CN114506343B

CN114506343B - Track planning method, device, equipment, storage medium and automatic driving vehicle

Info

Publication number: CN114506343B
Application number: CN202210205416.1A
Authority: CN
Inventors: 夏中谱; 潘屹峰; 朱振广
Original assignee: Apollo Intelligent Technology Beijing Co Ltd
Current assignee: Apollo Intelligent Technology Beijing Co Ltd
Priority date: 2022-03-02
Filing date: 2022-03-02
Publication date: 2024-07-16
Anticipated expiration: 2042-03-02
Also published as: CN114506343A

Abstract

The disclosure provides a track planning method, a device, equipment, a storage medium and an automatic driving vehicle, relates to the technical field of artificial intelligence, and particularly relates to the fields of unmanned driving, automatic driving, intelligent traffic and the like. The specific implementation scheme is as follows: determining a first planned track point in a planned path according to the current position of a vehicle and the planned path, wherein the first planned track point is the next planned track point of the current position; determining a plurality of to-be-selected track points corresponding to the first planning track point according to the obstacle information of the current position and the first planning track point; acquiring sampling information of the plurality of track points to be selected; and determining a target track point in the plurality of track points to be selected according to the sampling information of the track points to be selected and the barrier information, and controlling the vehicle to travel towards the target track point. The rapid strain capacity of the vehicle to the environment in track planning is improved.

Description

Track planning method, device, equipment, storage medium and automatic driving vehicle

Technical Field

The disclosure relates to the technical field of artificial intelligence, in particular to a track planning method, a device, equipment, a storage medium and an automatic driving vehicle, which can be used in the fields of unmanned driving, automatic driving, intelligent traffic and the like.

Background

When the autonomous vehicle performs planning of the travel path, it is necessary to sample the track points in the travel space and then plan the travel path for the autonomous vehicle based on the sampled data.

In the related art, for a feasible region to be planned, map data in the feasible region is generally obtained at a starting point, and then a planned path in the feasible region is obtained according to the map data and sampling information of track points in the feasible region, so that an automatic driving vehicle is guided to run according to the planned path.

Because the road conditions in the automatic driving scene are frequently changed, the scheme is difficult to adapt to the changed environment scene, and the quick strain capacity is poor.

Disclosure of Invention

The present disclosure provides a trajectory planning method, apparatus, device, storage medium, and autonomous vehicle.

According to a first aspect of the present disclosure, there is provided a trajectory planning method, comprising:

determining a first planned track point in a planned path according to the current position of a vehicle and the planned path, wherein the first planned track point is the next planned track point of the current position;

determining a plurality of to-be-selected track points corresponding to the first planning track point according to the obstacle information of the current position and the first planning track point;

Acquiring sampling information of the plurality of track points to be selected;

and determining a target track point in the plurality of track points to be selected according to the sampling information of the plurality of track points to be selected and the barrier information, and controlling the vehicle to travel towards the target track point.

According to a second aspect of the present disclosure, there is provided a trajectory planning device comprising:

The system comprises a determining unit, a determining unit and a determining unit, wherein the determining unit is used for determining a first planning track point in a planning path according to the current position of a vehicle and the planning path, and the first planning track point is the next planning track point of the current position;

The processing unit is used for determining a plurality of to-be-selected track points corresponding to the first planning track point according to the obstacle information of the current position and the first planning track point;

the acquisition unit is used for acquiring sampling information of the plurality of track points to be selected;

And the planning unit is used for determining a target track point in the plurality of track points to be selected according to the sampling information of the plurality of track points to be selected and the barrier information, and controlling the vehicle to travel towards the target track point.

According to a third aspect of the present disclosure, there is provided an electronic device comprising:

at least one processor; and

A memory communicatively coupled to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of the first aspect.

According to a fourth aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method of the first aspect

According to a fifth aspect of the present disclosure, there is provided a computer program product comprising: a computer program stored in a readable storage medium, from which it can be read by at least one processor of an electronic device, the at least one processor executing the computer program causing the electronic device to perform the method of the first aspect.

According to a sixth aspect of the present disclosure, there is provided an autonomous vehicle comprising an electronic device according to the third aspect.

The track planning method, the track planning device, the track planning equipment, the storage medium and the automatic driving vehicle are characterized in that first, according to the current position of the vehicle and a planned path, a first planned track point is determined in the planned path, and the first planned track point is the next planned track point of the current position; then determining a plurality of track points to be selected corresponding to the first planning track point according to the barrier information of the current position; after the plurality of track points to be selected are determined, sampling the plurality of track points to be selected to obtain sampling information of the plurality of track points to be selected, so that a target track point can be determined in the plurality of track points to be selected based on the sampling information of the plurality of track points to be selected and the barrier information of the current position, and the vehicle is controlled to travel towards the target track point. In the scheme of the embodiment of the disclosure, when planning the track points, a plurality of sampled track points to be selected can be determined according to the barrier information of the current position to sample, and track planning is performed based on the sampling information and the barrier information of the current position.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.

Drawings

The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

fig. 1 is a schematic view of an application scenario provided in an embodiment of the present disclosure;

fig. 2 is a flow chart of a trajectory planning method according to an embodiment of the present disclosure;

FIG. 3 is a schematic diagram of obtaining a planned path provided by an embodiment of the present disclosure;

fig. 4 is a schematic flow chart of determining a candidate trajectory point according to an embodiment of the present disclosure;

FIG. 5 is a schematic diagram of determining a sampling region provided by an embodiment of the present disclosure;

FIG. 6 is a schematic diagram of a trajectory planning provided by an embodiment of the present disclosure;

FIG. 7 is a schematic diagram of a trajectory planning provided by an embodiment of the present disclosure;

fig. 8 is a schematic structural diagram of a trajectory planning device according to an embodiment of the present disclosure;

Fig. 9 is a block diagram of an electronic device for implementing a trajectory planning method of an embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

In embodiments of the present disclosure, "at least one" means one or more, and "a plurality" means two or more. "and/or" describes the access relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may represent: there are three cases, a alone, a and B together, and B alone, wherein a, B may be singular or plural. In the text description of the present disclosure, the character "/" generally indicates that the front-rear associated object is an or relationship. Furthermore, in the embodiments of the present disclosure, "first", "second", "third", "fourth", "fifth" and "sixth" are only for distinguishing contents of different objects, and have no other special meaning.

The track planning refers to a process of performing track planning in a feasible region of an automatic driving vehicle based on relevant sampling information, barrier information and the like of track points on a road in the feasible region, and controlling the automatic driving vehicle to run according to the planned track.

The process of trajectory planning may be understood, for example, in connection with fig. 1. Fig. 1 is a schematic view of an application scenario provided in an embodiment of the present disclosure, as shown in fig. 1, where a vehicle 10 is at a starting point, and a trajectory planning needs to be performed on the vehicle 10 in a feasible region.

The feasible region is a traveling space of the vehicle 10, and may be represented by S, s= (X, Y, H, V), where X represents a range of an abscissa in the feasible region S, Y represents a range of an ordinate in the feasible region S, X and Y collectively represent a coordinate range of the feasible region S, H represents a vehicle orientation range in the feasible region S, and V represents a speed range in the feasible region S. That is, the feasible region includes not only the coordinate range in which the vehicle 10 is allowed to travel, but also the heading range and the speed range in which the vehicle 10 travels. The coordinate ranges, heading ranges, and speed ranges corresponding thereto may be different at different locations within the feasible region S, and the associated range requirements may need to be met when the vehicle 10 is traveling in a region on the feasible region S. For example, if a certain area within the selectable area S requires a speed limit of 60km/h, the traveling speed of the vehicle 10 cannot be greater than 60km/h if the vehicle 10 travels to that area.

In the track planning process, track points in a feasible region need to be sampled, and the sampling process is the basis of track planning. Taking sampling in the feasible region as an example, the feasible region can be divided according to a certain method, so that a plurality of track points are acquired in the feasible region. After the plurality of track points are acquired, the plurality of track points can be sampled to obtain sampling information of the track points, and the sampling information can include a coordinate range, an orientation range, a speed range and the like corresponding to the track points.

In the related art, in a scheme for performing track planning based on track sampling, track points in the whole feasible region are generally sampled at the beginning to obtain sampling information of the track points. Then, road-related information in the feasible region, including, for example, information of intersections, the number of lanes, and the like in the feasible region, and obstacle information, including, for example, information of the number, position, size, type, and the like of obstacles, are acquired based on the high-precision map.

After the sampling information, the road related information and the obstacle information of the track points are obtained, a running track of the vehicle in a feasible area can be planned for the vehicle according to the road related information, the obstacle information and the sampling information of the track points, and the vehicle is controlled to run according to the planned running track.

The scheme is a one-time planning process, namely the track sampling process can be completed only once, the track planning time consumption is low, but the obstacle information on the road changes at any time, and the scheme is easy to cause slow response of the vehicle and can not realize rapid strain in a changing scene. Generally, track planning is required to be performed in real time to realize rapid strain of a vehicle aiming at a changed scene, but when track planning is performed in real time, track point sampling is required to be performed on the whole feasible region, so that the driving track point of the next frame is determined according to obstacle information and road related information acquired in real time. The rapid strain capacity of the scheme is good, but the space dimension of sampling is high, and the solution is very time-consuming.

Aiming at the technical problems, the present disclosure provides the following technical ideas: for a feasible region to be planned, firstly determining a planned path, then determining a track point to be selected according to the obstacle information of the current position of the vehicle and the planned path for sampling, finally determining a target track point of the current position, and controlling the vehicle to drive to the target track point.

On the basis of the above description, the track planning method provided by the present disclosure is described below in conjunction with specific embodiments. The execution body of each embodiment in the present disclosure may be, for example, a device having a data processing function, such as a server, a processor, a microprocessor, or a chip, and the specific execution body of each embodiment in the present disclosure is not limited, and may be selected and set according to actual needs, so long as the device having a data processing function can be used as the execution body of each embodiment in the present disclosure.

First, referring to fig. 2, fig. 2 is a schematic flow chart of a trajectory planning method according to an embodiment of the disclosure, as shown in fig. 2, the method may include:

S21, determining a first planned track point in the planned path according to the current position of the vehicle and the planned path, wherein the first planned track point is the next planned track point of the current position.

The execution body of the embodiment of the present disclosure may be, for example, a server on a vehicle, a power amplifier, or other devices with a certain data processing capability, and in the following embodiment, a server on a vehicle will be described as an example. The server may acquire the current position of the vehicle and then plan the travel track for the vehicle.

The planned path in the embodiment of the present disclosure is a path determined before the vehicle travel track is planned. When the vehicle is located at the starting point, a feasible region of the vehicle from the starting point may be divided to obtain a plurality of track points, where the track points represent a part of the feasible region. And then, carrying out track sampling on a plurality of track points in the feasible region, and determining a planned path according to track sampling information of the track points and the state of the vehicle when the vehicle is at the starting point.

The planned path is a path obtained from data such as current obstacle information, map data of a feasible region, track sampling information of track points and the like when the vehicle is located at the starting point, and is a current theoretically optimal running path. The planned path comprises a plurality of planned track points, and the planned track points correspond to one-time track point planning of the vehicle.

The first planned track point is one of a plurality of planned track points of the planned path, and the first planned track point is the next planned track point of the current position, namely if the vehicle runs at the current position according to the plan of the planned path, the server controls the vehicle to run to the first planned track point.

S22, determining a plurality of candidate track points corresponding to the first planning track point according to the obstacle information of the current position.

After the first planned track point is determined, the obstacle information of the current position can be acquired, and then a plurality of to-be-selected track points corresponding to the first planned track point are determined according to the obstacle information of the current position.

The trajectory point to be selected is the next possible trajectory point of the current position, and the obstacle information of the current position may include, for example, a position of the obstacle acquired by the vehicle at the current position, a type of the obstacle, a size of the obstacle, and the like. Because the obstacle information is changed in real time, in the embodiment of the disclosure, the obstacle information of the current position is obtained in real time when the track planning is performed, so that a plurality of track points to be selected are determined according to the obstacle information of the current position.

S23, acquiring sampling information of a plurality of track points to be selected.

After determining a plurality of to-be-selected track points, track sampling is required to be carried out on the plurality of to-be-selected track points, so that sampling information of the plurality of to-be-selected track points is obtained. The sampling information of the track point to be selected may include, for example, a coordinate range of the track point to be selected, a vehicle orientation range of the track point to be selected, an allowable speed range of the track point to be selected, and the like.

S24, determining target track points in the plurality of track points to be selected according to sampling information and barrier information of the plurality of track points to be selected, and controlling the vehicle to travel towards the target track points.

After the sampling information of the plurality of track points to be selected and the barrier information of the current position are obtained, a target track point can be determined according to the sampling information of the plurality of track points to be selected and the barrier information, and the target track point is one of the plurality of track points to be selected.

The target track point is a track point suitable for the driving of the vehicle, and needs to be comprehensively determined according to the sampling information and the obstacle information of the track point to be selected. For example, it is possible to determine which obstacles are included on the path from the current position to the locus point to be selected, and the size, type, movement condition, and the like of the obstacles, select the locus point to be selected that meets the requirement of the sampling information and can avoid the obstacles as the target locus point in combination with the information of the orientation range, the allowable speed range, and the like in the sampling information, and control the vehicle to travel toward the target locus point.

According to the track planning method provided by the embodiment of the disclosure, first, a first planned track point is determined in a planned path according to the current position of a vehicle and the planned path, wherein the first planned track point is the next planned track point of the current position; then determining a plurality of track points to be selected corresponding to the first planning track point according to the barrier information of the current position; after the plurality of track points to be selected are determined, sampling the plurality of track points to be selected to obtain sampling information of the plurality of track points to be selected, so that a target track point can be determined in the plurality of track points to be selected based on the sampling information of the plurality of track points to be selected and the barrier information of the current position, and the vehicle is controlled to travel towards the target track point. In the scheme of the embodiment of the disclosure, when planning the track points, a plurality of sampled track points to be selected can be determined according to the barrier information of the current position to sample, and track planning is performed based on the sampling information and the barrier information of the current position.

Based on the above description, the track planning method provided in the present disclosure is further described in detail below with reference to the accompanying drawings.

In one section of track planning, real-time planning is required based on the current position of the vehicle and the planned path, so that determining the planned path is a precondition for track planning. The process of determining the planned path is first described in connection with fig. 3.

Fig. 3 is a schematic diagram of acquiring a planned path according to an embodiment of the present disclosure, please refer to fig. 3, in which a vehicle is initially located at a starting point O, and a feasible region from the starting point O is illustrated in fig. 3, and a driving track of the vehicle in the feasible region from the starting point O needs to be planned.

Before track planning, the feasible region may be divided to obtain corresponding sub-regions, where the dividing manner may include, for example, grid division, and so on. Taking a grid division method as an example, a plurality of subareas are obtained after the feasible region is subjected to grid division, and then the central point of the subareas is used as the track point of the subareas, so that a plurality of track points in the feasible region are obtained.

In the embodiment of the disclosure, the feasible region can be divided at equal intervals in the horizontal direction, so that a plurality of groups of track points are obtained, and the horizontal coordinates of each group of track points are relatively similar. For example, in fig. 3, a track point A1, a track point A2, a track point A6 are a set of track points, a track point B1, a track point B2, a track point B6 are a set of track points, and a track point C1, a track point C2, a track point C6 are a set of track points.

When the vehicle is at the starting point O, a plurality of track points in the feasible region may be sampled to obtain sampling information of the plurality of track points, where the sampling information may include, for example, information of a position range, an orientation range, a speed range, and the like of the track points.

Then, the server may acquire map data of the feasible region and initial obstacle information, wherein the map data may include, for example, data of lanes, traffic lights, intersections, etc. of the feasible region, and the map data may be acquired according to a high-precision electronic map. The initial obstacle information is obstacle information acquired from a device such as a sensor on the vehicle when the vehicle is at the start O, and may include, for example, the position, size, type (e.g., static or dynamic) of the obstacle, and the like.

After the map data and the initial obstacle information of the feasible region are acquired, a planned path may be acquired according to the sampling information of the plurality of track points, the map data and the initial obstacle information. The method for obtaining the planned path may include, for example, a dynamic planning method, an a-star method, and the like, which are not described herein.

In the embodiment of the present disclosure, the planned path may be represented by τ= [ (t _i,x_i,y_i,h_i,v_i), i=1, 2,3, ], n ], where t _j is a future moment, x _i is an abscissa of the planned track point in the planned path at the moment t _i, y _i is an ordinate of the planned track point at the moment t _i, x _i and y _i jointly reflect the position of the planned track point at the moment t _i, h _i is the planned direction of the planned track point, v _i is the planned speed of the planned track point, and n is the number of the planned track points in the planned path. In fig. 3, one possible planned trajectory is illustrated, namely a planned trajectory from the start point O to the trajectory point A4, the trajectory point B4, the trajectory point C5 in this order.

The planned track is only an optimal track determined according to the related information acquired from the starting point, and because the obstacle information in the feasible region is dynamically changed, the obstacle information of the current position needs to be acquired in real time in the track planning process, and the track planning is realized by combining the planned path. Referring to fig. 3, when the vehicle is at the starting point O, since the planned path is determined according to the initial obstacle information, which is the obstacle information acquired in real time by the vehicle at the starting point O, the map data, and the sampling information of the trajectory points, the vehicle can travel according to the plan of the planned path at this time. For example, in fig. 3, the vehicle may travel to track point A4 according to the planned path. In the subsequent trajectory planning, planning may be performed according to the current position of the vehicle.

In the embodiment of the disclosure, after determining the target track point according to the current position of the vehicle and controlling the vehicle to travel to the target track point, completing track planning of the current frame, the vehicle enters track planning of the next frame, the target track point at the moment becomes the current position of the new vehicle, and then the planning and planning process is continuously repeated. The implementation of the track planning process per frame of the vehicle is similar, and in the following embodiments, a track planning process per frame of the vehicle will be described.

First, a process of determining a candidate trajectory point will be described with reference to fig. 4, and fig. 4 is a schematic flow chart of determining a candidate trajectory point according to an embodiment of the disclosure, as shown in fig. 4, including:

s41, track information of the vehicle from a first position to a current position is acquired, wherein the first position is the position above the current position.

The first position is the position above the current position, the vehicle performs the track planning of the previous frame at the first position, and the current position is the target track point when the vehicle is positioned at the first position, so that the vehicle is controlled to travel towards the current position. After traveling to the current position, the current frame trajectory planning is required.

Since the current position is determined as the target track point corresponding to the first position in the track planning of the previous frame, the server controls the vehicle to travel from the first position to the current position, so that a track from the first position to the current position is formed. When track planning is performed, not only the position of the target track point of the running track is planned, but also how to control the running of the vehicle to the target track point is planned, for example, setting the direction and speed of the vehicle to the target track point, and the information of the direction, the speed and the like is track information.

In the embodiment of the disclosure, when the track planning of the current frame is performed, track information of the vehicle from the first position to the current position is acquired, where the track information of the first position to the current position may include information such as an orientation, coordinates, a speed, etc. of the vehicle in a process from the first position to the current position, and may also include obstacle information of the vehicle in the first position, etc.

S42, determining a plurality of track points to be selected according to the track information, the obstacle information and the first planning track point.

After track information of the vehicle from the first position to the current position is acquired, a plurality of track points to be selected are determined according to the track information, the obstacle information and the first planning track point. Optionally, the plurality of track points to be selected are track points in a certain range near the first planned track point. By combining the first planning track point with the obstacle information of the current position and the track information from the first position to the current position, a smaller range can be determined in the whole feasible region, and the track point to be selected is determined to sample in the smaller range, so that the calculation amount of sampling can be reduced, and the time consumption of track planning is reduced.

Specifically, first, according to track information and barrier information of a vehicle from a first position to a current position, sampling parameters corresponding to a first planned track point are obtained, wherein the sampling parameters are used for indicating a sampling range corresponding to the first planned track point. After determining the sampling parameters, a plurality of track points to be selected may be determined according to the sampling parameters and the positions of the first planned track points.

In this embodiment, the track planning for the current position may determine a change in traffic environment from the first position to the periphery of the vehicle at the current position based on track information of the vehicle from the first position to the current position and obstacle information of the current position, where the change in traffic environment may include, for example, a change in the number, size, position, direction, and the like of the obstacles. When the change of the traffic environment is large, a large sampling range can be set according to the sampling parameters, and subsequent track sampling is performed so as to improve the success rate of track planning; when the change of the traffic environment is small, a small sampling range can be set according to the sampling parameters, so that the sampling range is reduced on the premise of ensuring the success of the track planning, and the calculated amount of the track planning is reduced.

In one possible implementation, the sampling parameters may include sampling distance and sampling number. After the sampling parameters are obtained according to the track information and the obstacle information, the sampling area of the first planned track point can be determined according to the sampling distance and the position of the first planned track point. Fig. 5 is a schematic diagram of determining a sampling area according to an embodiment of the present disclosure, as shown in fig. 5, taking a first planned track point as a track point B4 as an example, and setting a sampling distance as r, according to the sampling distance r and the position of the track point B4, a sampling area 50 may be determined, where the distances between any point in the sampling area 50 and the track point B4 are all less than or equal to the sampling distance r.

After the sampling area is determined, a plurality of candidate trajectory points may be determined in the sampling area according to the number of samples. Referring to fig. 5, the track point B4 is a first planned track point, and assuming that the sampling information of the track point B4 is (t ₁,x₁,y₁,h₁,v₁), the sampling information of the track point B4 in one dimension may be fixed and the sampling information of the other dimensions may be extended to determine the track point to be selected.

Taking the dimension of fixed x _i as an example, from the sampling information of the trace point B4, the corresponding sampling space can be determined as τ= [ (t ₁+Δt,x₁,y₁+Δt,h₁+Δt,v₁ +Δt) ]. Under the condition that the sampling parameters are unchanged, according to the planned path τ= [ (t _i,x_i,y_i,h_i,v_i), i=1, 2,3, ], n ], a corresponding sampling space τ+Δt= [ (t _i+Δt,x_i,y_i+Δt,h_i+Δt,v_i +Δt), i=1, 2,3, ], n ] can be obtained.

Compared with the track sampling in the whole feasible region s= (X, Y, H, V), the scheme of the embodiment of the disclosure determines the corresponding sampling space by planning the path and samples in the sampling space, and the sampling space has smaller scale than the feasible region, so that the sampling range is reduced, and the time consumption and the calculation amount of track planning are reduced.

After the plurality of track points to be selected are determined, the plurality of track points to be selected can be sampled to obtain sampling information of the track points to be selected, so that the target track points are determined in the plurality of track points to be selected according to the sampling information of the track points to be selected and the barrier information.

Specifically, after the candidate trajectory point is determined, the traveling information of the vehicle at the current position may be acquired, where the traveling information includes at least one of coordinates of the vehicle at the current position, an orientation of the vehicle, and a speed of the vehicle. And then determining the track points to be selected which meet the running requirement of the vehicle from a plurality of track points to be selected according to the running information of the vehicle and the sampling information of the track points to be selected.

The server can select one of the to-be-selected track points meeting the running requirement of the vehicle as a target track point, can select one of the to-be-selected track points meeting the running requirement of the vehicle as the target track point, and controls the vehicle to run from the current position to the target track point according to the track planning, so that the real-time performance of the track planning is realized, and the strain capacity of the vehicle to the changing environment is improved.

In some cases, in the case that a traffic environment such as obstacle information is suddenly changed, where there is no suitable track point to be selected as a target track point, among the plurality of track points to be selected, the sampling parameters may be updated at this time, so as to re-perform track planning. This process is described below in connection with fig. 6.

Fig. 6 is a schematic diagram of trajectory planning provided by an embodiment of the present disclosure, as shown in fig. 6, a plurality of trajectory points to be selected, namely, a trajectory point B3 and a trajectory point B5, are determined according to the obstacle information of the current position and the first planned trajectory point (i.e., the trajectory point B4).

After determining the plurality of to-be-selected track points, it is necessary to determine whether there are to-be-selected track points satisfying the running requirement of the vehicle among the plurality of to-be-selected track points. In the example of fig. 6, neither the track point B3 nor the track point B5 is suitable as the next target track point when the vehicle is at the current position, i.e., the target track point cannot be determined from the plurality of track points to be selected. At this time, the sampling parameters may be updated, and then the target track point may be determined according to the updated sampling parameters.

Specifically, after updating the sampling parameters, at least one new track point to be selected may be determined according to the updated sampling parameters. Since the sampling parameters may include the sampling distance and the sampling number, when the sampling parameters are updated, the sampling distance may be updated, the sampling number may be updated, and both the sampling distance and the sampling number may be updated.

When the sampling distance is updated, the sampling distance can be increased, so that the sampling range is enlarged. When the number of samples is updated, the number of samples may be increased so that more trace points are sampled in the sampling area.

For example, in fig. 6, the sampling area 60 is redetermined based on the updated sampling parameters, as illustrated by the dashed box in the figure. After the new sampling area 60 is determined, the new sampling area 60 is sampled, and at least one new candidate trajectory point, i.e., the trajectory point B2 and the trajectory point B6 in fig. 6, is determined. Then, new sampling information of the track points B2 and B6 is acquired, so that the target track point is determined from the new track points to be selected according to the new sampling information and the obstacle information. For example, in fig. 6, the track point B2 is determined as the target track point, and then the vehicle can be controlled to drive from the current position to the track point B2.

When the track points meeting the running requirement do not exist in the track points to be selected, the sampling parameters can be adjusted, so that new track points to be selected are determined according to the updated sampling parameters, the target track points are redetermined according to the new track points to be selected, the continuity of track planning of frames before and after a vehicle is improved, the strain capacity under the condition of sudden shaking caused by environmental noise is improved, the anti-noise performance of the scheme is better, the sampling parameters can be adjusted in real time according to the environmental change, and the adaptability is also better.

Fig. 7 is a schematic diagram of a track plan provided by an embodiment of the present disclosure, as shown in fig. 7, in which starting point O to track point A4, track point B4, and track point C5 are initial planned paths, and in an actual track plan, track points sampled during track planning are determined according to the planned paths, for example, track point A3, track point A5, track point B3, track point B5, track point C4, track point C6 in fig. 7, and so on. By planning the path and the barrier information, the sampling area is greatly reduced, so that real-time track planning can be realized without sampling the whole feasible area, and the calculated amount of track planning is reduced on the premise of ensuring the rapid strain capacity of the changed environment in the track planning process.

In summary, in the track planning method provided by the present disclosure, a planned path is determined initially, then based on the planned path, in a subsequent track planning process, obstacle information of a current position is obtained in real time, and a plurality of track points to be selected are determined by combining with a first planned track point corresponding to the planned path, so that compared with the whole feasible region, the sampling range and number are greatly reduced, and the calculation amount of track planning is reduced. And sampling a plurality of track points to be selected, and determining a target track point at the current position according to sampling information, so that the vehicle is controlled to travel to the target track point, real-time planning of the track is realized, and the strain and the processing capacity of a changed environment are improved.

Fig. 8 is a schematic structural diagram of a trajectory planning device according to an embodiment of the disclosure, and as shown in fig. 8, the trajectory planning device 80 may include:

A determining unit 81, configured to determine a first planned track point in a planned path according to a current position of a vehicle and the planned path, where the first planned track point is a next planned track point of the current position;

A processing unit 82, configured to determine a plurality of to-be-selected track points corresponding to the first planned track point according to the obstacle information of the current position and the first planned track point;

An obtaining unit 83, configured to obtain sampling information of the plurality of track points to be selected;

And a planning unit 84, configured to determine a target track point from the plurality of track points to be selected according to the sampling information of the track points to be selected and the obstacle information, and control the vehicle to travel to the target track point.

In one possible implementation, the processing unit 82 includes:

The first acquisition module is used for acquiring track information of the vehicle from the first position to the current position, wherein the first position is the position which is the last position of the current position;

And the first determining module is used for determining the plurality of track points to be selected according to the track information, the obstacle information and the first planning track point.

In one possible implementation manner, the first determining module includes:

The first acquisition submodule is used for acquiring sampling parameters corresponding to the first planning track point according to the track information and the obstacle information;

and the first determining submodule is used for determining the plurality of track points to be selected according to the sampling parameters and the positions of the first planning track points.

In one possible embodiment, the sampling parameters include a sampling distance and a sampling number; the first determination submodule is specifically configured to:

determining a sampling area of the first planning track point according to the sampling distance and the position of the first planning track point;

and determining the plurality of track points to be selected in the sampling area according to the sampling quantity.

In one possible implementation, the planning unit 84 includes:

A second obtaining module, configured to obtain running information of the vehicle at the current position, where the running information includes at least one of coordinates, an orientation, and a speed of the vehicle at the current position;

The second determining module is used for determining the track points to be selected which meet the running requirement of the vehicle from the plurality of track points to be selected according to the running information and the sampling information of the track points to be selected;

and the third determining module is used for determining the target track point from the track points to be selected which meet the running requirement.

In one possible implementation, if none of the plurality of candidate trajectory points meets the driving requirement, the planning unit 84 is further configured to:

Updating the sampling parameters, and determining at least one new track point to be selected according to the updated sampling parameters;

acquiring new sampling information of the at least one new track point to be selected;

And determining the target track point in the at least one new track point to be selected according to the new sampling information and the obstacle information.

In a possible embodiment, the method further comprises an acquisition unit for:

acquiring a plurality of track points in a feasible region, map data of the feasible region and initial obstacle information;

Acquiring sampling information of a plurality of track points in the feasible region;

And acquiring the planned path according to the sampling information of the track points, the map data and the initial obstacle information.

The track planning device provided by the embodiment of the present application is used for executing the above method embodiment, and its implementation principle and technical effects are similar, and this embodiment will not be described herein.

The disclosure provides a track planning method, a device, equipment, a storage medium and an automatic driving vehicle, which are applied to the fields of unmanned driving, automatic driving, intelligent traffic and the like in artificial intelligence technology, so as to achieve the purpose of reducing the calculated amount of track planning in the process of real-time track planning.

Note that, the head model in this embodiment is not a head model for a specific user, and cannot reflect personal information of a specific user. It should be noted that, the two-dimensional face image in this embodiment is derived from the public data set.

In the technical scheme of the disclosure, the related processes of collecting, storing, using, processing, transmitting, providing, disclosing and the like of the personal information of the user accord with the regulations of related laws and regulations, and the public order colloquial is not violated.

According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

According to an embodiment of the present disclosure, the present disclosure also provides a computer program product comprising: a computer program stored in a readable storage medium, from which at least one processor of an electronic device can read, the at least one processor executing the computer program causing the electronic device to perform the solution provided by any one of the embodiments described above.

According to an embodiment of the present disclosure, there is further provided an autonomous vehicle, where the autonomous vehicle includes an electronic device, and when the autonomous vehicle is running, at least one processor of the electronic device in the autonomous vehicle may read a computer program from a readable storage medium, and execution of the computer program by the at least one processor causes the electronic device to execute the solution provided in any one of the above embodiments, so as to implement trajectory planning of the autonomous vehicle, so that the autonomous vehicle runs according to the planned trajectory.

Fig. 9 shows a schematic block diagram of an example electronic device 900 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 9, the apparatus 900 includes a computing unit 901 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 902 or a computer program loaded from a storage unit 908 into a Random Access Memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the device 900 can also be stored. The computing unit 901, the ROM 902, and the RAM 903 are connected to each other by a bus 904. An input/output (I/O) interface 905 is also connected to the bus 904.

Various components in device 900 are connected to I/O interface 905, including: an input unit 906 such as a keyboard, a mouse, or the like; an output unit 907 such as various types of displays, speakers, and the like; a storage unit 908 such as a magnetic disk, an optical disk, or the like; and a communication unit 909 such as a network card, modem, wireless communication transceiver, or the like. The communication unit 909 allows the device 900 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunications networks.

The computing unit 901 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 901 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 901 performs the respective methods and processes described above, such as a trajectory planning method. For example, in some embodiments, the trajectory planning method may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as the storage unit 908. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 900 via the ROM 902 and/or the communication unit 909. When the computer program is loaded into RAM 903 and executed by the computing unit 901, one or more steps of the trajectory planning method described above may be performed. Alternatively, in other embodiments, the computing unit 901 may be configured to perform the trajectory planning method by any other suitable means (e.g. by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.

The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service ("Virtual PRIVATE SERVER" or simply "VPS") are overcome. The server may also be a server of a distributed system or a server that incorporates a blockchain.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel or sequentially or in a different order, provided that the desired results of the technical solutions of the present disclosure are achieved, and are not limited herein.

The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.

Claims

1. A trajectory planning method, comprising:

Acquiring sampling information of the plurality of track points to be selected; the sampling information of the track points to be selected comprises: the coordinate range of the track point to be selected, the vehicle orientation range of the track point to be selected and the allowable speed range of the track point to be selected;

determining a target track point in the plurality of track points to be selected according to the sampling information of the plurality of track points to be selected and the barrier information, and controlling the vehicle to travel towards the target track point;

Wherein determining the target track point among the plurality of track points to be selected according to the sampling information of the plurality of track points to be selected and the obstacle information comprises:

Acquiring running information of the vehicle at the current position, wherein the running information comprises at least one of coordinates, directions and speeds of the vehicle at the current position;

Determining a track point to be selected meeting the running requirement of the vehicle in the plurality of track points to be selected according to the running information and the sampling information of the plurality of track points to be selected;

And determining the target track point from the track points to be selected which meet the running requirement.

2. The method of claim 1, wherein the determining a plurality of candidate track points corresponding to the first planned track point according to the obstacle information of the current position and the first planned track point includes:

acquiring track information of the vehicle from a first position to the current position, wherein the first position is the position above the current position;

And determining the plurality of track points to be selected according to the track information, the obstacle information and the first planning track point.

3. The method of claim 2, wherein the determining the plurality of candidate trajectory points from the trajectory information, the obstacle information, and the first planned trajectory point comprises:

acquiring sampling parameters corresponding to the first planning track points according to the track information and the obstacle information;

And determining the plurality of track points to be selected according to the sampling parameters and the positions of the first planning track points.

4. A method according to claim 3, wherein the sampling parameters include sampling distance and number of samples; the determining the plurality of to-be-selected track points according to the sampling parameters and the positions of the first planning track points includes:

5. The method of claim 3 or 4, wherein if none of the plurality of candidate trajectory points meets the travel requirement, the method further comprises:

6. The method of any of claims 1-4, wherein the method further comprises:

7. A trajectory planning device, comprising:

The acquisition unit is used for acquiring sampling information of the plurality of track points to be selected; the sampling information of the track points to be selected comprises: the coordinate range of the track point to be selected, the vehicle orientation range of the track point to be selected and the allowable speed range of the track point to be selected;

The planning unit is used for determining a target track point in the plurality of track points to be selected according to the sampling information of the plurality of track points to be selected and the obstacle information, and controlling the vehicle to travel towards the target track point;

wherein the planning unit comprises:

the second determining module is used for determining the track points to be selected which meet the running requirement of the vehicle in the plurality of track points to be selected according to the running information and the sampling information of the plurality of track points to be selected;

8. The apparatus of claim 7, wherein the processing unit comprises:

the first acquisition module is used for acquiring track information of the vehicle from a first position to the current position, wherein the first position is the position above the current position;

9. The apparatus of claim 8, wherein the first determination module comprises:

10. The apparatus of claim 9, wherein the sampling parameters comprise a sampling distance and a sampling number; the first determination submodule is specifically configured to:

11. The apparatus according to claim 9 or 10, wherein if none of the plurality of candidate trajectory points meets the driving requirement, the planning unit is further configured to:

12. The apparatus according to any one of claims 7-10, further comprising an acquisition unit for:

13. An electronic device, comprising:

at least one processor; and

A memory communicatively coupled to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.

14. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-6.

15. A computer program product comprising a computer program which, when executed by a processor, implements the steps of the method of any of claims 1-6.

16. An autonomous vehicle comprising the electronic device of claim 13.