CN118331257A - Obstacle avoidance method and device for distributed power trailer - Google Patents

Abstract

The application relates to the technical field of intelligent driving, in particular to an obstacle avoidance method and device of a distributed power trailer, wherein the method comprises the following steps: detecting whether a target trailer is in a preset collision working condition or not, matching a target barrier in the current environment with the most relevant vehicle body of the target trailer, and generating a unit obstacle avoidance track of the most relevant vehicle body based on preset constraint conditions and preset cost functions of the target trailer; and obtaining independent obstacle avoidance tracks of each vehicle body in all the vehicle bodies of the target trailer by the unit obstacle avoidance tracks, so as to control each vehicle body to avoid the obstacle by utilizing the independent obstacle avoidance tracks. According to the embodiment of the application, under the condition that the trailer has collision risk, the vehicle body with the largest correlation with the collision risk in the trailer is detected to be the most correlated vehicle body, and the independent obstacle avoidance control of each vehicle body of the trailer is realized by planning the obstacle avoidance track of the most correlated vehicle body, so that the safety and the intelligence of vehicle driving are stronger.

Description

Obstacle avoidance method and device for distributed power trailer

Technical Field

The application relates to the technical field of intelligent driving, in particular to an obstacle avoidance method and device of a distributed power trailer.

Background

With the development of automatic driving technology, the autonomous driving tractor and trailer system realizes flexible automatic transfer of goods, and effectively liberates productivity. In the related art, there are emerging distributed power tractor and trailer systems, wherein each trailer is added with a sensor, a controller, a power unit and the like, and each vehicle body is independently controlled by a distributed power source.

However, in the related art, because the conventional tractor and the trailer belong to an underactuated system, the obstacle avoidance method of the conventional tractor and the trailer system is controlled only by aiming at the tractor, so that the situations of different front and rear vehicle movement tracks, large swept area, increased vision blind areas and the like are easily generated, the track planning method of the conventional tractor and the trailer system is low in instantaneity, dynamic obstacles in the vehicle driving process cannot be avoided in time, the high-quality application requirements of the emerging distributed power tractor and the trailer system are difficult to meet, the safety guarantee of vehicle driving is reduced, and the reliability of the vehicle is insufficient.

Disclosure of Invention

The application provides an obstacle avoidance method and device for a distributed power trailer, which aim at solving the problems that the traditional tractor and the trailer belong to an underactuated system, the obstacle avoidance method aiming at the traditional tractor and the trailer system is only controlled aiming at the tractor, the situations of different front and rear vehicle movement tracks, large swept area, increased vision blind areas and the like are easy to occur, the track planning method for the traditional tractor and the trailer system is low in instantaneity, dynamic obstacles in the running process of the vehicle cannot be avoided in time, practical application in the emerging distributed power tractor and the trailer system is difficult to realize, the safety guarantee of vehicle driving is reduced, the reliability of the vehicle is insufficient and the like.

An embodiment of a first aspect of the present application provides an obstacle avoidance method for a distributed power trailer, including the steps of: detecting whether a target trailer is in a preset collision working condition or not; under the condition that the target trailer is detected to be in the preset collision working condition, matching a most relevant vehicle body of the target trailer based on a target obstacle of a current environment; generating a unit obstacle avoidance track of the most relevant vehicle body based on a preset constraint condition and a preset cost function of the target trailer; and obtaining independent obstacle avoidance tracks of each vehicle body in all the vehicle bodies of the target trailer by the unit obstacle avoidance tracks, and controlling each vehicle body to avoid an obstacle by utilizing the independent obstacle avoidance tracks.

Optionally, in one embodiment of the present application, the target obstacle based on the current environment matches the most relevant vehicle body of the target trailer, including: generating a trailer virtual wall by utilizing the initial planning track of the target trailer, wherein the trailer virtual wall comprises a near collision side wall surface and a far collision side wall surface; calculating the collision time of the target obstacle with the near-collision side wall surface and/or the far-collision side wall surface based on the predicted track of the target obstacle; and calculating a collision estimated point of the target trailer according to the collision moment so as to confirm the most relevant vehicle body according to the collision estimated point.

Optionally, in one embodiment of the present application, the identifying the most relevant vehicle body according to the collision estimation point includes: judging whether the collision estimation point is in a preset connection area or not; and if the collision estimation point is in the preset connection area, judging that the car body behind the collision estimation point is the most relevant car body.

Optionally, in one embodiment of the present application, the obtaining, by the unit obstacle avoidance trajectory, an independent obstacle avoidance trajectory for each of all the bodies of the target trailer includes: under the condition that the relative position of the current car body is the front car body position of the most relevant car body, acquiring an independent obstacle avoidance track of a car body of a later section of the current car body; and calculating the independent obstacle avoidance track of the current car body in the preset feasible range of all the front car bodies of the most relevant car bodies based on the independent obstacle avoidance track of the next car body, the most relevant car body path constraint, the preset constraint condition and the preset cost function.

Optionally, in one embodiment of the present application, the obtaining, by the unit obstacle avoidance trajectory, an independent obstacle avoidance trajectory for each of all the bodies of the target trailer includes: and under the condition that the relative position of the current vehicle body is the rear vehicle body position of the most relevant vehicle body, judging that the independent obstacle avoidance track of the current vehicle body is the unit obstacle avoidance track.

An embodiment of a second aspect of the present application provides an obstacle avoidance device for a distributed power trailer, comprising: the detection module is used for detecting whether the target trailer is in a preset collision working condition or not; the matching module is used for matching the most relevant vehicle body of the target trailer based on the target obstacle of the current environment under the condition that the target trailer is detected to be in the preset collision working condition; the generation module is used for generating a unit obstacle avoidance track of the most relevant vehicle body based on a preset constraint condition and a preset cost function of the target trailer; the obstacle avoidance module is used for obtaining independent obstacle avoidance tracks of each vehicle body in all the vehicle bodies of the target trailer through the unit obstacle avoidance tracks so as to control each vehicle body to avoid an obstacle by utilizing the independent obstacle avoidance tracks.

Optionally, in one embodiment of the present application, the matching module includes: the generating unit is used for generating a trailer virtual wall by utilizing the initial planning track of the target trailer, wherein the trailer virtual wall comprises a near collision side wall surface and a far collision side wall surface; a first calculation unit configured to calculate a collision time of the target obstacle with the near-collision side wall surface and/or the far-collision side wall surface based on a predicted trajectory of the target obstacle; and a confirmation unit for calculating a collision estimation point of the target trailer from the collision time to confirm the most relevant vehicle body according to the collision estimation point.

Optionally, in one embodiment of the present application, the confirmation unit is specifically configured to: judging whether the collision estimation point is in a preset connection area or not; and if the collision estimation point is in the preset connection area, judging that the car body behind the collision estimation point is the most relevant car body.

Optionally, in one embodiment of the present application, the obstacle avoidance module includes: the acquisition unit is used for acquiring an independent obstacle avoidance track of a later section of the current vehicle body under the condition that the relative position of the current vehicle body is the front vehicle body position of the most relevant vehicle body; the second calculation unit is used for calculating the independent obstacle avoidance track of the current car body in the preset feasible range of all the front car bodies of the most relevant car bodies based on the independent obstacle avoidance track of the next car body, the most relevant car body path constraint, the preset constraint condition and the preset cost function.

Optionally, in one embodiment of the present application, the obstacle avoidance module includes: and the judging unit is used for judging that the independent obstacle avoidance track of the current vehicle body is the unit obstacle avoidance track under the condition that the relative position of the current vehicle body is the rear vehicle body position of the most relevant vehicle body.

An embodiment of a third aspect of the present application provides a distributed power trailer, which is used to implement the obstacle avoidance method of the distributed power trailer according to the above embodiment.

An embodiment of a fourth aspect of the present application provides an electronic device, including: the system comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the program to realize the obstacle avoidance method of the distributed power trailer.

A fifth aspect of the present application provides a computer readable storage medium storing a computer program which when executed by a processor implements a method of obstacle avoidance for a distributed power trailer as above.

A sixth aspect of the present application embodiment provides a computer program which, when executed, implements a method of obstacle avoidance for a distributed power trailer as above.

According to the embodiment of the application, under the condition that the trailer has collision risk, the vehicle body with the largest correlation with the collision risk in the trailer is detected to be the most correlated vehicle body, and the independent obstacle avoidance control of each vehicle body of the trailer is realized by planning the obstacle avoidance track of the most correlated vehicle body, so that the safety and the intelligence of vehicle driving are stronger. Therefore, the problems that the traditional tractor and the trailer belong to an underactuated system, the obstacle avoidance method aiming at the traditional tractor and the trailer system only aims at controlling the tractor, the situations of different front and rear vehicle movement tracks, large swept area, increased visual field blind areas and the like are easy to generate, the track planning method for the traditional tractor and the trailer system is low in instantaneity, dynamic obstacles in the vehicle driving process cannot be avoided in time, the high-quality application requirements of the emerging distributed power tractor and the trailer system are difficult to meet, the safety guarantee of vehicle driving is reduced, the reliability of the vehicle is insufficient and the like are solved.

Additional aspects and advantages of the application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the application.

Drawings

The foregoing and/or additional aspects and advantages of the application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:

FIG. 1 is a flow chart of a method for obstacle avoidance for a distributed power trailer according to an embodiment of the present application;

FIG. 2 is a schematic diagram of projective transformation based on Frenet coordinate system according to one embodiment of the present application;

FIG. 3 is a schematic diagram illustrating the discrimination of the most relevant vehicle body according to an embodiment of the present application;

FIG. 4 is a schematic diagram of a space-time diagram marker according to an embodiment of the present application;

FIG. 5 is a schematic representation of an improvement of the EM algorithm of one embodiment of the present application;

FIG. 6 is a schematic illustration of a change in track of a lead vehicle in accordance with one embodiment of the application;

FIG. 7 is a schematic diagram of an obstacle avoidance process for a distributed power trailer in accordance with one embodiment of the present application;

FIG. 8 is a schematic diagram of a distributed power trailer obstacle avoidance device according to an embodiment of the present application;

Fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present application and should not be construed as limiting the application.

The following describes an obstacle avoidance method and device of a distributed power trailer according to an embodiment of the present application with reference to the accompanying drawings. Aiming at the problems that the traditional tractor and the trailer belong to an underactuated system, the obstacle avoidance method of the traditional tractor and the trailer system only aims at controlling the tractor, the situations of different front and rear vehicle movement tracks, large swept area, increased vision blind areas and the like are easy to occur, the track planning method of the traditional tractor and the trailer system is low in instantaneity, dynamic obstacles in the running process of the vehicle cannot be avoided in time, the requirements of high-quality application in the emerging distributed power tractor and the trailer system are difficult to meet, the safety guarantee of vehicle driving is reduced, and the reliability of the vehicle is insufficient. Therefore, the problems that the traditional tractor and the trailer belong to an underactuated system, the obstacle avoidance method aiming at the traditional tractor and the trailer system only aims at controlling the tractor, the situations of different front and rear vehicle movement tracks, large swept area, increased visual field blind areas and the like are easy to generate, the track planning method for the traditional tractor and the trailer system is low in instantaneity, dynamic obstacles in the vehicle driving process cannot be avoided in time, the requirements of high-quality application in the emerging distributed power tractor and the trailer system are difficult to meet, the safety guarantee of vehicle driving is reduced, the reliability of the vehicle is insufficient and the like are solved.

Specifically, fig. 1 is a schematic flow chart of an obstacle avoidance method of a distributed power trailer according to an embodiment of the present application.

As shown in fig. 1, the obstacle avoidance method of the distributed power trailer comprises the following steps:

in step S101, it is detected whether the target trailer is in a preset collision condition.

It should be noted that the preset collision condition may be set by those skilled in the art according to actual situations, and is not specifically limited herein.

It will be appreciated that in the embodiments of the present application, the target trailer may be a new trailer system with sensors, controllers, power units, etc. added, where the sensors of the new trailer system may meet the requirements that each vehicle may detect the surrounding environment, scan for static obstacles, determine the trajectory of moving obstacles, each vehicle may have a power unit that may be controlled independently, and may implement steering control, each vehicle may communicate with other vehicles, and obtain other vehicle information.

Specifically, global planning can be performed according to a kinematic model of a target trailer, according to initial static barriers, vehicle start and end postures and other information in a priori map, a collision-free initial path is generated by considering kinematic constraints of a tractor and a trailer system through a track planning algorithm, tracking of the track is achieved by controlling an independent power unit and a steering mechanism of each section of the trailer body through a controller of each section of the trailer body according to the track planning result, surrounding environments are detected through sensors on each section of the trailer body of the target trailer, dynamic barriers which are possibly threatening the surrounding are detected, prediction is performed according to the original planned track of the target trailer and future movement trends of the barriers, and if the dynamic barriers possibly collide with the vehicle, the target trailer is judged to be in a preset collision working condition.

In the actual implementation process, the vehicle kinematic model can be added into the algorithm based on the mixed A algorithm, when the path planning node search is carried out, the next node expanded from the current node is not the midpoint of the network grid any more, but the node to which the vehicle can travel, and the position of the next node can appear at any position of the grid area, so that the path searched by the algorithm can meet the vehicle kinematic constraint.

Because the target trailer has inter-vehicle communication, the rear vehicle can acquire the track of the front vehicle through communication, and the rear vehicle defaults to travel along the same track with the front vehicle under the condition that no new moving obstacle exists. In the track tracking control link, the applied sensors can be hinge force sensors, vehicle speed sensors, vehicle acceleration sensors, angular acceleration sensors, satellite positioning and the like among the vehicle bodies. For example, the horizontal and longitudinal forces of front and rear hinges (couplers) can be obtained through hinge force sensors between the vehicle bodies, the current speed of the vehicle can be obtained through a vehicle speed sensor, the acceleration of the vehicle can be obtained through an acceleration sensor, the angle of the vehicle can be obtained through an angular acceleration sensor, the vehicle can be positioned through satellites, the current pose of the vehicle body can be obtained through calculation, the current pose of the vehicle body can be substituted into the kinematics and dynamics models of the tractor and the trailer, and the expected motion state of each vehicle body can be obtained through expected tracks. The device can be divided into transverse control and longitudinal control, and the independent power unit and steering mechanism of each car body are controlled to complete tracking of the preset track.

In dynamic obstacle detection, a laser radar or other sensors in the sensor can be used for detecting obstacles in a scene to form a point cloud image, and the positions of the obstacles are marked in the point cloud image. For moving the obstacle, the position information of the obstacle in a plurality of sampling periods can be obtained, and the moving track of the obstacle can be predicted according to the moving state of the current obstacle.

In step S102, in the case where it is detected that the target trailer is in the preset collision condition, the target obstacle based on the current environment matches the most relevant vehicle body of the target trailer.

It will be appreciated that in embodiments of the present application, the most relevant vehicle bodies may be determined based on projective transformation. The rear vehicle runs according to the track of the front vehicle by default, the track of the head vehicle can be used as a reference path, and the trailer and the obstacle are projected and transformed into the same coordinate system. The speed of the trailer system of the tractor and the track speed of the predicted dynamic obstacle can be used for calculating the corresponding vehicle body of the first collision between the moving obstacle and the trailer under the current track condition, and the most relevant vehicle body is obtained by matching

For example, the most relevant vehicle body is determined based on projective transformation, which enters the same coordinate system, and Frenet coordinate system can be adopted. The method for judging the most relevant vehicle body by projective transformation based on the Frenet coordinate system mainly comprises the following steps: establishing a Frenet coordinate system, wherein all the vehicle bodies run along the same track by default, and the tractor track can be used as a guide wire, so that the Frenet coordinate system is established; all the bodies and moving obstacles of the tractor and trailer system are projected and transformed into a Frenet coordinate system, as shown in FIG. 2, which is a projection transformation schematic diagram based on the Frenet coordinate system according to one embodiment of the application, at this time, the tractor and trailer system should travel along the s-axis, and the most relevant bodies are determined by the speed of the trailer and the track speed of the obstacles.

Optionally, in one embodiment of the present application, the target obstacle based on the current environment matches the most relevant body of the target trailer, including: generating a trailer virtual wall by utilizing an initial planning track of a target trailer, wherein the trailer virtual wall comprises a near collision side wall surface and a far collision side wall surface; calculating the collision time of the target obstacle and the near-collision side wall surface and/or the far-collision side wall surface based on the predicted track of the target obstacle; and calculating a collision estimated point of the target trailer from the collision time to confirm the most relevant vehicle body according to the collision estimated point.

In the actual execution process, all the vehicle bodies of the target trailer travel along the same initial planned track, can be regarded as all traveling along the S axis in the transformed Frenet coordinate system, the center of the vehicle body is on the S axis, the vehicle body can be simplified into two straight lines on two sides of the S axis under the Frenet coordinate system of the target trailer after projection transformation, the distance between the two straight lines can be slightly wider than the length of the vehicle body, and the two straight lines are symmetrically distributed on two sides of the S axis, so that the vehicle body is used as a virtual wall of the trailer of the target trailer, one side close to a collided object is a near-collision side wall surface, and one side far away from the collided object is a far-collision side wall surface.

Specifically, as shown in fig. 3, a schematic diagram of determining the most relevant vehicle body according to an embodiment of the present application is shown. The method can be based on the virtual wall of the trailer, judge according to the current predicted track of the moving obstacle, and when the moving obstacle collides with any side wall surface of the virtual wall of the trailer, the moving obstacle is regarded as colliding with the vehicle body, and the predicted collision moment is recorded. And calculating the pose of the vehicle at the moment of collision according to the predicted moment of collision and the track speed of the vehicle, so as to obtain a collision estimated point, judging the position of the specific vehicle body corresponding to the collision estimated point, and taking the vehicle body as the most relevant vehicle body.

For example, if the estimated point of collision is in front of the whole vehicle near the collision side wall, the moving track of the moving obstacle needs to be continuously calculated until the obstacle completely passes through the far collision side wall (tangency), the passing time of the obstacle is recorded, the pose of the vehicle at the time is calculated again, if the passing time of the obstacle is not in front of the pose of the vehicle at the time, the tractor (the head car) is judged to be the most relevant vehicle body, otherwise, the moving obstacle is considered to not influence the vehicle, namely, the collision time of the target obstacle and the far collision side wall is obtained.

Optionally, in one embodiment of the present application, identifying the most relevant vehicle body according to the collision estimation point includes: judging whether the collision estimation point is in a preset connection area or not; if the collision estimation point is in the preset connection area, the next car body of the collision estimation point is judged to be the most relevant car body.

It should be noted that the preset connection area may be set by a person skilled in the art according to the actual situation, and is not specifically limited herein.

In the actual execution process, if the collision estimation point is between two sections of the vehicle bodies, the collision estimation point is considered to be in a preset connection area of the target trailer, namely a connection area between the two vehicle bodies, and the next section of the vehicle body is judged to be the most relevant vehicle body.

In step S103, a unit obstacle avoidance trajectory of the most relevant vehicle body is generated based on the preset constraint condition and the preset cost function of the target trailer.

It should be noted that the preset constraint condition and the preset cost function may be set by those skilled in the art according to the actual situation, and are not specifically limited herein.

It can be understood that, in the embodiment of the present application, the route may be re-planned based on the most relevant vehicle body obtained in the above steps, centering on the most relevant vehicle body. The preset constraint conditions can comprise constraint of vehicle kinematics, collision avoidance constraint and boundary value constraint, meanwhile, whether the most relevant vehicle body and the subsequent vehicle body can run along the track or not is considered, a target cost function is established according to an actual scene, a path of the most relevant vehicle body is re-planned, and a new collision-free path aiming at the most relevant vehicle body is generated and used as a unit obstacle avoidance track of the most relevant vehicle body.

For example, the unit obstacle avoidance trajectories of the most relevant vehicle bodies can be generated by utilizing a target cost function according to a space-time diagram method. The three-dimensional space-time diagram S-L-T diagram is established, the time dimension is increased on the basis of the Frenet coordinate system S-L diagram, and the time dimension can reflect the relation between the dynamic barrier and the vehicle in space-time; marking information of the obstacle in a space-time diagram according to the predicted information of the obstacle track, as shown in fig. 4, which is a schematic diagram of space-time diagram marking according to one embodiment of the application; and according to the constraint of the most relevant vehicle body, searching and solving in the three-dimensional space-time diagram to obtain a feasible collision-free track serving as a unit obstacle avoidance track of the most relevant vehicle body. In particular, in the case of a portion where a speed planning is performed, an overall vehicle model is considered, and only the most relevant vehicle body cannot be considered, and in the S-L dimension, since the vehicles travel along the same trajectory, the overall vehicle body can be judged as a whole.

For another example, an EM (motion-mapping) algorithm may be used, as shown in fig. 5, which is a schematic diagram of an improvement of the EM algorithm according to an embodiment of the present application. In fig. 5 (a), the existing EM algorithm performs a preliminary estimation by means of the nominal driving trajectory χ _norm, which can be set as the trajectory over a period on the most relevant vehicle body; and then analyzing the collision condition of χ _norm and all moving/static obstacles in the environment, marking the position of the obstacle at the moment of collision as a whole obstacle, establishing a corresponding cost function and constraint by a sampling search and optimization method, obtaining a fine path χ for avoiding the marked obstacle, replacing χ _norm with χ, and repeating the steps until the obtained trajectory χ does not collide with the obstacle in the environment. In fig. 5 (b), for the novel trailer system of the present application, it is noted that in planning a fine path, all the vehicles need to detour the obstacle from the same side due to the existence of the hinge constraint, so it is necessary to add a tunnel filling area in the direction in which the moving obstacle initially approaches, preventing the vehicles from detouring from that side.

In step S104, an independent obstacle avoidance track of each vehicle body in all vehicle bodies of the target trailer is obtained from the unit obstacle avoidance tracks, so that each vehicle body is controlled to avoid an obstacle by using the independent obstacle avoidance track.

It can be understood that in the embodiment of the application, corresponding track adjustment can be performed on other vehicle bodies according to the unit obstacle avoidance track of the most relevant vehicle body. Considering the kinematic model of the target trailer and the collision avoidance constraint on the obstacle, recursively obtaining new paths of other vehicle bodies to two sides, and when the trajectories of other vehicle bodies are planned again, enabling the most relevant vehicle bodies to meet the paths designed in the previous step. And then, according to the condition of the obstacle, carrying out speed re-planning on the whole tractor and trailer system to form a complete obstacle avoidance track, and realizing independent obstacle avoidance control among all the vehicle bodies.

Optionally, in one embodiment of the present application, obtaining the independent obstacle avoidance track of each of all the bodies of the target trailer from the unit obstacle avoidance tracks includes: under the condition that the relative position of the current car body is the front car body position of the most relevant car body, acquiring an independent obstacle avoidance track of a rear car body of the current car body; based on the independent obstacle avoidance track of the next section of vehicle body, the most relevant vehicle body path constraint, the preset constraint condition and the preset cost function, calculating the independent obstacle avoidance track of the current vehicle body in the preset feasible range of all the front vehicle bodies of the most relevant vehicle body.

It should be noted that the preset feasible range may be set by those skilled in the art according to actual situations, and is not specifically limited herein.

In the actual execution process, for a single or a plurality of front vehicle bodies with relative positions in front of the most relevant vehicle bodies in the whole vehicle body distribution, taking preset constraint conditions such as a kinematic model of a target trailer and the like into consideration, searching in a feasible range of the front vehicle according to a planning result of the most relevant vehicle bodies, and finding out a track which can meet the most relevant vehicle bodies as an independent obstacle avoidance track of the current vehicle body at the front vehicle body position.

Besides the kinematic constraint of the objective cost function, the constraint of the most relevant vehicle body path and the collision avoidance constraint, the front vehicle track should be made to coincide with the track of the most relevant vehicle body as soon as possible, as shown in fig. 6, which is a schematic diagram of the front vehicle track change in one embodiment of the application, since the influence of the subsequent obstacle is considered when the most relevant vehicle body path is rescheduled, the obstacle avoidance is not needed to be considered after the front vehicle track coincides with the most relevant vehicle body track. After the track of the front vehicle is re-planned, gradually recursively pushing the next adjacent front vehicle according to the re-planned path of the current vehicle body until the front vehicle path of the most relevant vehicle body can meet the conditions.

Optionally, in one embodiment of the present application, obtaining the independent obstacle avoidance track of each of all the bodies of the target trailer from the unit obstacle avoidance tracks includes: and under the condition that the relative position of the current vehicle body is the rear vehicle body position of the most relevant vehicle body, judging that the independent obstacle avoidance track of the current vehicle body is a unit obstacle avoidance track.

In the actual execution process, for a single or a plurality of rear vehicle bodies with relative positions behind the most relevant vehicle bodies in the whole vehicle body distribution, the vehicle is defaulted to run along the same path with the front vehicle, namely, the vehicle is subjected to obstacle avoidance running according to the unit obstacle avoidance tracks obtained in the steps.

The working of the embodiment of the present application will be described in detail in the following. Fig. 7 is a schematic diagram of an obstacle avoidance process of a distributed power trailer according to an embodiment of the present application.

Step S701: and (5) initial global path planning.

And performing global planning based on a kinematic model of the target trailer to generate an initial collision-free path.

Step S702: and (5) track tracking control.

And according to the result of the track planning, the controller of each car body controls the independent power unit and steering mechanism of each car body to track the track.

Step S703: dynamic obstacle detection.

Wherein, through the sensor on each car body, detect whether there is the dynamic obstacle in the surrounding environment, if there is, go to step S704, otherwise go to step S702.

Step S704: the most relevant vehicle body is judged based on projective transformation.

The method comprises the steps of projecting and transforming a target trailer and an obstacle into the same coordinate system, and obtaining the most relevant vehicle body by the speed of the target trailer and the track speed of the predicted dynamic obstacle.

Step S705: and (5) planning the most relevant vehicle body again.

The route of the most relevant vehicle body is re-planned, and a new collision-free route aiming at the most relevant vehicle body is generated.

Step S706: and planning the track of other vehicle bodies in a recursive manner.

According to the planning result of the most relevant vehicle body, collision avoidance constraint of the obstacle is considered, new paths of other vehicle bodies are recursively obtained to two sides, and circulation tracking control of the track is realized according to environment transformation of the target trailer.

According to the obstacle avoidance method of the distributed power trailer, provided by the embodiment of the application, the vehicle body with the largest collision risk correlation in the trailer can be detected as the most relevant vehicle body under the condition that the trailer has collision risk, and the independent obstacle avoidance control of each vehicle body of the trailer is realized by planning the obstacle avoidance track of the most relevant vehicle body, so that the safety and the intelligence of vehicle driving are stronger. Therefore, the problems that the traditional tractor and the trailer belong to an underactuated system, the obstacle avoidance method aiming at the traditional tractor and the trailer system only aims at controlling the tractor, the situations of different front and rear vehicle movement tracks, large swept area, increased visual field blind areas and the like are easy to generate, the track planning method for the traditional tractor and the trailer system is low in instantaneity, dynamic obstacles in the vehicle driving process cannot be avoided in time, the requirements of high-quality application in the emerging distributed power tractor and the trailer system are difficult to meet, the safety guarantee of vehicle driving is reduced, the reliability of the vehicle is insufficient and the like are solved.

Next, an obstacle avoidance device of a distributed power trailer according to an embodiment of the present application will be described with reference to the accompanying drawings.

Fig. 8 is a schematic structural view of an obstacle avoidance device of a distributed power trailer according to an embodiment of the present application.

As shown in fig. 8, the obstacle avoidance device 10 of the distributed power trailer includes: the device comprises a detection module 100, a matching module 200, a generation module 300 and an obstacle avoidance module 400.

The detection module 100 is configured to detect whether the target trailer is in a preset collision condition.

And the matching module 200 is used for matching the most relevant vehicle body of the target trailer based on the target obstacle of the current environment under the condition that the target trailer is detected to be in the preset collision working condition.

The generating module 300 is configured to generate a unit obstacle avoidance track of the most relevant vehicle body based on a preset constraint condition and a preset cost function of the target trailer.

The obstacle avoidance module 400 is configured to obtain an independent obstacle avoidance track of each vehicle body in all vehicle bodies of the target trailer from the unit obstacle avoidance tracks, so as to control each vehicle body to avoid an obstacle by using the independent obstacle avoidance track.

Optionally, in one embodiment of the present application, the matching module 200 includes: the device comprises a generating unit, a first calculating unit and a confirming unit.

The generating unit is used for generating a trailer virtual wall by utilizing an initial planning track of a target trailer, wherein the trailer virtual wall comprises a near collision side wall surface and a far collision side wall surface.

And the first calculating unit is used for calculating the collision time of the target obstacle and the near-collision side wall surface and/or the far-collision side wall surface based on the predicted track of the target obstacle.

And a confirmation unit for calculating a collision estimation point of the target trailer from the collision time to confirm the most relevant vehicle body from the collision estimation point.

Optionally, in one embodiment of the present application, the confirmation unit is specifically configured to: judging whether the collision estimation point is in a preset connection area or not; if the collision estimation point is in the preset connection area, the next car body of the collision estimation point is judged to be the most relevant car body.

Optionally, in one embodiment of the present application, the obstacle avoidance module 400 includes: an acquisition unit and a second calculation unit.

The acquisition unit is used for acquiring the independent obstacle avoidance track of the next section of the current vehicle body under the condition that the relative position of the current vehicle body is the front vehicle body position of the most relevant vehicle body.

The second calculation unit is used for calculating the independent obstacle avoidance track of the current car body in the preset feasible range of all the front car bodies of the most relevant car bodies based on the independent obstacle avoidance track of the next car body, the most relevant car body path constraint, the preset constraint condition and the preset cost function.

Optionally, in one embodiment of the present application, the obstacle avoidance module 400 includes: and a determination unit.

The judging unit is used for judging that the independent obstacle avoidance track of the current vehicle body is a unit obstacle avoidance track under the condition that the relative position of the current vehicle body is the rear vehicle body position of the most relevant vehicle body.

It should be noted that the explanation of the embodiment of the obstacle avoidance method of the distributed power trailer is also applicable to the obstacle avoidance device of the distributed power trailer of the embodiment, and will not be repeated here.

According to the obstacle avoidance device of the distributed power trailer, provided by the embodiment of the application, the vehicle body with the largest collision risk correlation in the trailer can be detected as the most relevant vehicle body under the condition that the trailer has collision risk, and the independent obstacle avoidance control of each vehicle body of the trailer is realized by planning the obstacle avoidance track of the most relevant vehicle body, so that the safety and the intelligence of vehicle driving are stronger. Therefore, the problems that the traditional tractor and the trailer belong to an underactuated system, the obstacle avoidance method aiming at the traditional tractor and the trailer system only aims at controlling the tractor, the situations of different front and rear vehicle movement tracks, large swept area, increased visual field blind areas and the like are easy to generate, the track planning method for the traditional tractor and the trailer system is low in instantaneity, dynamic obstacles in the vehicle driving process cannot be avoided in time, the requirements of high-quality application in the emerging distributed power tractor and the trailer system are difficult to meet, the safety guarantee of vehicle driving is reduced, the reliability of the vehicle is insufficient and the like are solved.

Fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application. The electronic device may include:

Memory 901, processor 902, and a computer program stored on memory 901 and executable on processor 902.

The processor 902 implements the obstacle avoidance method of the distributed power trailer provided in the above embodiments when executing a program.

Further, the electronic device further includes:

A communication interface 903 for communication between the memory 901 and the processor 902.

Memory 901 for storing a computer program executable on processor 902.

Memory 901 may comprise high-speed RAM memory or may also include non-volatile memory (non-volatile memory), such as at least one disk memory.

If the memory 901, the processor 902, and the communication interface 903 are implemented independently, the communication interface 903, the memory 901, and the processor 902 may be connected to each other through a bus and perform communication with each other. The bus may be an industry standard architecture (Industry Standard Architecture, abbreviated ISA) bus, an external device interconnect (PERIPHERAL COMPONENT INTERCONNECT, abbreviated PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, abbreviated EISA) bus, among others. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, only one thick line is shown in fig. 9, but not only one bus or one type of bus.

Alternatively, in a specific implementation, if the memory 901, the processor 902, and the communication interface 903 are integrated on a chip, the memory 901, the processor 902, and the communication interface 903 may communicate with each other through internal interfaces.

The processor 902 may be a central processing unit (Central Processing Unit, abbreviated as CPU), or an Application SPECIFIC INTEGRATED Circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the application.

The embodiment also provides a distributed power trailer for realizing the obstacle avoidance method of the distributed power trailer.

The present embodiment also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor implements the obstacle avoidance method of a distributed power trailer as above.

The embodiment also provides a computer program which is executed to realize the obstacle avoidance method of the distributed power trailer.

In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or N embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.

Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, "N" means at least two, for example, two, three, etc., unless specifically defined otherwise.

Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and additional implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order from that shown or discussed, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present application.

Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or N wires, a portable computer cartridge (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.

It is to be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the N steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As with the other embodiments, if implemented in hardware, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.

Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.

In addition, each functional unit in the embodiments of the present application may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product.

The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like. While embodiments of the present application have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the application, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the application.

Claims (10)

1. The obstacle avoidance method of the distributed power trailer is characterized by comprising the following steps of:

detecting whether a target trailer is in a preset collision working condition or not;

under the condition that the target trailer is detected to be in the preset collision working condition, matching a most relevant vehicle body of the target trailer based on a target obstacle of a current environment;

Generating a unit obstacle avoidance track of the most relevant vehicle body based on a preset constraint condition and a preset cost function of the target trailer;

And obtaining independent obstacle avoidance tracks of each vehicle body in all the vehicle bodies of the target trailer by the unit obstacle avoidance tracks, and controlling each vehicle body to avoid an obstacle by utilizing the independent obstacle avoidance tracks.

2. The method of claim 1, wherein the current environment-based target obstacle matches a most relevant body of the target trailer, comprising:

Generating a trailer virtual wall by utilizing the initial planning track of the target trailer, wherein the trailer virtual wall comprises a near collision side wall surface and a far collision side wall surface;

Calculating the collision time of the target obstacle with the near-collision side wall surface and/or the far-collision side wall surface based on the predicted track of the target obstacle;

And calculating a collision estimated point of the target trailer according to the collision moment so as to confirm the most relevant vehicle body according to the collision estimated point.

3. The method of claim 2, wherein said identifying the most relevant vehicle body from the collision estimation point comprises:

Judging whether the collision estimation point is in a preset connection area or not;

and if the collision estimation point is in the preset connection area, judging that the car body behind the collision estimation point is the most relevant car body.

4. The method of claim 1, wherein the deriving from the unit obstacle avoidance trajectory an independent obstacle avoidance trajectory for each of all bodies of the target trailer comprises:

Under the condition that the relative position of the current car body is the front car body position of the most relevant car body, acquiring an independent obstacle avoidance track of a car body of a later section of the current car body;

And calculating the independent obstacle avoidance track of the current car body in the preset feasible range of all the front car bodies of the most relevant car bodies based on the independent obstacle avoidance track of the next car body, the most relevant car body path constraint, the preset constraint condition and the preset cost function.

5. The method of claim 1, wherein the deriving from the unit obstacle avoidance trajectory an independent obstacle avoidance trajectory for each of all bodies of the target trailer comprises:

and under the condition that the relative position of the current vehicle body is the rear vehicle body position of the most relevant vehicle body, judging that the independent obstacle avoidance track of the current vehicle body is the unit obstacle avoidance track.

6. An obstacle avoidance device for a distributed power trailer, comprising:

the detection module is used for detecting whether the target trailer is in a preset collision working condition or not;

the matching module is used for matching the most relevant vehicle body of the target trailer based on the target obstacle of the current environment under the condition that the target trailer is detected to be in the preset collision working condition;

The generation module is used for generating a unit obstacle avoidance track of the most relevant vehicle body based on a preset constraint condition and a preset cost function of the target trailer;

The obstacle avoidance module is used for obtaining independent obstacle avoidance tracks of each vehicle body in all the vehicle bodies of the target trailer through the unit obstacle avoidance tracks so as to control each vehicle body to avoid an obstacle by utilizing the independent obstacle avoidance tracks.

7. A distributed power trailer for implementing the obstacle avoidance method of the distributed power trailer as claimed in any one of claims 1 to 5.

8. An electronic device, comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the obstacle avoidance method of the distributed power trailer as claimed in any one of claims 1 to 5.

9. A computer readable storage medium having stored thereon a computer program, wherein the program is executed by a processor for implementing the obstacle avoidance method of a distributed power trailer as claimed in any one of claims 1 to 5.

10. A computer program, characterized in that it is executed for implementing an obstacle avoidance method of a distributed power trailer as claimed in any one of claims 1-5.