold. For example, the unmanned vehicle orientation difference threshold is 90 degrees. The unmanned vehicle orientation difference threshold can also be other values. By limiting the unmanned vehicle orientation difference between the reference position point and the candidate position point, the candidate position points that do not conform to the motion law of the unmanned vehicle can be filtered out, thereby further improving the path accessibility and further improving the path stability.

[0060] In some embodiments, the vehicle dynamics related information includes vehicle dynamics attribute information or vehicle motion trajectory information, and the vehicle dynamics attribute information or vehicle motion trajectory information can be used to determine at least one reference path starting from a reference position point corresponding to each sampling line.

[0061] Taking the vehicle dynamics related information including the vehicle dynamics attribute information such as the preset speed, orientation, turning angle and wheelbase of the unmanned vehicle as an example, at least one reference path starting from the reference position point corresponding to each sampling line can be determined based on the vehicle dynamics attribute information such as the preset speed, orientation, turning angle and wheelbase of the unmanned vehicle. For example, the vehicle motion trajectory information can be determined based on the vehicle dynamics attribute information such as the preset speed, orientation, turning angle and wheelbase of the unmanned vehicle, and then at least one reference path starting from the reference position point corresponding to each sampling line can be determined based on the vehicle motion trajectory information.

[0062] In some embodiments, before determining the reference path, the turning angle range of the unmanned vehicle can be sampled to obtain multiple reference turning angles. The reference path includes paths under multiple reference turning angles. By sampling the turning angles, the stability of the planned path can be improved while avoiding excessive computing power consumption, thereby balancing the relationship between computing power consumption and path stability.

[0063] In some embodiments, the rotation angle range is determined by a preset resolution. Sampling is performed to obtain the unmanned vehicle corner set in, is the minimum turning angle of the unmanned vehicle, is the maximum turning angle of the driverless car.

[0064] Gathering at the corner with driverless car For example, the reference path of the unmanned vehicle at different turning angles can be determined using information related to vehicle dynamics.

[0065] In some embodiments, based on vehicle dynamics-related information including vehicle dynamics attribute information such as the preset speed of the unmanned vehicle, the direction of the unmanned vehicle, the unmanned vehicle turning angle and the unmanned vehicle wheelbase in the sampled unmanned vehicle turning angle set, the vehicle motion trajectory information of the unmanned vehicle is determined according to the relationship between the vehicle dynamics attribute information and the vehicle motion trajectory information.

[0066] For example, the relationship between vehicle dynamics attribute information and vehicle motion trajectory information can be represented by a bicycle model. The functional relationship represented by the bicycle model is

[0067]

[0068] In the above functional relationship, θ is the direction of the unmanned vehicle at the current position, v is the preset speed of the unmanned vehicle, is the set of sampled unmanned vehicle turning angles, and L is the wheelbase of the unmanned vehicle. Taking the coordinates of the current position of the unmanned vehicle as (x, y, θ) as an example, It represents the vehicle motion trajectory information of the unmanned vehicle, that is, the coordinate change of the unmanned vehicle starting from the current position.

[0069] According to the current position of the unmanned vehicle and the vehicle motion trajectory information of the unmanned vehicle, multiple coordinates reflecting the vehicle motion trajectory of the unmanned vehicle at different unmanned vehicle turning angles can be obtained. According to these multiple discretized coordinates, the unmanned vehicle can be determined in the unmanned vehicle turning angle set. Reference path for the unmanned vehicle turning at the corner. arrive Multiple reference paths under Figure 2 The reference trajectories at different turning angles of the unmanned vehicle have different turning radii R, where

[0070] In some embodiments, the vehicle dynamics related information includes vehicle trajectory description information, and the vehicle trajectory description information can be used to determine at least one reference path starting from a reference position point corresponding to each sampling line.

[0071] Still Figure 2 For example, for Figure 2 The candidate locations of a sampling line include P1 to P7. Figure 2 The candidate position points on the sampling line shown constitute a candidate position point set S = {P1, P2, ..., P7, ...}.

[0072] In some embodiments, for each sampling line, the intersection of the previous frame path of the unmanned vehicle and each sampling line can also be determined as a candidate position point on each sampling line. In this way, the relationship between the selection of the target position point on the current frame path and the previous frame path of the unmanned vehicle is considered, thereby further considering the similarity of the path, reducing path jitter, and further improving the stability of the planned path.

[0073] by Figure 2 For example, the intersection of the last frame path of the unmanned vehicle and the sampling line is P8. P8 is also added to the candidate position point set as a candidate position point.

[0074] In step S140 , a plurality of target position points that can be reached in sequence from the current position point are screened from a plurality of candidate position points located on a plurality of sampling lines.

[0075] In some embodiments, a plurality of target locations may be determined using a pathfinding algorithm based on the current location, a plurality of candidate locations on a plurality of sampling lines, and a preset driving cost. The stopping condition of the pathfinding algorithm includes that the mileage from the current location to the last target location is greater than or equal to a mileage threshold. For example, the pathfinding algorithm includes an algorithm for finding the best path, such as the A-star algorithm.

[0076] In some embodiments, a set of candidate location points S and a current location point are used as inputs of a path-finding algorithm, and a preset driving cost is used as a target constraint, so that a plurality of target location points can be determined.

[0077] In some embodiments, the preset driving cost includes at least one of a smoothness cost and a safety cost. The smoothness cost is positively correlated with the difference in orientation of the unmanned vehicle between the position point currently processed by the pathfinding algorithm and the candidate position point. The safety cost is negatively correlated with the shortest distance from the line segment between the position point currently processed by the pathfinding algorithm and the candidate position point to the obstacle. The position point currently processed by the pathfinding algorithm is the current position point or the candidate position point.

[0078] In some embodiments, when the candidate position point includes the intersection of the previous frame path of the unmanned vehicle and each sampling line, the preset driving cost also includes a path similarity cost. The path similarity cost represents the similarity between the path starting from the position point currently processed by the path-finding algorithm and the previous frame path. By reflecting the similarity between the planned current frame path and the previous frame path through the path similarity cost, the path stability can be further improved.

[0079] In some embodiments, taking the preset driving cost including smoothness cost, safety cost and path similarity cost as an example, the preset driving cost is obtained by weighting the smoothness cost, safety cost and path similarity cost. For example, the weight value used for the weighted operation includes a first weight value, a second weight value and a third weight value. Preset driving cost = first weight value × smoothness cost + second weight value × safety cost + third weight value × path similarity cost. The first weight value, the second weight value and the third weight value are set according to actual conditions.

[0080] In some embodiments, the path similarity cost is positively correlated to the shortest distance between the path segments from the position point currently processed by the path-finding algorithm to each adjacent position point on the path of the previous frame, or the shortest distance between the path segments from the previous position point of the position point currently processed by the path-finding algorithm to each adjacent position point on the path of the previous frame.

[0081] In some embodiments, multiple candidate location points that meet the second preset motion condition can be selected from multiple candidate location points located on multiple sampling lines, wherein the second preset motion condition includes at least one of no collision between location points and the candidate location points being located within a preset map range. Then, multiple target location points are selected from the multiple candidate location points that meet the second preset motion condition. The process of selecting multiple target location points from the multiple candidate location points that meet the second preset motion condition can refer to the above-mentioned pathfinding algorithm.

[0082] For example, the obstacle information around the unmanned vehicle or autonomous driving vehicle can be obtained from the perception module of the unmanned vehicle to determine whether the movement between the position points is collision-free. Figure 2 For reference, the path from the current position point c to P1 passes through an obstacle, so the candidate position point P1 will be deleted from the candidate position point set S.

[0083] For example, map data can be obtained from a map module of the unmanned vehicle, and based on a preset map range, it is determined whether the position of the candidate location point in the map data is within the preset map range.

[0084] In step S150, the current frame path of the unmanned vehicle is determined based on the current position point and multiple target position points. In some embodiments, the initial path formed by the current position point and multiple target position points is smoothed to obtain the current frame path of the unmanned vehicle. The current frame path is also called a trajectory, which is composed of a series of trajectory points arranged from first to last according to relative time. The trajectory point information includes but is not limited to coordinates, speed, acceleration, direction, and relative time.

[0085] Figure 3A It is a schematic diagram showing the result of path planning according to the path planning method based on uniform sampling.

[0086] Figure 3B It is a schematic diagram showing the result of path planning according to the path planning method of some embodiments of the present disclosure.

[0087] Figure 3A The figure shows the change of position coordinates of each path point obtained by path planning based on uniform sampling path planning method. Figure 3B The figure shows the change of the position coordinates of each path point obtained by performing path planning according to the path planning method of some embodiments of the present disclosure. The x-axis and the y-axis together constitute the position coordinates of the path point.

[0088] contrast Figure 3A and Figure 3B It can be found that Figure 3A In the results of path planning based on uniform sampling, the path frame jitter is obvious, especially Figure 3A In the area marked by the rectangular box, the position coordinates of the path points planned during the path planning process vary widely and are scattered. Figure 3B In the results of path planning according to the path planning method of some embodiments of the present disclosure, the path frame is relatively more stable, referring to the similar Figure 3A Within the area marked by the rectangular box, the position coordinates of the path points used in the path planning process vary in a small and concentrated range.

[0089] Figure 4 is a block diagram showing a path planning device according to some embodiments of the present disclosure.

[0090] like Figure 4 As shown, the path planning device 41 for autonomous driving includes a first determination module 411 , a second determination module 412 , a sampling module 413 , a screening module 414 and a third determination module 415 .

[0091] The first determination module 411 is configured to determine a guide line for assisting the unmanned vehicle in driving according to the navigation path of the unmanned vehicle, for example, Figure 1 Step S110 is shown.

[0092] The second determination module 412 is configured to determine a plurality of sampling lines for assisting multi-layer sampling according to the guide line, each sampling line corresponding to a layer of sampling, for example, performing the following steps: Figure 1 Step S120 is shown.

[0093] The sampling module 413 is configured to obtain at least one candidate position point from each sampling line based on the current position point of the unmanned vehicle and using the vehicle dynamics related information, for example, by performing the following steps: Figure 1 Step S130 is shown.

[0094] The screening module 414 is configured to screen multiple target positions that can be reached sequentially from the current position from multiple candidate positions on multiple sampling lines, for example, by performing the following steps: Figure 1 Step S140 is shown.

[0095] The third determination module 415 is configured to determine the current frame path of the unmanned vehicle according to the current position point and multiple target position points, for example, by performing the following steps: Figure 1 Step S150 is shown.

[0096] In some embodiments, the third determination module 315 includes an initial path determination module and a path smoothing module. The initial path determination module is configured to determine an initial path formed by a current position point and a plurality of target position points. The path smoothing module is configured to smooth the initial path formed by the current position point and a plurality of target position points to obtain the current frame path of the unmanned vehicle.

[0097] Figure 5 is a block diagram showing a path planning device according to some other embodiments of the present disclosure.

[0098] like Figure 5 As shown, the path planning device 51 for autonomous driving includes a memory 511; and a processor 512 coupled to the memory 511. The memory 511 is used to store instructions for executing the path planning method corresponding to the embodiment. The processor 512 is configured to execute the path planning method in any of the embodiments of the present disclosure based on the instructions stored in the memory 511.

[0099] Figure 6 is a block diagram showing an unmanned vehicle according to some embodiments of the present disclosure.

[0100] like Figure 6 As shown, the unmanned vehicle 6 includes a path planning device 61. The path planning device 61 is configured to execute the path planning method in any embodiment of the present disclosure. For example, the path planning device 61 has the same or similar structure or function as the path planning device 41 or 51.

[0101] In some embodiments, the unmanned vehicle 6 further includes a positioning module 62. The positioning module 62 is configured to send the speed of the unmanned vehicle, the position coordinates of the current position point, and the direction of the unmanned vehicle to the path planning device 61. For example, the speed of the unmanned vehicle is a preset speed.

[0102] In some embodiments, the unmanned vehicle 6 further includes a navigation module 63. The navigation module 63 is configured to send the navigation path of the unmanned vehicle to the path planning device 61.

[0103] In some embodiments, the unmanned vehicle 6 further includes a map module 64. The map module 64 is configured to provide map data to the path planning device 61.

[0104] In some embodiments, the unmanned vehicle 6 further includes a perception module 65. The perception module 65 is configured to perceive obstacles around the unmanned vehicle and send the perceived obstacle information to the path planning device 61. The perception module 65 is also configured to perceive traffic light information and the like.

[0105] In some embodiments, the unmanned vehicle 6 further includes a control module 66. The control module 66 is configured to receive a current frame path from the path planning device 61 and control the unmanned vehicle to travel according to the current frame path.

[0106] Figure 7 is a block diagram showing an unmanned vehicle according to some other embodiments of the present disclosure.

[0107] like Figure 7 As shown, the unmanned vehicle 7 mainly includes four parts: an automatic driving module 71, a chassis module 72, a remote monitoring and streaming module 73 and a cargo box module 74.

[0108] The autonomous driving module 71 includes an autonomous driving sensor and core processing unit (Orin or Xavier module) component 711, a traffic light recognition camera 712, front, rear, left, and right surround view cameras 7131, 7132, 7133, 7134, a multi-line laser radar 714, a positioning module 715 (such as Beidou, GPS, etc.), and an inertial navigation unit 716. The camera can communicate with the autonomous driving module. In order to increase the transmission speed and reduce the wiring harness, GMSL link communication can be used. The autonomous driving sensor and core processing unit (Orin or Xavier module) component 711 includes the path planning device in any of the embodiments of the present disclosure and is configured to execute the path planning method in any of the embodiments of the present disclosure.

[0109] In some embodiments, the autonomous driving module 71 also includes a switch 717 and front, rear, left and right blind spot radars 7181, 7182, 7183, and 7184.

[0110] The chassis module 72 mainly includes a battery 721, a power management device 722, a chassis controller 723, a motor driver 724, and a power motor 725. The battery 721 provides power for the entire unmanned vehicle system. The power management device 722 converts the battery output into different voltage levels that can be used by each functional module and controls power on and off. The chassis controller 723 receives motion instructions from the automatic driving module to control the unmanned vehicle to turn, move forward, move backward, brake, etc. For example, the motion instructions are Figure 6 The control module 66 is shown to be determined based on the current frame path. The chassis module 72 also includes a main battery 726.

[0111] The remote monitoring streaming module 73 is composed of a front monitoring camera 731, a rear monitoring camera 732, a left monitoring camera 733, a right monitoring camera 734 and a streaming module 734. The module transmits the video data collected by the monitoring camera to the background server for viewing by the background operator.

[0112] The cargo box module 74 is a cargo carrying device of the unmanned vehicle, including a delivery cargo box 741. A display interaction module 742 is also provided on the cargo box module 74. The display interaction module 742 is used for the interaction between the unmanned vehicle and the user, and the user can perform operations such as picking up, storing, and purchasing goods through the display interaction module. The type of cargo box can be changed according to actual needs. For example, in a logistics scenario, the cargo box can include multiple sub-boxes of different sizes, which can be used to load goods for delivery. In a retail scenario, the cargo box can be set as a transparent box so that users can intuitively see the products for sale.

[0113] The cargo box module 74 also includes an antenna 743. The chassis module 72 also includes a wireless communication module 727. The wireless communication module 727 communicates with the backend server via the antenna 743, so that the backend operator can remotely control the unmanned vehicle.

[0114] Figure 8 is a side view showing an unmanned vehicle according to some embodiments of the present disclosure.

[0115] like Figure 8 As shown, the unmanned vehicle includes a display interaction module 81, a chassis 82, a left blind spot radar 83, a right blind spot radar 84, a rear blind spot radar 85, a laser radar 86, a right camera 87, and a cargo box 88. The functions of the interaction module 81, the chassis 82, the left blind spot radar 83, the right blind spot radar 84, the rear blind spot radar 85, the laser radar 86, the right camera 87, and the cargo box 88 can be referred to. Figure 7 The description in will not be repeated here.

[0116] Fig. 9 is a block diagram illustrating a computer system for implementing some embodiments of the present disclosure.

[0117] like Fig. 9 As shown, the computer system 90 may be embodied in the form of a general-purpose computing device. The computer system 90 includes a memory 910, a processor 920, and a bus 900 that connects the various system components.

[0118] The memory 910 may include, for example, a system memory, a non-volatile storage medium, etc. The system memory may store, for example, an operating system, an application program, a boot loader, and other programs. The system memory may include a volatile storage medium, such as a random access memory (RAM) and / or a cache memory. The non-volatile storage medium may store, for example, instructions for executing the corresponding embodiment of the path planning method. The non-volatile storage medium may include, but is not limited to, a disk storage, an optical storage, a flash memory, etc.

[0119] The processor 920 can be implemented by a general processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistors, etc. Discrete hardware components. Accordingly, each module such as the judgment module and the determination module can be implemented by a central processing unit (CPU) running instructions in a memory that execute corresponding steps, or can be implemented by a dedicated circuit that executes corresponding steps.

[0120] The bus 900 may use any of a variety of bus architectures, including, but not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MCA) bus, and a Peripheral Component Interconnect (PCI) bus.

[0121] The computer system 90 may also include an input / output interface 930, a network interface 940, a storage interface 950, etc. These interfaces 930, 940, 950, the memory 910, and the processor 920 may be connected via a bus 900. The input / output interface 930 may provide a connection interface for input / output devices such as a display, a mouse, and a keyboard. The network interface 940 may provide a connection interface for various networked devices. The storage interface 950 may provide a connection interface for external storage devices such as a floppy disk, a USB flash drive, and an SD card.

[0122] Here, various aspects of the present disclosure are described with reference to flowcharts and / or block diagrams of methods, devices, and computer program products according to embodiments of the present disclosure. It should be understood that each frame of the flowchart and / or block diagram and the combination of frames can be implemented by computer-readable program instructions.

[0123] These computer-readable program instructions may be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable device to produce a machine, so that the processor executes the instructions to produce means for implementing the functions specified in one or more blocks in the flowchart and / or block diagram.

[0124] These computer-readable program instructions may also be stored in a computer-readable memory, which cause the computer to work in a specific manner to produce an article of manufacture, including instructions for implementing the functions specified in one or more blocks in the flowchart and / or block diagram.

[0125] The present disclosure can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects.

[0126] The path planning method and device, unmanned vehicle, and computer storable medium in the above embodiments can improve the stability of the planned path.

[0127] So far, the path planning method and device, unmanned vehicle, and computer storable medium according to the present disclosure have been described in detail. In order to avoid obscuring the concept of the present disclosure, some details known in the art are not described. Based on the above description, those skilled in the art can fully understand how to implement the technical solution disclosed herein.

Claims

1. A path planning method for autonomous driving, comprising: Determining, according to the navigation path of the unmanned vehicle, a guide line for assisting the unmanned vehicle in driving; According to the guide line, a plurality of sampling lines for assisting multi-layer position point sampling are determined, each sampling line corresponds to a layer of position point sampling, and the plurality of sampling lines are perpendicular to the guide line; Based on the current position point of the unmanned vehicle, using vehicle dynamics related information, sampling from each sampling line to obtain at least one candidate position point, including: for each sampling line, determining the intersection of the previous frame path of the unmanned vehicle and each sampling line as a candidate position point located on each sampling line; Selecting, from a plurality of candidate position points located on a plurality of sampling lines, a plurality of target position points that can be reached in sequence starting from the current position point; The current frame path of the unmanned vehicle is determined according to the current position point and the multiple target position points.

2. The path planning method according to claim 1, wherein: Based on the current position point, using vehicle dynamics related information, sampling from each sampling line to obtain at least one candidate position point includes: For each sampling line, using vehicle dynamics related information, determine at least one reference path starting from a reference position point corresponding to each sampling line, wherein, when each sampling line is a sampling line closest to the current position point, the reference position point is the current position point, and when each sampling line is another sampling line, the reference position point is each candidate position point on a sampling line adjacent to each sampling line and close to the direction of the current position point; At least one candidate position point located on each sampling line is determined according to an intersection point between each sampling line and the at least one reference path.

3. The path planning method according to claim 2, wherein: For a sampling line closest to the current position point, determining at least one reference path starting from the current position point by using vehicle dynamics related information; Determine at least one candidate position point located on the sampling line closest to the current position point according to an intersection of the sampling line closest to the current position point and at least one reference path starting from the current position point; For each other sampling line, using the vehicle dynamics related information, determine at least one reference path starting from each candidate position point on the sampling line adjacent to each other sampling line and closest to the current position point; At least one candidate position point located on each other sampling line is determined according to the intersection of each other sampling line and at least one reference path starting from each candidate position point located on a sampling line adjacent to each other sampling line and closest to the current position point.

4. The path planning method according to any one of claims 1 to 3, wherein: The vehicle dynamics related information includes vehicle dynamics attribute information or vehicle motion trajectory information. Using the vehicle dynamics related information, determining at least one reference path starting from a reference position point corresponding to each sampling line includes: At least one reference path starting from a reference position point corresponding to each sampling line is determined by using the vehicle dynamics attribute information or the vehicle motion trajectory information.

5. The path planning method according to claim 2, further comprising: The turning angle range of the unmanned vehicle is sampled to obtain a plurality of reference turning angles, wherein the reference path includes paths under the plurality of reference turning angles.

6. The path planning method according to claim 2, wherein: The candidate position points on each sampling line are intersection points that satisfy a first preset motion condition, wherein the first preset motion condition includes that the unmanned vehicle orientation difference between the reference position points corresponding to each sampling line and the candidate position points on each sampling line is less than or equal to an unmanned vehicle orientation difference threshold.

7. The path planning method according to claim 1, wherein: From a plurality of candidate position points located on a plurality of sampling lines, screening a plurality of target position points that are sequentially reached from the current position point comprises: The multiple target location points are determined using a pathfinding algorithm based on the current location point, multiple candidate location points on the multiple sampling lines and preset driving costs, wherein a stopping condition of the pathfinding algorithm includes that the mileage from the current location point to the last target location point is greater than or equal to a mileage threshold.

8. The path planning method according to claim 7, wherein: The preset driving cost includes at least one of a smoothness cost and a safety cost, wherein the smoothness cost is positively correlated with the difference in orientation of the unmanned vehicle between the position point currently processed by the pathfinding algorithm and the candidate position point, and the safety cost is negatively correlated with the shortest distance from the line segment between the position point currently processed by the pathfinding algorithm and the candidate position point to an obstacle, and the position point currently processed by the pathfinding algorithm is the current position point or the candidate position point.

9. The path planning method according to claim 8, wherein: In the case where the candidate position point includes the intersection of the previous frame path of the unmanned vehicle and each sampling line, the preset driving cost also includes a path similarity cost, and the path similarity cost represents the similarity between the path starting from the position point currently processed by the path finding algorithm and the previous frame path.

10. The path planning method according to claim 9, wherein: The path similarity cost is positively correlated with the shortest distance of the path segments between the position point currently processed by the path-finding algorithm and each adjacent position point on the path of the previous frame, or the shortest distance of the path segments between the previous position point of the position point currently processed by the path-finding algorithm and each adjacent position point on the path of the previous frame.

11. The path planning method according to claim 1, wherein: From a plurality of candidate position points located on a plurality of sampling lines, screening a plurality of target position points that are sequentially reached from the current position point comprises: Selecting a plurality of candidate position points satisfying a second preset motion condition from a plurality of candidate position points located on a plurality of sampling lines, wherein the second preset motion condition includes at least one of no collision between the position points and the candidate position points being located within a preset map range; The plurality of target position points are selected from a plurality of candidate position points that meet a second preset motion condition.

12. A path planning device for autonomous driving, comprising: A first determination module is configured to determine a guide line for assisting the unmanned vehicle in driving according to the navigation path of the unmanned vehicle; A second determination module is configured to determine, according to the guide line, a plurality of sampling lines for assisting multi-layer sampling, each sampling line corresponds to a layer of sampling, and the plurality of sampling lines are perpendicular to the guide line; The sampling module is configured to obtain at least one candidate position point by sampling from each sampling line based on the current position point of the unmanned vehicle and using the vehicle dynamics related information, including: for each sampling line, determining the intersection point of the previous frame path of the unmanned vehicle and each sampling line as the candidate position point located on each sampling line; A screening module is configured to screen a plurality of target position points that are sequentially reached from the current position point from a plurality of candidate position points located on a plurality of sampling lines; The third determination module is configured to determine the current frame path of the unmanned vehicle based on the current position point and the multiple target position points.

13. A path planning device for automatic driving, comprising: Memory; as well as A processor coupled to the memory, wherein the processor is configured to execute the path planning method according to any one of claims 1 to 11 based on instructions stored in the memory.

14. An unmanned vehicle, comprising: A path planning device for autonomous driving as claimed in claim 12 or 13.

15. The unmanned vehicle according to claim 14, further comprising: At least one of a positioning module, a navigation module, a perception module and a map module, wherein: The positioning module is configured to send the speed of the unmanned vehicle, the position coordinates of the current position point, and the direction of the unmanned vehicle to the path planning device; The navigation module is configured to send the navigation path of the unmanned vehicle to the path planning device; The perception module is configured to perceive obstacles around the unmanned vehicle and send the perceived obstacle information to the path planning device; The map module is configured to provide map data to the path planning device.

16. The unmanned vehicle according to claim 14, further comprising: The control module is configured to receive the current frame path from the path planning device and control the unmanned vehicle to travel according to the current frame path.

17. A computer storable medium having computer program instructions stored thereon, which, when executed by a processor, implement the path planning method according to any one of claims 1 to 11.

Images