CN117555340B

CN117555340B - Path planning method and related device

Info

Publication number: CN117555340B
Application number: CN202410047887.3A
Authority: CN
Inventors: 廖江
Original assignee: Beijing Jidu Technology Co Ltd
Current assignee: Beijing Jidu Technology Co Ltd
Priority date: 2024-01-12
Filing date: 2024-01-12
Publication date: 2024-04-09
Anticipated expiration: 2044-01-12
Also published as: CN117555340A

Abstract

The application provides a path planning method and a related device, and relates to the technical field of intelligent driving. The path planning method may include: controlling the unmanned aerial vehicle to simulate the vehicle to fly according to the first planning cruising path; the first planning cruising path is planned under the kinematic constraint condition of the vehicle; under the condition that the real cruising path of the unmanned aerial vehicle deviates from the expected path, the planned cruising path of the unmanned aerial vehicle is adjusted, and a second planned cruising path which deviates to the first direction is obtained; the first direction is opposite to the second direction, and the second direction is the direction of the real cruising path deviating from the expected path; determining a path planning area according to the second planning cruising path and the central line of the road; in the route planning area, the travel route of the vehicle is planned. The technical scheme that this application provided can solve among the prior art vehicle easily deviate from the problem that the road central line was gone.

Description

Path planning method and related device

Technical Field

The present application relates to the field of intelligent driving technologies, and in particular, to the field of path planning technologies, and more particularly, to a path planning method and a related apparatus.

Background

With the intelligent development of vehicles, the intelligent driving function is paid more and more attention to vehicle enterprises. Wherein, the reasonable planning of the driving path of the intelligent driving vehicle is the key place for realizing the intelligent driving function. In the prior art, path planning is generally performed based on a road center line, that is, it is desirable that a vehicle runs as close to the road center line as possible, but in some cases, for example, when the vehicle runs on a road with a large curvature, it may be difficult to run near the road center line according to the planned path due to the characteristics of the vehicle itself.

Disclosure of Invention

Based on the defects and shortcomings of the prior art, the application provides a path planning method and a related device, which can solve the problem that an intelligent driving vehicle in the prior art easily deviates from a central line of a road to run.

According to a first aspect of an embodiment of the present application, there is provided a path planning method applied to a vehicle on which an unmanned aerial vehicle is mounted, the method including:

controlling the unmanned aerial vehicle to simulate the vehicle to fly according to a first planned cruising path; the first planning cruising path is planned under the kinematic constraint condition of the vehicle;

under the condition that the real cruising path of the unmanned aerial vehicle deviates from the expected path, adjusting the planned cruising path of the unmanned aerial vehicle to obtain a second planned cruising path which deviates towards the first direction; the first direction is opposite to a second direction, and the second direction is a direction in which the real cruising path deviates from an expected path;

Determining a path planning area according to the second planning cruising path and the central line of the road; the road center line is the road center line of the lane where the vehicle is located;

and planning a driving path of the vehicle in the path planning area.

According to a second aspect of embodiments of the present application, there is provided a path planning apparatus applied to a vehicle on which an unmanned aerial vehicle is mounted, the apparatus including:

the flight control module is used for controlling the unmanned aerial vehicle to simulate the vehicle to fly according to a first planned cruising path; the first planning cruising path is planned under the kinematic constraint condition of the vehicle;

the path adjustment module is used for adjusting the planned cruising path of the unmanned aerial vehicle to obtain a second planned cruising path which is deviated to the first direction under the condition that the real cruising path of the unmanned aerial vehicle deviates from the expected path; the first direction is opposite to a second direction, and the second direction is a direction in which the real cruising path deviates from an expected path;

the area determining module is used for determining a path planning area according to the second planning cruising path and the central line of the road; the road center line is the road center line of the lane where the vehicle is located;

And the path planning module is used for planning the running path of the vehicle in the path planning area.

According to a third aspect of embodiments of the present application, there is provided a vehicle for implementing the path planning method according to the first aspect.

According to a fourth aspect of embodiments of the present application, there is provided a path planning system, the system comprising: vehicles and unmanned aerial vehicles;

the unmanned aerial vehicle is used for simulating the vehicle to fly under the control of the vehicle;

the vehicle is configured to implement the path planning method according to the first aspect.

According to a fifth aspect of embodiments of the present application, there is provided an electronic device, including: a memory and a processor;

the memory is connected with the processor and used for storing programs;

the processor is configured to implement the path planning method according to the first aspect by running a program in the memory.

According to a sixth aspect of embodiments of the present application, there is provided a storage medium having stored thereon a computer program which, when executed by a processor, implements the path planning method according to the first aspect.

According to a seventh aspect of embodiments of the present application, there is provided a computer program product or a computer program, the computer program product comprising a computer program stored in a computer readable storage medium; a processor of the computer device reads the computer program from the computer readable storage medium, which processor, when executing the computer program, implements the steps of the path planning method according to the first aspect.

In the technical scheme provided by the application, based on the kinematic constraint of the vehicle, the unmanned aerial vehicle is controlled to simulate the vehicle, fly for a section above a road on which the vehicle is to travel in advance, and predict the real travel path of the vehicle. Under the condition that the real cruising path of the unmanned aerial vehicle deviates from the expected path, the planned cruising path of the unmanned aerial vehicle is adjusted aiming at overcoming the deviation from the expected path, and then a path planning area is determined by combining the adjusted planned cruising path and the road center line, and the path planning is carried out in the path planning area. Since the path planning area considers the problem of travel path deviation, the travel path planned in the area has been deviated in the opposite direction in advance, so that the degree of deviation of the vehicle with respect to the center line of the roadway can be reduced even if the vehicle deviates when traveling according to the planned travel path, thereby enabling the vehicle to travel close to the center line of the roadway.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present application, and that other drawings may be obtained according to the provided drawings without inventive effort to a person skilled in the art.

Fig. 1 is a flow chart of a path planning method according to an embodiment of the present application.

Fig. 2 is a schematic diagram of a relationship between a real cruising path and an expected path according to an embodiment of the present application.

Fig. 3 is a schematic diagram of path planning provided in an embodiment of the present application.

Fig. 4 is a block diagram of a path planning apparatus according to an embodiment of the present application.

Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.

Summary of the application

In the prior art, a path planning of an intelligent driving vehicle is generally performed based on a road center line, and the vehicle is expected to run near the road center line as much as possible, for example, a planned running path is generally the road center line when no obstacle (such as other vehicles, pedestrians, roadblocks and the like) exists around the vehicle or the obstacle does not influence the running of the vehicle; when an obstacle affecting the running of the vehicle is present around the vehicle, the obstacle is avoided and the vehicle is also located as close to the center line of the road as possible. However, in some cases, for example, when the vehicle is traveling on a road with a large curvature (such as a hillside road), because the vehicle steering gear is used as an inertia system, there is a certain execution delay and execution deviation, it is difficult to control the vehicle to travel near the center line of the road, and the situation that the vehicle deviates from the center line of the road more and travels outside the center line of the road may cause the vehicle to travel to a side lane or exit the road, and there is a safety hazard. In addition, delays in communication, computational variances in the control modules, etc. can also cause the vehicle to deviate from the center line of the roadway.

In order to solve the foregoing problems, the embodiments of the present application provide a path planning technique, which controls an unmanned aerial vehicle to simulate a vehicle based on kinematic constraints of the vehicle, to fly a section of the vehicle above a road on which the vehicle is to travel in advance, and to predict a real travel path of the vehicle. Under the condition that the real cruising path of the unmanned aerial vehicle deviates from the expected path, the planned cruising path of the unmanned aerial vehicle is adjusted aiming at overcoming the deviation from the expected path, so that the adjusted planned cruising path deviates in the opposite direction, and then a path planning area is determined by combining the adjusted planned cruising path and the road center line, and path planning is carried out in the path planning area. Since the path planning area considers the problem of travel path deviation, the travel path planned in the area has been deviated in the opposite direction in advance, so that the degree of deviation of the vehicle with respect to the center line of the roadway can be reduced even if the vehicle deviates when traveling according to the planned travel path, thereby enabling the vehicle to travel close to the center line of the roadway.

Exemplary method

The embodiment of the application provides a path planning method which is applied to an intelligent driving vehicle (hereinafter simply referred to as a vehicle) carrying an unmanned aerial vehicle, for example, a vehicle which can communicate with the unmanned aerial vehicle and can control the unmanned aerial vehicle to fly. The vehicle has a driving assistance or automatic driving function.

As shown in fig. 1, the method may include the steps of:

step 101: the control drone simulates a vehicle flight according to the first planned cruising path.

The first planned cruising path described herein is adapted to the vehicle, i.e. the path planned for the vehicle in the current environment may be planned by a planning module of the vehicle, and may specifically be planned by the planning module under the kinematic constraint condition of the vehicle. After the planning is completed, the vehicle sends the planned cruising path to the unmanned aerial vehicle.

Alternatively, the first planned cruising path may be derived based on kinematic constraints of the vehicle in the event that there are no obstacles around the vehicle or that the obstacles do not affect the travel of the vehicle.

Optionally, in the case where there is an obstacle around the vehicle that affects the running, the obstacle trajectory may be recombined to obtain the first planned cruising path, that is: the first planned cruising path is planned based on the obstacle trajectory under kinematic constraints of the vehicle. The first planned cruising path needs to meet the condition of avoiding the obstacle.

Alternatively, in order to make the planned cruising path approach the central line of the road, the cruising path may be planned by combining the central line of the road on the basis of the former two cases. The road center line is the road center line of the lane where the vehicle is located.

Because the kinematic constraint of the unmanned aerial vehicle is different from that of the vehicle, compared with the vehicle, the unmanned aerial vehicle has more abundant executable actions, such as up-and-down lifting, 360-degree rotation and the like, so that the unmanned aerial vehicle can be carried out under the kinematic constraint condition of the vehicle when planning the cruising path of the unmanned aerial vehicle in order to simulate the vehicle more truly. The kinematic constraints described herein may include, but are not limited to: and estimating the path pose (namely the position and the direction) of the next moment based on the path pose (namely the position and the direction) of the previous moment of the vehicle. For example, in the case where there is no obstacle around the vehicle or the obstacle does not affect the running of the vehicle, the first planned cruising path may be generated according to the estimated path pose. Under the condition that an obstacle influencing the running of the vehicle exists around the vehicle, a first planning cruising path can be generated by combining the track of the obstacle and the estimated path pose, and the first planning cruising path needs to meet the condition of avoiding the obstacle. For another example, in order to make the planned cruising path approach the road center line, the cruising path may be planned by combining the road center line on the basis of the former two cases.

Alternatively, the kinematic constraint of the vehicle may be referred to as a bicycle kinematic model, which may be represented by three formulas as follows:

（1）

（2）

（3）

In the formulas (1) to (3),、/>and +.>Pose information representing a route point at the next moment of the vehicle, < +.>Can indicate the next time of the vehicleX-axis coordinates of the position +.>Y-axis coordinates, which may represent the position of the vehicle at the next moment,/->Heading angle of next moment of vehicle, +.>Indicating the heading angle of the vehicle at the previous moment. The previous time refers to the time when pose information of a path point at the next time of the vehicle is calculated. />Indicating the speed of the vehicle at the previous moment, +.>Front wheel corner indicating the previous moment of the vehicle, < >>Representing the bearing length of the vehicle.

The control module of the vehicle can control the flight of the unmanned aerial vehicle. The control module can send control instructions to the unmanned aerial vehicle through communication connection between the vehicle and the unmanned aerial vehicle so as to control the unmanned aerial vehicle.

Alternatively, the road center line may be obtained based on a center line identifier on the lane, or may be obtained based on lane lines on both sides of the lane, or may be obtained in other realizations. The center line identification and the lane line can be acquired based on a perception system of the vehicle, specifically can be acquired through an image capturing device in the perception system, more specifically can be acquired through a camera in the image capturing device, namely, the information of the center line identification, the lane line and the like can be obtained through an image shot by the camera. The sensing system described herein refers to a system that collects environmental information (such as other vehicle information, pedestrian information, traffic identification information, etc.) around a vehicle through various sensors and understands the environmental information, and includes at least an image capturing device, such as a camera.

According to the embodiment of the application, the unmanned aerial vehicle can be controlled to simulate the running of the vehicle, a section of the unmanned aerial vehicle flies above a road on which the vehicle is required to run in advance, and the real running path of the vehicle after the running path is obtained according to the road center line planning is predicted. For example, when the vehicle is traveling on a road with a large curvature, the delay and deviation of the execution of the steering device of the vehicle are simulated, and at the same time, the delay of communication and the deviation of the calculation of the control module can be simulated, so that the unmanned aerial vehicle can be imagined to be a vehicle, and the unmanned aerial vehicle is only driven prior to the ground vehicle.

Step 102: and under the condition that the real cruising path of the unmanned aerial vehicle deviates from the expected path, adjusting the planned cruising path of the unmanned aerial vehicle to obtain a second planned cruising path which deviates towards the first direction.

The method and the device can also acquire the real cruising path of the unmanned aerial vehicle and determine whether the real cruising path deviates from the expected path.

The desired path as described herein may refer to a particular path, such as a path that is the same as or similar to the centerline of the roadway, or may refer to a range of paths, such as a range of areas that is determined based on the centerline of the roadway. The desired path is a desired path of the vehicle.

Since the unmanned aerial vehicle is imitating the vehicle to fly, if the real cruising path of the unmanned aerial vehicle deviates from the expected path, the vehicle may deviate from the expected path, and therefore, the planned cruising path of the unmanned aerial vehicle needs to be adjusted to obtain a second planned cruising path which deviates in the first direction. The first direction is opposite to the second direction, and the second direction is a direction in which the real cruising path deviates from the expected path, for example, when the real cruising path deviates to the left of the expected path, a second planned cruising path deviating to the right from the previous first planned cruising path is obtained, and similarly, when the real cruising path deviates to the right of the expected path, a second planned cruising path deviating to the left from the previous second planned cruising path is obtained. The specific offset distance can be determined according to road conditions, such as road curvature; the determination may also be made based on the degree of deviation of the actual cruising path from the desired path, for example, the actual cruising path is deviated 10 cm in the second direction from the deviation of the desired path, and the planned cruising path is deviated a distance greater than or equal to 10 cm in the opposite first direction, although other realizable determinations may be employed.

Step 103: and determining a path planning area according to the second planning cruising path and the central line of the road.

For example, an area between the second planned cruising path and the road centerline may be determined as a path planning area; the area between the second planning cruising path and the central line of the road can be expanded outwards by a certain distance to obtain an area, and the area is determined as a path planning area; the area obtained after the area between the second planned cruising path and the center line of the road converges inwards by a certain distance can also be determined as a path planning area. The expansion and convergence may be performed based on the second planned cruising path, or based on the road center line, or based on the second planned cruising path and the road center line, respectively. Can be specifically set according to actual requirements.

Step 104: in the route planning area, the travel route of the vehicle is planned.

Because the path planning area comprises an area with the direction opposite to the deviation direction of the real cruising track of the unmanned aerial vehicle, when path planning is carried out in the path planning area, a driving path with the direction opposite to the deviation direction of the real cruising track of the unmanned aerial vehicle can be obtained, namely: the travel path planned in this area has been shifted in the opposite direction in advance, so that even if the vehicle is shifted when traveling in accordance with the planned travel path, the degree of shift of the vehicle with respect to the center line of the road can be reduced, thereby enabling the vehicle to travel close to the center line of the road.

In some embodiments, at step 102: in the case that the real cruising path of the unmanned aerial vehicle deviates from the expected path, the method may further include:

in the case that a path exceeding a preset proportion among the real cruising paths of the unmanned aerial vehicle is not within a preset range of the center line of the road, it is determined that the real cruising path deviates from the desired path.

And under the condition that the paths with the smaller than or equal to the preset proportion in the real cruising path of the unmanned aerial vehicle are not in the preset range of the central line of the road, the real cruising path is considered to be in the preset range of the central line of the road. As shown in fig. 2 (a), the area range between two dash-dot lines on both sides of the center line 201 of the road represents the preset range 202, and the real cruise route 203 is completely within the preset range 202 at this time, which means that the deviation of the real cruise route from the center line of the road is small, and the influence on the normal running is small, and at this time, it can be considered that the real cruise route is not deviated from the desired route. The preset ratio may be a value less than 50%, for example, 40%, 30%, etc., and may even be specifically set according to actual requirements.

And if the path exceeding the preset proportion in the real cruising path of the unmanned aerial vehicle is not in the preset range of the central line of the road, the real cruising path is considered to be not in the preset range of the central line of the road. As shown in fig. 2 (b), most of the real cruise paths 203 are not outside the preset range 202, which means that the deviation of the real cruise paths from the center line of the road is large, the influence on normal running is large, and safety accidents are liable to occur, and the real cruise paths are considered to deviate from the desired paths.

It can be understood that, for the case that the real cruising path of the unmanned aerial vehicle is within the preset range of the central line of the road, the technical scheme provided according to the present embodiment may be combined (for example, the "adjusting the planned cruising path of the unmanned aerial vehicle in step 102, obtaining the second planned cruising path that is offset to the first direction" and steps 103 and 104 are continuously executed), so as to perform the path planning of the vehicle, so that the vehicle can travel closer to the central line of the road, and further improve the safety of the vehicle.

According to the method and the device for planning the vehicle travel path, the real cruise path of the unmanned aerial vehicle can be compared with the expected path, so that whether the real cruise path deviates from the expected path or not is determined, the possible travel problem of the vehicle is found in advance, and the planned cruise path of the unmanned aerial vehicle is adjusted to be used for planning the vehicle travel path more reasonably.

In some embodiments, step 101: controlling the drone to simulate the vehicle flying according to the first planned cruising path may include:

in the event that the vehicle is detected to travel to the target type lane, the control drone simulates a vehicle flight according to the first planned cruising path.

The target type lanes described herein may include mountain roads and the like, and may also include: the lane with the curvature radius smaller than the preset radius can be set according to actual requirements, and specifically, the preset radius can be a curvature radius with a larger influence on the vehicle driving deviating from the planned path.

For roads with smaller curvature radius, the problem that the real running path of the vehicle is easily deviated from the planned running path is solved, so that when the vehicle runs on the road, the unmanned aerial vehicle can be started to simulate the running of the vehicle and predict the future running behavior of the vehicle, thereby planning the proper running path in time and improving the running safety of the vehicle.

In some embodiments, the path planning region may be determined from the second planned cruising path of the drone and the centre line of the roadway without an obstacle. In the case of an obstacle, the path planning area may be determined according to the second planned cruising path of the unmanned aerial vehicle, the road center line, and the obstacle trajectory.

For example, an example with an obstacle is illustrated. As shown in fig. 3, first, a second planned cruising path 301, a road centerline 302 (i.e., a grey dashed line in the figure), and an obstacle trajectory 303 may be projected under a global coordinate system, where 305 represents an own vehicle and 306 represents an obstacle vehicle; then, based on the second planned cruising path 301 and the road center line 302, a first region is determined, for example, a first preset distance is extended to the inside and the outside (i.e., a first preset distance is extended to the inside and the outside of the second planned cruising path 301 and a first preset distance is extended to the inside and the outside of the road center line 302) based on the second planned cruising path 301 and the road center line 302, respectively, and then a union of the two region ranges obtained thereby is obtained, which union is the first region; then, a second area is determined based on the obstacle track 303, for example, the second area is obtained by extending a second preset distance to the inner side and the outer side based on the obstacle track 303; finally, the intersection of the first area with the second area is removed, and the remaining area of the first area may be used as a path planning area for the vehicle, and the area between the two black dashed lines in fig. 3 represents the path planning area 307. Of course, this is merely illustrative, and specific implementations may be designed according to actual needs.

It should be noted that, in the embodiment of the present application, when determining the path planning area, the second planned cruising path of the unmanned aerial vehicle is combined, and since the second planned cruising path is obtained by simulating the real running process of the vehicle, the path planning area can be determined more accurately by the second planned cruising path, so the lateral width of the path planning area output by the embodiment of the present application is smaller than the width of the lane where the vehicle is located.

In some embodiments, step 102: the adjusting the planned cruising path of the unmanned aerial vehicle to obtain a second planned cruising path may include:

step A1: the radius of curvature of the lane in which the vehicle is located is determined.

The vehicle may detect the radius of curvature of the road by using sensors and algorithms.

Longitude and latitude coordinates of the current position of the vehicle are provided, for example, by a Global Positioning System (GPS). By recording the vehicle's position data over a period of time and processing and analyzing, the road curvature at the vehicle's location can be estimated. The radius of curvature can be estimated by calculating the rate of change of the vehicle position and the rate of change of direction.

For another example, the vehicle's position, velocity, and direction changes are derived by measuring the vehicle's linear acceleration and angular velocity through an Inertial Measurement Unit (IMU). By analyzing these data, the radius of curvature of the road is calculated.

For another example, visual sensors such as cameras or lidar may be used to capture the geometry and characteristics of the road. By processing and analyzing the image or point cloud data, curvature information of the road can be extracted. For example, feature extraction and curve fitting algorithms may be used to calculate the radius of curvature of the road.

Of course, the above methods can also be combined for use, and can be specifically selected according to actual requirements.

Step A2: a trajectory offset corresponding to the radius of curvature is determined.

In the embodiment of the application, the track offset of the planned cruising track can be determined according to the curvature radius of the lane, and the track offset can be understood as the track correction.

The track offset may be preset, e.g., different track offsets may be preset for lanes of different radii of curvature; or can be calculated by combining the curvature radius of the lane and the preset track offset, for example, the track offset is obtained by a difference algorithm.

For example, the calibration can be performed according to the radius of curvature of the road, for example, when the radius of curvature is 800, the calibration optimal offset is 5cm; when the curvature radius is 600, calibrating the optimal offset to be 10cm; when the curvature radius is 400, the calibrated optimal offset is 15cm; when the radius of curvature is 200, the calibrated optimal offset is 20cm.

The offset value of the curvature radius of the road between the calibration values can be calculated by an interpolation method, and the formula is as follows: l=r_min+ (r_max-r)/(r_max-r_min) × (l_max-l_min), for example, when the current road radius of curvature r is 700, r_max is 800, r_min is 600, l_min is 5m, l_max is 10, and the current offset l is 7.5 calculated by substituting the above formula.

Step A3: and according to the obtained track offset, the planned cruising path of the unmanned aerial vehicle is offset towards the inner side of the central line of the road, and a second planned cruising path is obtained.

In the embodiment of the application, different track offsets can be set for lanes with different curvature radiuses, so that the planned cruising path of the unmanned aerial vehicle can be adjusted more reasonably.

In some embodiments, step 104: in the path planning area, planning a travel path of the vehicle may include:

step B1: sampling is carried out in the path planning area, and a plurality of sampling points are obtained.

The spreading point sampling can be performed in the path planning area to obtain sampling points for path planning.

Step B2: and planning a driving path according to the plurality of sampling points.

In the embodiment of the application, the sampling points for path planning are obtained in the path planning area, and the path planning area is a more accurate path planning area.

Optionally, step B1: sampling in the path planning area to obtain a plurality of sampling points may include:

and in the path planning area, sampling is carried out in the transverse direction at intervals of preset distances along the longitudinal direction, and N sampling points are obtained. N is an integer greater than or equal to 2.

For example, as shown in fig. 3, from the front of the vehicle, 2 points 308 are sampled laterally at each longitudinal level, at a longitudinal spacing of 2m within the path planning area. The lateral spacing of the 2 dots 308 may be 0.3m. The lateral spacing may be determined from the width of the path planning region and is not a fixed value. Therefore, the number of sampling points can be further reduced on the basis of the method, so that the algorithm calculation speed is improved, and the path planning efficiency is further improved.

The longitudinal direction refers to the longitudinal direction of the road, and the transverse direction refers to the transverse direction of the road.

Optionally, step B2: planning the driving path according to the plurality of sampling points may include:

step B21: and respectively acquiring the transverse shortest distance from each sampling point to the target object.

In the case where the surrounding of the vehicle includes an obstacle, the target object may include: a road centerline, a second planned cruising path, and an obstacle trajectory; in the case where no obstacle is included around the vehicle, the target object may include: a road centerline and a second planned cruising path.

Taking the example that the sampling point A in the plurality of sampling points and the target object comprise a road center line, a second planning cruising path and an obstacle track, the steps are as follows: and respectively acquiring the transverse shortest distance from the sampling point A to the central line of the road, the transverse shortest distance from the sampling point A to the second planning cruising path and the transverse shortest distance from the sampling point A to the obstacle track.

Step B22: and scoring each sampling point according to the transverse shortest distance.

The scores described herein are used to indicate the suitability of the sampling points for path planning, i.e. whether they are suitable for path planning. For example, for a sampling point where a collision is likely, it is not suitable for path planning, and for a sampling point where a collision does not occur and a distance from the second planned cruising path and the road center line is closer, it is suitable for path planning.

For the transverse shortest distance to the second planning cruising path and the transverse shortest distance to the central line of the road, the smaller the value is, the better the suitability of the sampling point is, and the planning is facilitated to obtain a better running path; on the contrary, the larger the value is, the worse the suitability of the sampling point is, and the better running path is not beneficial to planning.

For the transverse shortest distance to the obstacle track, the larger the value is, the better the suitability of the sampling point is, and the planning is facilitated to obtain a better running path; on the contrary, the smaller the value is, the worse the suitability of the sampling point is, and the better running path is not beneficial to planning.

Optionally, the embodiment of the present application may take the cost as a criterion of suitability, score the suitability of each sampling point, and include, with the target object: the road center line, the second planned cruising path and the obstacle trajectory are exemplified.

1. The cost calculation formula of the transverse shortest distance from the sampling point to the road center line is as follows:

（4）

in the formula (4) of the present invention,and a cost value representing the transverse shortest distance from the sampling point to the road center line. />Representing the sampling point +.>Representing the closest point of the sampling point projection on the road centerline, the lateral distance between the two is the shortest. The smaller the transverse shortest distance from the sampling point to the central line of the road is, the smaller the cost value is; conversely, the larger the transverse shortest distance from the sampling point to the road center line, the larger the cost value.

2. The cost calculation formula of the transverse shortest distance from the sampling point to the second planning cruising path is as follows:

（5）

In the formula (5) of the present invention,and a cost value representing the shortest lateral distance of the sampling point to the second planned cruising path. />Representing the sampling point +.>Representing the closest point of the sampling point projection on the second planned cruising path, the lateral distance between the two is the shortest. The smaller the transverse shortest distance from the sampling point to the second planned cruising path isThe smaller the cost value; conversely, the larger the transverse shortest distance from the sampling point to the second planned cruising path, the larger the cost value.

3. The cost calculation formula of the transverse shortest distance from the sampling point to the obstacle track is as follows:

（6）

in the formula (6) of the present invention,a cost value representing the shortest lateral distance of the sampling point to the obstacle trajectory. />For sampling points +.>Representing the closest point of the sampling point projection on the obstacle trajectory, the lateral distance between the two is the shortest. />Representing a safe distance threshold. />Representing a collision threshold. />The cost value at the time of collision judgment is represented. />Indicating a penalty factor that is not crashed but is relatively close. The smaller the transverse shortest distance from the sampling point to the obstacle track is, the larger the cost value is; conversely, the larger the transverse shortest distance from the sampling point to the obstacle track, the smaller the cost value.

4. Based on the three scoring results, a comprehensive scoring result of one sampling point is obtained, which is specifically shown in a formula (7):

（7）

Wherein,representing the composite scoring result.

The smaller the cost value is, the better the suitability of the sampling point is; otherwise, the larger the cost value is, the worse the suitability of the sampling point is.

Step B23: and screening a plurality of target sampling points matched with the path planning from the plurality of sampling points according to the scoring result.

In the embodiment of the application, the sampling points can be screened based on the scoring result to obtain the sampling points with better suitability, namely a plurality of target sampling points.

Step B24: and planning a driving path according to the plurality of target sampling points.

In the embodiment of the application, by scoring the suitability of the sampling points, some sampling points which are poor in suitability and are unfavorable for obtaining a high-quality driving path, such as sampling points which are easy to collide and sampling points which are far away from the central line of the road, can be removed. And then, carrying out path planning by using the sampling points with better suitability obtained by screening, so that firstly, a better running path can be planned, and secondly, the sampling points for path planning can be reduced, thereby improving the calculation speed of an algorithm and further improving the path planning efficiency.

Further, step B24: planning the driving path according to the plurality of target sampling points can comprise:

Step B241: and planning to obtain a plurality of driving paths according to the plurality of target sampling points.

Alternatively, a fifth order polynomial may be used to fit points to each other to obtain multiple travel paths.

Step B242: and determining the smoothness of each driving path.

For the fitted driving path fCost of smoothnessThe value design and cost value calculation formula are as follows:

（8）

in the formula (8) of the present invention,representing a ride comfort cost; />、/>、/>Respectively represent the travel path fWeights of first-order, second-order and third-order cost terms, ++>For the first derivative of the driving path, +.>For the second derivative of the driving path, +.>Is the third order derivative of the travel path.

Step B243: and determining the running path with the maximum smoothness as the running path of the vehicle.

In the embodiment of the application, by analyzing the smoothness of each running path, a smoother running path can be screened out as the running path of the vehicle, so that the running stability and the running comfort of the vehicle are improved.

In some embodiments, step B24: planning the driving path according to the plurality of target sampling points can comprise:

step B245: and respectively acquiring the transverse shortest distance from each sampling point to the target object.

In case the path planning information does not comprise an obstacle trajectory, the target object comprises: a road centerline and a second planned cruising path; in case the path planning information comprises an obstacle trajectory, the target object comprises: the road centerline, the second planned cruising path and the obstacle trajectory.

Step B246: and scoring the quality of each sampling point according to the transverse shortest distance to obtain a first scoring result.

Step B247: and planning the driving paths according to the plurality of sampling points to obtain a plurality of driving paths.

Step B248: and scoring the smoothness of each driving path to obtain a second scoring result.

Step B249: and obtaining a final grading result of each driving path according to the second grading result of each driving path and the first grading result of the sampling point included in each driving path.

Step B2410: and screening out the final driving path according to the final grading result of each driving path.

After the quality of the sampling points is scored, the sampling points are not screened (collision points are screened), path planning is performed according to all the sampling points (except the collision points), smoothness of each driving path is scored, and final scores of the corresponding driving paths are obtained according to the scores of each driving path and the scores of the sampling points included in the driving path. In this way, the travel path can be more comprehensively evaluated, so that an optimal travel path is obtained.

As shown in equation (9), the smoothness cost value of a driving path (i.e.) And the cost value of the included sampling point (i.e +.>) And, as a final scoring result.

（9）

Where n represents the number of sampling points that one travel path includes.

In some embodiments, after the planned cruising path of the unmanned aerial vehicle is adjusted to obtain the second planned cruising path that is offset towards the first direction, the path planning area may be determined based on the real cruising path of the unmanned aerial vehicle after flying according to the adjusted planned cruising path (for distinguishing the "real cruising path" in step 102, the "real cruising path" in step 102 may be referred to as the first real cruising path, and the "real cruising path" in this embodiment may be referred to as the second real cruising path) and the road center line.

In this embodiment, the track offset in the first direction may be determined according to the road condition, for example, according to the curvature of the road; the determination may also be made based on the degree of deviation of the actual cruise path from the desired path, although other realizations may be employed.

Alternatively, the trajectory offset in this embodiment may also be a margin on the basis of the previous embodiment, i.e. the planned cruising path of the unmanned aerial vehicle may be offset somewhat more in the first direction, such that the actual cruising path of the unmanned aerial vehicle is also offset somewhat more in the first direction, than in an embodiment in which the path planning area is determined from the second planned cruising path and the centre line of the roadway. In this way, the problem of travel path deviation can be better taken into account in the path planning area determined based on the actual cruising path and the road center line.

Because the unmanned aerial vehicle is imitating the vehicle to run, the real cruising path of the unmanned aerial vehicle is closer to the real running path of the vehicle, so that a more accurate path planning area can be obtained based on the real cruising path and the central line of the road, the sampling space is reduced, the data processing amount is reduced, and the path planning efficiency is improved.

In some embodiments, in the case where lane line information acquired through a perception system of a vehicle does not meet a path planning requirement, an image acquired by an unmanned aerial vehicle may be acquired, and then lane line information and obstacle information are obtained based on the image acquired by the unmanned aerial vehicle and the image acquired by the vehicle; and then, obtaining a lane center line and an obstacle track according to the obtained lane line information and the obstacle information.

The lane line information refers to road line information on both sides of a lane.

In the embodiment of the application, the air exploration capability of the unmanned aerial vehicle can be utilized to acquire the road information which cannot be acquired by the vehicle in advance, so that the vehicle can conduct path planning in advance aiming at the road condition ahead, and reasonable planning of the vehicle aiming at the cruising path of the unmanned aerial vehicle is facilitated. For example, when the vehicle travels on a mountain-climbing highway type road, under a scene (such as a ghost probe scene) in which other obstacles are blocked in the traveling process, under a scene in which a lane line cannot be detected at a passing port, and the like, due to the limited detection distance, when the traveling of the vehicle is possibly affected, the problem that the vehicle deviates from the center line of the road can be solved, and more surrounding environment information can be collected by the unmanned aerial vehicle for path planning of the vehicle and cruise path planning of the unmanned aerial vehicle.

Finally, it should be noted that, the cruising path, the driving path, and the like in the embodiments of the present application refer to specific path information of the unmanned aerial vehicle or the vehicle.

The above is a description of the path planning method provided in the embodiment of the present application.

In summary, in the technical solution provided in the present application, based on the kinematic constraint of the vehicle, the unmanned aerial vehicle is controlled to simulate the vehicle, fly for a certain period above the road on which the vehicle is to travel in advance, and predict the travel path of the vehicle. Under the condition that the real cruising path of the unmanned aerial vehicle deviates from the expected path, the planned cruising path of the unmanned aerial vehicle is adjusted aiming at overcoming the deviation from the expected path, and then a path planning area is determined by combining the adjusted planned cruising path and the road center line, and the path planning is carried out in the path planning area. Since the path planning area considers the problem of travel path deviation, the travel path planned in the area has been deviated in the opposite direction in advance, so that the degree of deviation of the vehicle with respect to the center line of the roadway can be reduced even if the vehicle deviates when traveling according to the planned travel path, thereby enabling the vehicle to travel close to the center line of the roadway.

Exemplary apparatus

Correspondingly, the embodiment of the application also provides a path planning device which is applied to the vehicle carrying the unmanned aerial vehicle.

As shown in fig. 4, the apparatus may include:

a flight control module 401 for controlling the drone to simulate the vehicle flight according to a first planned cruising path.

The first planned cruising path is planned based on a road center line of a lane where the vehicle is located under a kinematic constraint condition of the vehicle.

And the path adjustment module 402 is configured to adjust the planned cruising path of the unmanned aerial vehicle to obtain a second planned cruising path that is offset to the first direction, when the actual cruising path of the unmanned aerial vehicle deviates from the expected path.

The first direction is opposite to a second direction, which is a direction in which the actual cruising path deviates from a desired path.

The area determining module 403 is configured to determine a path planning area according to the second planned cruising path and the road center line.

The road center line is the road center line of the lane where the vehicle is located.

And the path planning module 404 is configured to plan a driving path of the vehicle in the path planning area.

Optionally, the path adjustment module 402 may include:

and the curvature radius determining unit is used for determining the curvature radius of the lane where the vehicle is located.

And the offset determining unit is used for determining the track offset corresponding to the curvature radius.

And the path adjusting unit is used for shifting the planned cruising path of the unmanned aerial vehicle to the inner side of the central line of the road according to the track offset to obtain the second planned cruising path.

Optionally, the path planning module 404 may include:

sampling unit: sampling is carried out in the path planning area, and a plurality of sampling points are obtained.

And the path planning unit is used for planning a driving path according to the plurality of sampling points.

Optionally, the sampling unit may specifically be configured to:

sampling is carried out in the transverse direction along the longitudinal direction at intervals of preset distances in the path planning area, and N sampling points are obtained; n is an integer greater than or equal to 2.

Optionally, the path planning unit may include:

and the distance determination subunit is used for respectively acquiring the transverse shortest distance from each sampling point to the target object.

In the case where an obstacle is included around the vehicle, the target object includes: the road centerline, the second planned cruising path, and an obstacle trajectory; in the case where no obstacle is included around the vehicle, the target object includes: the road centerline and the second planned cruising path.

The scoring subunit is used for scoring each sampling point according to the transverse shortest distance; the score is used to indicate the suitability of the sampling point for path planning.

And the screening subunit is used for screening a plurality of target sampling points matched with the path planning from the plurality of sampling points according to the scoring result.

And the path planning subunit is used for planning a driving path according to the plurality of target sampling points.

Optionally, the path planning subunit may specifically be configured to:

planning to obtain a plurality of driving paths according to the target sampling points; determining smoothness of each driving path; and determining the running path with the maximum smoothness as the running path of the vehicle.

Optionally, the apparatus may further include:

and the deviation determining module is used for determining that the real cruising path deviates from the expected path when the path exceeding the preset proportion in the real cruising path is not in the preset range of the central line of the road.

Optionally, the flight control module 401 may include:

a flight control unit for controlling the unmanned aerial vehicle to simulate the vehicle flight according to a first planned cruising path in case of detecting that the vehicle is traveling to a target type lane; the target type lane includes: lanes with a radius of curvature smaller than a preset radius.

The path planning device provided in this embodiment belongs to the same application conception as the path planning method provided in the foregoing embodiments of the present application, and may execute the path planning method provided in any of the foregoing embodiments of the present application, and has a functional module and beneficial effects corresponding to the execution method. Technical details not described in detail in this embodiment may be referred to the specific processing content of the path planning method provided in the foregoing embodiments of the present application, and will not be described herein again.

Exemplary electronic device

The embodiment of the application also provides an electronic device, as shown in fig. 5, which includes: a memory 500 and a processor 510.

The memory 500 is coupled to the processor 510 for storing a program.

The processor 510 is configured to implement the path planning method in the above embodiment by running the program stored in the memory 500.

Specifically, the electronic device may further include: a communication interface 520, an input device 530, an output device 540, and a bus 550.

The processor 510, the memory 500, the communication interface 520, the input device 530, and the output device 540 are connected to each other by a bus. Wherein:

bus 550 may include a path to transfer information between components of the computer system.

Processor 510 may be a general-purpose processor such as a general-purpose Central Processing Unit (CPU), microprocessor, etc., or may be an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of programs in accordance with aspects of the present invention. But may also be a Digital Signal Processor (DSP), application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components.

Processor 510 may include a main processor, and may also include a baseband chip, modem, and the like.

The memory 500 stores programs for implementing the technical scheme of the present invention, and may also store an operating system and other key services. In particular, the program may include program code including computer-operating instructions. More specifically, the memory 500 may include read-only memory (ROM), other types of static storage devices that may store static information and instructions, random access memory (random access memory, RAM), other types of dynamic storage devices that may store information and instructions, disk storage, flash, and the like.

The input device 530 may include means for receiving data and information entered by a user, such as a keyboard, mouse, camera, scanner, light pen, voice input device, touch screen, pedometer, or gravity sensor, among others.

Output device 540 may include means, such as a display screen, printer, speakers, etc., that allow information to be output to a user.

Communication interface 520 may include devices that use any type of transceiver to communicate with other devices or communication networks, such as an ethernet, a Radio Access Network (RAN), a Wireless Local Area Network (WLAN), etc.

The processor 510 executes the program stored in the memory 500 and invokes other devices that can be used to implement the various steps of the path planning method provided in the above-described embodiments of the present application.

Exemplary computer program product and storage Medium

In addition to the methods and apparatus described above, embodiments of the present application may also be a computer program product comprising computer program instructions which, when executed by a processor, cause the processor to perform the steps in the path planning method described in the embodiments of the present application.

The computer program product may write program code for performing the operations of embodiments of the present application in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server.

Furthermore, embodiments of the present application may also be a storage medium having stored thereon a computer program for executing steps in the path planning method described in the embodiments of the present application by a processor.

For the foregoing method embodiments, for simplicity of explanation, the methodologies are shown as a series of acts, but one of ordinary skill in the art will appreciate that the present application is not limited by the order of acts described, as some acts may, in accordance with the present application, occur in other orders or concurrently. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required in the present application.

The steps in the method of each embodiment of the application can be sequentially adjusted, combined and deleted according to actual needs, and the technical features described in each embodiment can be replaced or combined.

In the embodiments of the present application, the modules, units, and sub-units in the device and the terminal may be combined, divided, and deleted according to actual needs.

In the embodiments provided in the present application, it should be understood that the disclosed terminal, apparatus and method may be implemented in other manners. For example, the above-described terminal embodiments are merely illustrative, and for example, the division of modules or sub-modules is merely a logical function division, and there may be other manners of division in actual implementation, for example, multiple sub-modules or modules may be combined or integrated into another module, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or modules, which may be in electrical, mechanical, or other forms.

Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of functionality in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software unit executed by a processor, or in a combination of the two. The software elements may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

Claims

1. A path planning method applied to a vehicle on which an unmanned aerial vehicle is mounted, the method comprising:

and planning a driving path of the vehicle in the path planning area.

2. The path planning method according to claim 1, wherein said adjusting the planned cruising path of the unmanned aerial vehicle to obtain a second planned cruising path comprises:

determining the curvature radius of a lane where the vehicle is located;

determining a track offset corresponding to the radius of curvature;

And according to the track offset, the planned cruising path of the unmanned aerial vehicle is offset towards the inner side of the central line of the road, and the second planned cruising path is obtained.

3. The path planning method according to claim 1, characterized in that the planning of the travel path of the vehicle in the path planning area includes:

sampling is carried out in the path planning area, and a plurality of sampling points are obtained;

and planning a driving path according to the plurality of sampling points.

4. A path planning method according to claim 3, wherein said sampling in the path planning region to obtain a plurality of sampling points comprises:

5. The path planning method according to claim 3 or 4, wherein the planning of the travel path according to the plurality of sampling points includes:

respectively acquiring the transverse shortest distance from each sampling point to a target object; in the case where an obstacle is included around the vehicle, the target object includes: the road centerline, the second planned cruising path, and an obstacle trajectory; in the case where no obstacle is included around the vehicle, the target object includes: the road centerline and the second planned cruising path;

Scoring each sampling point according to the transverse shortest distance; the score is used for indicating the suitability of the sampling point to a path plan;

screening a plurality of target sampling points matched with the path planning from the plurality of sampling points according to the scoring result;

and planning a driving path according to the target sampling points.

6. The path planning method according to claim 5, wherein the planning of the travel path according to the target sampling point includes:

planning to obtain a plurality of driving paths according to the target sampling points;

determining smoothness of each driving path;

and determining the running path with the maximum smoothness as the running path of the vehicle.

7. The path planning method according to claim 1, characterized in that in case the actual cruising path of the unmanned aerial vehicle deviates from the desired path, the planned cruising path of the unmanned aerial vehicle is adjusted, before the second planned cruising path is obtained, the method further comprises:

and determining that the real cruising path deviates from the expected path in the case that the path exceeding the preset proportion in the real cruising path is not within the preset range of the central line of the road.

8. The path planning method of claim 1, wherein the controlling the drone to simulate the vehicle flying according to a first planned cruising path comprises:

controlling the unmanned aerial vehicle to simulate the vehicle to fly according to a first planned cruising path under the condition that the unmanned aerial vehicle is detected to travel to a target type lane; the target type lane includes: lanes with a radius of curvature smaller than a preset radius.

9. A path planning apparatus applied to a vehicle on which an unmanned aerial vehicle is mounted, the apparatus comprising:

10. A vehicle for implementing a path planning method according to any one of claims 1 to 8.

11. A path planning system, the system comprising: vehicles and unmanned aerial vehicles;

the vehicle is configured to implement the path planning method according to any one of claims 1 to 8.

12. An electronic device, comprising: a memory and a processor;

the memory is connected with the processor and used for storing programs;

the processor is configured to implement the path planning method according to any one of claims 1 to 8 by running a program in the memory.

13. A storage medium having stored thereon a computer program which, when executed by a processor, implements a path planning method according to any one of claims 1 to 8.