CN115230719B

CN115230719B - Driving track planning method and device

Info

Publication number: CN115230719B
Application number: CN202111454583.1A
Authority: CN
Inventors: 黄超; 叶玥
Original assignee: Shanghai Xiantu Intelligent Technology Co Ltd
Current assignee: Shanghai Xiantu Intelligent Technology Co Ltd
Priority date: 2021-12-01
Filing date: 2021-12-01
Publication date: 2023-09-26
Anticipated expiration: 2041-12-01
Also published as: CN115230719A; WO2023097874A1

Abstract

The embodiment of the disclosure provides a driving track planning method and device, wherein the method comprises the following steps: acquiring road information obtained by acquiring information of a road; planning a normal running track of a vehicle according to the road information to obtain the normal running track, and planning a retreating running track of the vehicle to obtain the retreating running track, wherein the running track of the vehicle is a planned normal running track, and the planned running distance of the retreating running track is shorter than the planned running distance of the normal running track; and in response to failure of planning the normal running track, converting the running track of the vehicle into a rollback running track. The method not only generates a normal running track, but also generates a back running track, and when the normal running track cannot be driven, the method is switched to the back running track, so that the probability of accident occurrence can be reduced.

Description

Driving track planning method and device

Technical Field

The disclosure relates to the technical field of intelligent driving, in particular to a driving track planning method and device.

Background

In the intelligent driving system, a planning module is responsible for integrating the contents of a plurality of modules such as sensing, predicting, positioning, mapping, vehicles and the like, and generating a rapid, safe and feasible track for the intelligent driving vehicle.

Travel trajectory planning is broadly divided into decision making, path planning and speed planning. The decision module gives macroscopic decisions such as decisions of lane keeping, lane changing, road borrowing and the like according to road conditions. And (3) path planning, according to an upper layer decision, taking static barriers and low-speed dynamic barriers into consideration, and generating a plurality of safe collision-free paths. The speed planning is to consider dynamic obstacles with higher speed on the basis of path planning, make decisions such as overtaking, following, parking avoidance and the like, and generate corresponding ST (distance time) diagrams. Finally, a plurality of tracks are obtained through combining path planning and speed planning, and an optimal safe, collision-free and comfortable running track is obtained through screening. The path planned by the path only comprises space position information, and the running track comprises space-time information, namely the position on the running track corresponds to the time point reaching the position.

However, in complex road scenes such as cities, planning failure may occur due to the fact that the number of traffic participants is large, the uncertainty of behaviors is large, or the accuracy of algorithm of the intelligent driving system is not high. At this time, the speed of the vehicle may be high, and the steering avoidance operation and other operations cannot be completed when the planning fails, thereby causing dangerous consequences. For example, since the path planning is far away from the planned travel distance and multiple paths may be planned under different decisions, in order to ensure the planning frequency, the path planning accuracy is sacrificed, and in the scenario where high accuracy is required, the situation of planning failure may occur.

Disclosure of Invention

In view of this, the embodiments of the present disclosure provide at least one driving track planning method and apparatus.

Specifically, the embodiment of the disclosure is realized through the following technical scheme:

in a first aspect, a driving track planning method is provided, the method includes:

acquiring road information obtained by acquiring information of a road;

planning a normal running track of a vehicle according to the road information to obtain the normal running track, and planning a retreating running track of the vehicle to obtain the retreating running track, wherein the running track of the vehicle is a planned normal running track, and the planned running distance of the retreating running track is shorter than the planned running distance of the normal running track;

and in response to failure of planning the normal running track, converting the running track of the vehicle into a rollback running track.

In a second aspect, there is provided a travel path planning apparatus, the apparatus comprising:

the road information acquisition module is used for acquiring road information obtained by acquiring information of a road;

the driving track planning module is used for planning a normal driving track of a vehicle according to the road information to obtain the normal driving track, planning a retreating driving track of the vehicle to obtain the retreating driving track, wherein the driving track of the vehicle is a planned normal driving track, and the planning driving distance of the retreating driving track is shorter than that of the normal driving track;

and the driving track control module is used for converting the driving track of the vehicle into a back driving track in response to failure of planning the normal driving track.

In a third aspect, an electronic device is provided, the device comprising a memory for storing computer instructions executable on the processor for implementing a driving trajectory planning method according to any one of the embodiments of the present disclosure when the computer instructions are executed.

In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, which when executed by a processor implements a driving trajectory planning method according to any one of the embodiments of the present disclosure.

According to the running track planning method provided by the technical scheme provided by the embodiment of the disclosure, when the running track of the vehicle is planned, the normal running track is generated, and the rollback running track is also generated. When the vehicle cannot drive according to the normal running track, the vehicle is switched to the rollback running track, so that the occurrence probability of accidents is greatly reduced, and the vehicle is applicable to the existing running track planning frame; the planned driving distance of the rollback driving track is shorter than the planned driving distance of the normal driving track, so that the success rate and the planning precision of planning the rollback driving track are guaranteed, and the safety of the vehicle under complex road conditions can be greatly improved by combining the two planning methods.

Drawings

In order to more clearly illustrate the technical solutions of one or more embodiments of the present disclosure or related technologies, the following description will briefly describe the drawings that are required to be used in the embodiments or related technology descriptions, and it is apparent that the drawings in the following description are only some embodiments described in one or more embodiments of the present disclosure, and other drawings may be obtained according to these drawings without inventive effort to those of ordinary skill in the art.

FIG. 1 is a flow chart diagram of a method of driving trajectory planning shown in at least one embodiment of the present disclosure;

FIG. 2 is a flow chart of another travel path planning method shown in at least one embodiment of the present disclosure;

FIG. 3 is a block diagram of a method of rewinding a travel path shown in at least one embodiment of the present disclosure;

FIG. 3A is a schematic diagram of a Cartesian coordinate system and a reference line coordinate system illustrating at least one embodiment of the present disclosure;

FIG. 3B is a schematic diagram of another Cartesian coordinate system and a reference line coordinate system shown in accordance with at least one embodiment of the present disclosure;

FIG. 4 is a block diagram of another travel path planning apparatus shown in accordance with at least one embodiment of the present disclosure;

fig. 5 is a schematic diagram of a hardware structure of an electronic device according to at least one embodiment of the present disclosure.

Detailed Description

Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the present specification. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present description as detailed in the accompanying claims.

The terminology used in the description presented herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the description. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.

It should be understood that although the terms first, second, third, etc. may be used in this specification to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, the first information may also be referred to as second information, and similarly, the second information may also be referred to as first information, without departing from the scope of the present description. The word "if" as used herein may be interpreted as "at … …" or "at … …" or "responsive to a determination", depending on the context.

As shown in fig. 1, fig. 1 is a flowchart of a driving track planning method according to at least one embodiment of the present disclosure, where the method may be used in an intelligent driving system of a vehicle, and may also be used in a cloud server or a terminal device such as a mobile phone, where the vehicle may be an unmanned vehicle or a manned vehicle, and the method includes the following steps:

in step 102, road information obtained by information acquisition of a road is acquired.

The road information obtained by information acquisition of the road may be information obtained by information acquisition of the road by a sensor on the vehicle. For example, traffic signal information, lane line information, pedestrian information, other vehicle information and other obstacle information are obtained through shooting by a vehicle-mounted camera, and the distance between the vehicle and surrounding objects is measured through a vehicle-mounted radar or a laser radar.

The road information obtained by collecting the information of the road may be information obtained by collecting the information of the road by other devices. For example, GPS (Global Positioning System ) signal information, or pre-made high-precision map information, which contains a large amount of driving assistance information, such as an intersection layout, a road sign position, a speed limit of a road, a position where a left-turn lane starts, and the like.

In one example, the road information includes at least one of: obstacle information, traffic signal information, map information, road speed limit information, and lane line information.

In step 104, according to the road information, planning a normal running track of the vehicle to obtain the normal running track, and planning a rollback running track of the vehicle to obtain the rollback running track.

In this embodiment, the planning of the normal running track and the rollback running track is a local planning, that is, the normal running track and the rollback running track planned each time are not from the current position of the vehicle to the position of the final destination, but a small section of running track starting from the current position of the vehicle, and multiple running track planning is required to reach the final destination.

The triggering condition of the driving track planning is not limited in this embodiment, and may be at intervals, or may be when the vehicle-mounted camera shoots one frame of image, or may also be when the vehicle travels a certain distance. When the trigger condition is met, the normal running track and the back running track are required to be re-planned, and the planned normal running track and the planned back running track are respectively updated. It should be noted that, in this embodiment, the sequence of planning the normal running track and the rollback running track is not limited, and the two may be performed simultaneously or sequentially.

When the running track of the vehicle is the planned normal running track, the vehicle can run according to the speed and the direction indicated by the normal running track, and operations such as lane change, overtaking or parking are performed according to the instructions, and the normal running track is stored after the planning and updated after the next planning is completed.

The planning methods used in planning the normal running track of the vehicle and planning the retracted running track may be different, and the road information on which they are based may also be different. In the scheme, the planned driving distance of the rollback driving track is shorter than the planned driving distance of the normal driving track.

Generally, the planning frequency needs to be very frequent to ensure driving safety in road scenes with a large number of traffic participants and large uncertainty of behaviors. For the planning of the normal running track of the vehicle, because the length of the planning is far, and under different decisions, multiple paths can exist, in order to ensure the planning frequency, the planning precision is sacrificed, and for the scene requiring high precision, the situation that the path planning cannot be planned is likely to occur in the step of path planning, so that the planning failure is caused, the situation that the running track on which the vehicle is not based is blocked or out of control can occur, and the traffic safety is threatened.

In this step, the normal running track of the vehicle is planned to obtain a normal running track, and the rollback running track of the vehicle is planned to obtain a rollback running track, which may all be a common planning algorithm, for example, a dynamic planning algorithm, an optimization algorithm, a lattice algorithm, etc.

When planning the rollback running track, a shorter planning running distance than the normal running track can be set, so that when planning the rollback running track, higher planning precision can be used in a limited time, the rollback running track can be obtained by considering richer road information, and the planning success rate is ensured to be higher than that of the normal running track.

For example, a planned travel distance of the normal travel track may be set to be 100 meters, and a travel path of 100 meters needs to be planned from the current vehicle position to the destination direction when the normal travel track is planned; the planned travel distance of the rollback travel track is 20 meters, and a travel path of 20 meters needs to be planned from the current vehicle position to the destination direction when the rollback travel track is planned.

In one example, the planned travel distance may also be affected by setting a planned travel time. For example, the planned travel time of the normal travel track may be set to 30 seconds, and a travel path of the vehicle within 30 seconds from the current vehicle position to the destination direction is required when the normal travel track is planned; and the planned travel time of the rollback travel track is 10 seconds, and the travel path of the vehicle needs to be planned within 10 seconds from the current vehicle position to the destination direction when the rollback travel track is planned. By setting a shorter planned travel time for the return travel locus, the planned travel distance can be made shorter.

In step 106, in response to failure of the normal travel track planning, the travel track of the vehicle is converted to a rollback travel track.

The planning of the normal running track requires planning longer planning running distance, the success rate is lower than that of the planning of the rollback running track, and when the planning of the normal running track fails, in order to avoid the blocking or the out-of-control caused by the fact that the running vehicle cannot continue running after the guidance of the normal running track is lost, the running track of the vehicle is converted into the rollback running track, so that dangerous accidents are avoided.

When the running track of the vehicle is converted into the retreating running track, the vehicle runs according to the planned retreating running track, at the moment, the vehicle continuously plans the normal running track and the retreating running track, and if the planning of the normal running track still fails, the vehicle can continue to run according to the planned retreating running track.

In one example, in a case where the travel locus of the vehicle is a return travel locus, the travel locus of the vehicle is converted into a normal travel locus in response to success of planning the normal travel locus.

According to the travel track planning method provided by the embodiment of the disclosure, when the travel track of the vehicle is planned, not only the normal travel track but also the rollback travel track are generated. When the vehicle cannot drive according to the normal running track, the vehicle is switched to the retreating running track, so that the occurrence probability of accidents is greatly reduced; the planned driving distance of the rollback driving track is shorter than the planned driving distance of the normal driving track, so that the success rate and the planning precision of planning the rollback driving track are guaranteed, and the safety of the vehicle under complex road conditions can be greatly improved by combining the two planning methods.

In the current technology, the driving track planning is roughly divided into decision making, path planning and speed planning, and besides path planning failure possibly caused by a high-precision scene, other reasons for planning failure are also included. For example, the above-mentioned path planning and speed planning separate planning method, although the planning speed is relatively high, there may be a situation that the two planning methods are incompatible. For example, when a path is planned, only a part of dynamic obstacles (i.e. low-speed dynamic obstacles) are considered, a feasible path is planned, but after all dynamic obstacles are considered, speed planning is performed on a certain dynamic obstacle, limitation of acceleration of a vehicle, which is limited by acceleration of the vehicle, cannot be completed, limitation of deceleration of the vehicle, which is limited by deceleration of the vehicle, cannot be completed, and therefore, speed planning cannot be performed on the feasible path, so that planning fails.

Based on this, the present disclosure provides yet another driving trajectory planning method. As shown in fig. 2, fig. 2 is a flowchart of a driving track planning method according to at least one embodiment of the present disclosure, where the method includes the following processes, and the steps identical to those of fig. 1 are not repeated.

In step 202, road information obtained by information acquisition of a road is acquired.

In this embodiment, the road information includes at least obstacle information including static obstacle information, low-speed dynamic obstacle information, and high-speed dynamic obstacle information; the low-speed dynamic obstacle information is information of a dynamic obstacle with a speed less than a speed threshold, and the high-speed dynamic obstacle information is information of a dynamic obstacle with a speed not less than the speed threshold, and the setting of the speed threshold is not limited, for example, may be set to 20km/h.

In step 204, a path planning is performed on the rollback travel path of the vehicle according to the static obstacle information, the low-speed dynamic obstacle information and the high-speed dynamic obstacle information, so as to obtain at least one rollback travel path.

When the normal running path of the vehicle is planned, a traditional planning mode can be still adopted, namely, according to an upper layer decision, static obstacles and low-speed dynamic obstacles are considered to generate a plurality of safe collision-free paths. The high-speed dynamic obstacles are considered again when the speed planning is performed subsequently.

When the rollback driving path of the vehicle is planned, in addition to the static obstacle and the low-speed dynamic obstacle, the high-speed dynamic obstacle which needs to be considered in the speed planning of the normal driving track is also considered, so as to avoid the problem that incompatibility possibly occurs due to different obstacle information according to the separation mode of the path planning and the speed planning. That is, in this embodiment, the rollback travel path obtained by planning the rollback travel path of the vehicle includes not only spatial information but also time information, that is, it is required that the vehicle reach some route points on the rollback travel path.

Whether the rollback driving track or the normal driving track is planned, the planned driving time and the planned driving distance are required to be determined, and the road information of which time range and the road information in which distance range are required to be considered can be known to be planned according to the planned driving time and the planned driving distance. The planned travel distance of the rollback travel track is shorter than the planned travel distance of the normal travel track, and the planned travel time of the rollback travel track may also be shorter than the planned travel time of the normal travel track.

In one example, the planned travel time and the planned travel distance of the rollback travel track or the normal travel track may take on default settings or user-set values.

In one example, before this step, the planned travel time and the planned travel distance of the rollback travel track may also be determined according to the travel speed and the deceleration of the vehicle.

The planned travel time of the rollback travel track is a travel time of the vehicle from the current vehicle position, and the planned travel distance of the rollback travel track is a travel distance of the vehicle from the current vehicle position. Since the rollback travel track is a route used as an emergency, the vehicle can be planned with a larger deceleration, the maximum deceleration of the vehicle is alpha under the constraint of taking dynamics into consideration, and the planned travel time t=v/alpha is the shortest planned travel time under emergency braking assuming that the current travel speed of the vehicle is v, and the shortest planned travel distance can be calculatedThe planned travel time and the planned travel distance may be determined based on the shortest planned travel time and the shortest planned travel distance, i.e., the determined planned travel time and planned travel distance cannot be smaller than the shortest planned travel time and planned travel distance.

In one example, at least one motion trajectory of each dynamic obstacle in the planned travel distance range in the planned travel time may be predicted based on the low-speed dynamic obstacle information and the high-speed dynamic obstacle information, the dynamic obstacle including the low-speed dynamic obstacle and the high-speed dynamic obstacle; and planning a path of a rollback running path of the vehicle according to the static obstacle information and the motion trail of the dynamic obstacle to obtain at least one rollback running path.

In order to avoid an obstacle on the travel path, when planning the rollback travel path, it is necessary to calculate all possible positions of the dynamic obstacle within the future travel planning time. For example, the sensing and predicting module in the intelligent driving system predicts the motion trail of each dynamic obstacle in the planned driving distance range in the future planned driving time, and usually, the motion trail of each dynamic obstacle has a plurality of motion trails and is given to the planning module, and the planning module performs path planning on the rollback driving path of the vehicle according to the known static obstacle information and the motion trail of the dynamic obstacle to obtain at least one crashless rollback driving path.

In practical implementation, the motion trail of an illegal dynamic obstacle can be filtered through traffic lights, right-to-the-right running and traffic rules such as prohibiting the change of a solid line, and the legal motion trail is reserved. In one example, the shortest planned travel time t may be used to determine a position envelope formed by all legal movement tracks of the dynamic obstacle during the time period t. It is noted that the longer the time period t, the greater the uncertainty of the motion trail, the more rapidly the formed position envelope expands, and the shortest planned travel time t or the planned travel time set by us are shorter, so that the envelope can be prevented from being excessively expanded. By the method, the uncertainty of the behavior of the dynamic obstacle and the uncertainty of the prediction module can be eliminated, and the success rate and the accuracy of planning the rollback running track are improved. And the dynamic obstacle is excessively estimated for all legal behaviors in the future, so that the safety of the rollback driving track is fully ensured.

The following describes a specific flow of planning a rollback driving path of a vehicle according to static obstacle information and a motion track of a dynamic obstacle to obtain at least one rollback driving path in detail, as shown in fig. 3, including the following steps, where the following steps and other processing steps in the embodiment do not have a sequence limitation.

In step 302, global planning is performed according to the current position and the target position of the vehicle, so as to obtain a global planned driving road.

The global planning may be performed without consideration of the obstacle information. For example, the global path planning module of the intelligent driving system can directly obtain the route from the current position to the target position according to the map information, namely, the global planned driving road.

In step 304, the center line of the global planned driving road is extracted, and a reference line is obtained according to the center line.

After extracting the central line of the global planning driving road, preprocessing the central line, wherein the preprocessing comprises but is not limited to offset, smoothing and other processing modes. After pretreatment, spline curves such as cubic spline curves, quintic spline curves and the like are used for processing to obtain reference lines, and the spline curve processing can ensure that the first derivative, the second derivative and the like of the reference lines are continuous and smooth.

In step 306, a reference line coordinate system is established based on the tangential direction and the normal direction of the reference line.

In order to facilitate planning and visual display of the driving track, a Frenet coordinate system, namely a reference line coordinate system, can be established for planning, or a previous Cartesian coordinate system can be converted into the reference line coordinate system. The reference line coordinate system describes the position of the vehicle relative to the road. In the Frenet coordinate system, s represents the distance along the road, as shown in FIG. 3A, and is the tangential direction along the reference line, also referred to as the ordinate. d represents the displacement from the longitudinal line, being the current normal direction of the reference line, also called abscissa. At each point of the road, the horizontal and vertical axes are perpendicular. The ordinate represents the travel distance in the road, and the abscissa represents the distance by which the vehicle deviates from the center line. As shown in fig. 3A and 3B, the difference between the cartesian coordinate system and the reference line coordinate system is illustrated.

In step 308, according to the static obstacle information and the motion track of the dynamic obstacle, determining the obstacle positions of the static obstacle and the dynamic obstacle in the reference line coordinate system.

And converting the position information in the obstacle information from a Cartesian coordinate system to a reference line coordinate system, and obtaining the position of the obstacle in the reference line coordinate system.

In step 310, an obstacle map based on a reference line coordinate system is generated according to the planned travel distance, the obstacle position, and the current position of the vehicle.

For example, a high-precision grid map can be generated according to the planned driving distance and the current position of the vehicle, and the barrier position is filled into the grid map to obtain a barrier map based on a reference line coordinate system.

In step 312, a path planning is performed on the rollback running path of the vehicle according to the obstacle diagram based on the reference line coordinate system, so as to obtain at least one rollback running path.

The conventional planning algorithm can be used, and is not limited to a dynamic planning algorithm, an optimization algorithm, a lattice algorithm and other algorithms are used for conforming to a collision-free rollback driving path of vehicle dynamics, and the rollback driving path not only comprises space information but also comprises time information so as to avoid a position where a dynamic obstacle possibly appears at a future time.

In step 206, for any one of the rollback driving paths, according to the high-speed dynamic obstacle information, speed planning is performed on the speeds of the various path points of the vehicle on the rollback driving path, so as to obtain a longitudinal displacement time chart corresponding to the rollback driving path.

When the speed planning is carried out on the rollback running path, the speed of each path point of the vehicle on the rollback running path can be determined, wherein the speed of each path point is not a single speed value, but a speed range or a series of speeds, some path points of the rollback running path obtained in the last step may already have speed information, and the speeds of each path point can be optimized such as smoothing, so as to ensure that the vehicle runs stably.

For each rollback travel path, a corresponding longitudinal displacement time chart can be obtained, the ordinate is longitudinal displacement, and the abscissa is time, so as to represent the speed of each path point on each rollback travel path.

In step 208, the rollback travel path and the longitudinal displacement time chart corresponding to the rollback travel path are fused, so as to obtain a candidate rollback travel track.

And merging the rollback running paths and longitudinal displacement time diagrams corresponding to the rollback running paths, determining the accurate speed of each path point to obtain candidate rollback running tracks, and obtaining at least one candidate rollback running track by each rollback running path.

In step 210, according to the evaluation result of each candidate rollback track, the candidate rollback track with the highest evaluation is screened out as the rollback track.

The present embodiment does not limit the evaluation method of the candidate rollback running trajectory. For example, the candidate rollback travel trajectory may be evaluated based on at least one of a deviation from the center of the lane, a change in distance from an obstacle, speed, and curvature, pressure on the vehicle, safety, fuel consumption, and any other factors that the developer wants to consider. The candidate rollback trajectory with the highest evaluation is taken as the rollback trajectory, and of course, other candidate rollback trajectories may be taken as the rollback trajectory instead of the candidate rollback trajectory with the highest evaluation.

When the travel track planning method provided by the embodiment of the disclosure is used for carrying out rollback of the travel track, the planned travel distance is shorter, the planning precision can be improved, and the blocking caused by the precision problem is avoided. In addition, as the dynamic and static barriers are considered during path planning, the problem of blockage caused by inconsistent separation of path planning and speed planning can be avoided.

As shown in fig. 4, fig. 4 is a block diagram of a travel path planning apparatus according to at least one embodiment of the present disclosure, the apparatus including:

the road information acquisition module 41 is configured to acquire road information obtained by acquiring information of a road;

the driving track planning module 42 is configured to plan a normal driving track of a vehicle according to the road information, obtain the normal driving track, and plan a retracted driving track of the vehicle, so as to obtain the retracted driving track, where the driving track of the vehicle is a planned normal driving track, and a planned driving distance of the retracted driving track is shorter than a planned driving distance of the normal driving track;

and the driving track control module 43 is used for converting the driving track of the vehicle into a rollback driving track in response to failure of planning the normal driving track.

In one example, the driving track control module 43 is further configured to: and under the condition that the running track of the vehicle is a rollback running track, responding to the successful planning of the normal running track, and converting the running track of the vehicle into the normal running track.

In one example, the road information includes at least obstacle information including static obstacle information, low-speed dynamic obstacle information, and high-speed dynamic obstacle information; the low-speed dynamic obstacle information is information of a dynamic obstacle with the speed being smaller than a speed threshold value, and the high-speed dynamic obstacle information is information of a dynamic obstacle with the speed being not smaller than the speed threshold value;

the driving track planning module 42 is configured to, when configured to plan a rollback driving track of the vehicle according to the road information to obtain the rollback driving track, specifically:

planning a path of a rollback running path of the vehicle according to the static obstacle information, the low-speed dynamic obstacle information and the high-speed dynamic obstacle information to obtain at least one rollback running path; for any one of the rollback driving paths, according to the high-speed dynamic obstacle information, speed planning is carried out on the speed of each path point of the vehicle on the rollback driving path, and a longitudinal displacement time chart corresponding to the rollback driving path is obtained; fusing the rollback running path and the longitudinal displacement time diagram corresponding to the rollback running path to obtain a candidate rollback running track; and screening out the candidate rollback running track with the highest evaluation as the rollback running track according to the evaluation result of each candidate rollback running track.

In one example, the driving track planning module 42 is further configured to: and before planning a rollback running path of the vehicle according to the static obstacle information, the low-speed dynamic obstacle information and the high-speed dynamic obstacle information to obtain at least one rollback running path, determining the planned running time and the planned running distance of the rollback running track according to the running speed and the deceleration of the vehicle.

In one example, the driving track planning module 42 is specifically configured to, when performing path planning on the rollback driving path of the vehicle according to the static obstacle information, the low-speed dynamic obstacle information, and the high-speed dynamic obstacle information, obtain at least one rollback driving path: predicting at least one motion track of each dynamic obstacle in the planned driving distance range in the planned driving time according to the low-speed dynamic obstacle information and the high-speed dynamic obstacle information, wherein the dynamic obstacles comprise the low-speed dynamic obstacle and the high-speed dynamic obstacle; and planning a path of a rollback running path of the vehicle according to the static obstacle information and the motion trail of the dynamic obstacle to obtain at least one rollback running path.

In one example, the driving track planning module 42 is configured to plan a rollback driving path of the vehicle according to the static obstacle information and the motion track of the dynamic obstacle, so as to obtain at least one rollback driving path, and specifically is configured to: performing global planning according to the current position and the target position of the vehicle to obtain a global planning driving road; extracting a central line of the global planning driving road, and obtaining a reference line according to the central line; establishing a reference line coordinate system according to the tangential direction and the normal direction of the reference line; determining the obstacle positions of the static obstacle and the dynamic obstacle in the reference line coordinate system according to the static obstacle information and the motion trail of the dynamic obstacle; generating an obstacle map based on a reference line coordinate system according to the planned driving distance, the obstacle position and the current position of the vehicle; and planning a path of the rollback running path of the vehicle according to the obstacle diagram based on the reference line coordinate system to obtain at least one rollback running path.

The implementation process of the functions and roles of each module in the above device is specifically shown in the implementation process of the corresponding steps in the above method, and will not be described herein again.

The embodiment of the present disclosure further provides an electronic device, as shown in fig. 5, where the electronic device includes a memory 51 and a processor 52, where the memory 51 is configured to store computer instructions that can be executed on the processor, and the processor 52 is configured to implement the driving track planning method according to any embodiment of the present disclosure when executing the computer instructions.

The disclosed embodiments also provide a computer program product comprising a computer program/instruction which, when executed by a processor, implements the driving trajectory planning method according to any of the embodiments of the present disclosure.

The embodiments of the present disclosure also provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the driving trajectory planning method according to any of the embodiments of the present disclosure.

For the device embodiments, reference is made to the description of the method embodiments for the relevant points, since they essentially correspond to the method embodiments. The apparatus embodiments described above are merely illustrative, wherein the modules illustrated as separate components may or may not be physically separate, and the components shown as modules may or may not be physical, i.e., may be located in one place, or may be distributed over a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purposes of the present description. Those of ordinary skill in the art will understand and implement the present invention without undue burden.

The foregoing describes specific embodiments of the present disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Other embodiments of the present description will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This specification is intended to cover any variations, uses, or adaptations of the specification following, in general, the principles of the specification and including such departures from the present disclosure as come within known or customary practice within the art to which the specification pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the specification being indicated by the following claims.

It is to be understood that the present description is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present description is limited only by the appended claims.

The foregoing description of the preferred embodiments is provided for the purpose of illustration only, and is not intended to limit the scope of the disclosure, since any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the disclosure are intended to be included within the scope of the disclosure.

Claims

1. A method of driving trajectory planning, the method comprising:

acquiring road information obtained by acquiring information of a road;

in response to failure of planning the normal running track, converting the running track of the vehicle into a rollback running track;

the road information at least comprises obstacle information, wherein the obstacle information comprises static obstacle information, low-speed dynamic obstacle information and high-speed dynamic obstacle information; the low-speed dynamic obstacle information is information of a dynamic obstacle with the speed being smaller than a speed threshold value, and the high-speed dynamic obstacle information is information of a dynamic obstacle with the speed being not smaller than the speed threshold value;

planning the rollback running track of the vehicle according to the road information to obtain the rollback running track, wherein the method comprises the following steps:

planning a path of a rollback running path of the vehicle according to the static obstacle information, the low-speed dynamic obstacle information and the high-speed dynamic obstacle information to obtain at least one rollback running path;

for any one of the rollback driving paths, according to the high-speed dynamic obstacle information, speed planning is carried out on the speed of each path point of the vehicle on the rollback driving path, and a longitudinal displacement time chart corresponding to the rollback driving path is obtained;

fusing the rollback running path and the longitudinal displacement time diagram corresponding to the rollback running path to obtain a candidate rollback running track;

according to the evaluation result of each candidate rollback running track, screening out the candidate rollback running track with the highest evaluation as the rollback running track;

the step of planning a path of a rollback travel path of a vehicle according to the static obstacle information, the low-speed dynamic obstacle information and the high-speed dynamic obstacle information to obtain at least one rollback travel path comprises the following steps:

predicting at least one motion track of each dynamic obstacle in the planned driving distance range in the planned driving time according to the low-speed dynamic obstacle information and the high-speed dynamic obstacle information, wherein the dynamic obstacles comprise the low-speed dynamic obstacle and the high-speed dynamic obstacle;

and planning a path of a rollback running path of the vehicle according to the static obstacle information and the motion trail of the dynamic obstacle to obtain at least one rollback running path.

2. The method according to claim 1, wherein the method further comprises:

and under the condition that the running track of the vehicle is a rollback running track, responding to the successful planning of the normal running track, and converting the running track of the vehicle into the normal running track.

3. The method of claim 1, wherein prior to said planning a rollback travel path for a vehicle based on said static obstacle information, low-speed dynamic obstacle information, and high-speed dynamic obstacle information to obtain at least one of said rollback travel paths, said method further comprises:

and determining the planned running time and the planned running distance of the rollback running track according to the running speed and the deceleration of the vehicle.

4. The method according to claim 1, wherein the step of planning a rollback travel path of the vehicle according to the static obstacle information and the motion trajectory of the dynamic obstacle to obtain at least one rollback travel path includes:

performing global planning according to the current position and the target position of the vehicle to obtain a global planning driving road;

extracting a central line of the global planning driving road, and obtaining a reference line according to the central line;

establishing a reference line coordinate system according to the tangential direction and the normal direction of the reference line;

determining the obstacle positions of the static obstacle and the dynamic obstacle in the reference line coordinate system according to the static obstacle information and the motion trail of the dynamic obstacle;

generating an obstacle map based on a reference line coordinate system according to the planned driving distance, the obstacle position and the current position of the vehicle;

and planning a path of the rollback running path of the vehicle according to the obstacle diagram based on the reference line coordinate system to obtain at least one rollback running path.

5. The method of any of claims 1-4, wherein the road information comprises at least one of: obstacle information, traffic signal information, map information, road speed limit information, and lane line information.

6. A travel path planning apparatus, the apparatus comprising:

the driving track control module is used for converting the driving track of the vehicle into a back driving track in response to failure of planning the normal driving track;

7. An electronic device comprising a memory for storing computer instructions executable on the processor for implementing the method of any one of claims 1 to 5 when the computer instructions are executed.

8. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method of any of claims 1 to 5.