CN111619560A

CN111619560A - Vehicle control method and device

Info

Publication number: CN111619560A
Application number: CN202010745716.XA
Authority: CN
Inventors: 白钰; 马杰; 许笑寒; 任冬淳
Original assignee: Beijing Sankuai Online Technology Co Ltd
Current assignee: Beijing Sankuai Online Technology Co Ltd
Priority date: 2020-07-29
Filing date: 2020-07-29
Publication date: 2020-09-04
Anticipated expiration: 2040-07-29
Also published as: CN111619560B

Abstract

The specification discloses a vehicle control method and a vehicle control device, wherein the position and the speed of each obstacle are determined by acquiring point cloud data corresponding to a vehicle surrounding environment and acquired by a laser radar, a lane coordinate system taking a lane as a reference is determined according to the position of the vehicle, a transverse safe distance and a longitudinal safe distance between the obstacle and the vehicle under the lane coordinate system are determined aiming at each obstacle, a safe influence characteristic value of the obstacle on the vehicle is determined according to the transverse safe distance, the longitudinal safe distance and the position of the obstacle, at least one target obstacle is selected from each obstacle according to the safe influence characteristic value of each obstacle, and the vehicle is controlled according to the information of each target obstacle and the position of the vehicle. By the method, the target barrier which is more threatening to the driving safety of the vehicle can be screened out, so that the effect of more reasonably controlling the vehicle is achieved in a complex display scene.

Description

Vehicle control method and device

Technical Field

The specification relates to the technical field of traffic safety, in particular to a vehicle control method and device.

Background

Currently, safety issues during driving of vehicles are becoming a focus of attention.

Generally, an Automatic Emergency Braking (AEB) system may be installed on a vehicle. The AEB system can monitor the driving environment in front of the vehicle in real time and automatically start a vehicle braking system to decelerate the vehicle when collision danger possibly occurs so as to avoid collision or lighten collision consequences.

The AEB system considers the driving environment in front of the vehicle, so the recognition range of the AEB system is small and is not suitable for complex real scenes, and the AEB system simply selects a target obstacle according to factors such as the distance between each obstacle and the vehicle, does not consider the actual situation in the driving process of the vehicle, and is not enough to ensure the driving safety of the vehicle.

Disclosure of Invention

The embodiment of the specification provides a vehicle control method and a vehicle control device, and aims to partially solve the problems in the prior art.

The embodiment of the specification adopts the following technical scheme:

according to the vehicle control method provided by the specification, a laser radar is installed on a vehicle and used for collecting point cloud data corresponding to the surrounding environment of the vehicle; the method comprises the following steps:

acquiring point cloud data acquired by the laser radar and the position of the vehicle;

determining information of each obstacle according to the point cloud data, wherein the information of the obstacles comprises the position and the speed of the obstacle; determining a lane where the vehicle is located according to the position of the vehicle, and determining a lane coordinate system taking the lane as a reference according to the lane;

determining a dynamic parameter corresponding to each obstacle, and determining a transverse safe distance and a longitudinal safe distance between the obstacle and the vehicle in the lane coordinate system according to the lane coordinate system, the dynamic parameter and the speed of the obstacle;

determining a safety influence characteristic value of the obstacle on the vehicle in the transverse direction according to the transverse safety distance and the position of the obstacle, and/or determining a safety influence characteristic value of the obstacle on the vehicle in the longitudinal direction according to the longitudinal safety distance and the position of the obstacle;

selecting at least one target obstacle from the obstacles according to the determined safety influence characteristic value of each obstacle;

and controlling the vehicle according to the information of the target obstacle and the position of the vehicle.

Optionally, the information of the obstacle comprises an obstacle type;

determining a dynamic parameter corresponding to the obstacle specifically includes:

and determining the dynamic parameters corresponding to the obstacles according to the predetermined corresponding relation between each obstacle type and the dynamic parameters and the obstacle type of the obstacles.

Optionally, determining a transverse safe distance and a longitudinal safe distance between the obstacle and the vehicle in the lane coordinate system according to the lane coordinate system, the dynamic parameter, and the speed of the obstacle, specifically including:

acquiring the speed of the vehicle;

determining the vehicle transverse speed and the vehicle longitudinal speed of the vehicle in the lane coordinate system according to the speed of the vehicle, and determining the obstacle transverse speed and the obstacle longitudinal speed of the obstacle in the lane coordinate system according to the speed of the obstacle;

and determining the transverse safe distance according to the vehicle transverse speed, the obstacle transverse speed and the dynamic parameters, and determining the longitudinal safe distance according to the vehicle longitudinal speed, the obstacle longitudinal speed and the dynamic parameters.

Optionally, the dynamic parameters include lateral dynamic parameters and longitudinal dynamic parameters;

according to the lane coordinate system, the dynamic parameters and the speed of the obstacle, determining a transverse safe distance and a longitudinal safe distance between the obstacle and the vehicle in the lane coordinate system, specifically comprising:

and determining the transverse safe distance according to the lane coordinate system, the transverse dynamic parameter and the speed of the obstacle, and determining the longitudinal safe distance according to the lane coordinate system, the longitudinal dynamic parameter and the speed of the obstacle.

Optionally, the dynamic parameters include a first dynamic parameter and a second dynamic parameter;

determining a first transverse safe distance and a first longitudinal safe distance between the obstacle and the vehicle in the lane coordinate system according to the lane coordinate system, the first dynamic parameter and the speed of the obstacle;

and determining a second transverse safe distance and a second longitudinal safe distance between the obstacle and the vehicle in the lane coordinate system according to the lane coordinate system, the second dynamic parameter and the speed of the obstacle.

Optionally, determining a safety influence characterization value of the obstacle on the vehicle in the transverse direction according to the transverse safety distance and the position of the obstacle, specifically including:

determining a safety influence representation value of the obstacle on the vehicle in the transverse direction according to the first transverse safety distance, the second transverse safety distance and the position of the obstacle;

according to the longitudinal safe distance and the position of the obstacle, determining a safe influence characteristic value of the obstacle on the vehicle in the longitudinal direction, specifically comprising:

and determining a safety influence representation value of the obstacle on the vehicle in the longitudinal direction according to the first longitudinal safety distance, the second longitudinal safety distance and the position of the obstacle.

Optionally, according to the lateral safety probability and the longitudinal safety probability of each obstacle, selecting at least one target obstacle from the obstacles specifically includes:

classifying the obstacles according to the relative positions of the vehicle and the obstacles;

sequencing the obstacles in each class according to the safety influence characteristic values of the obstacles in the class aiming at the obstacles in each class;

according to the sorting result, a target obstacle is selected from the obstacles in the class.

This specification provides a vehicle control device, install lidar on the vehicle at device place, lidar is used for gathering the corresponding point cloud data of vehicle surrounding environment, the device includes:

the acquisition module is used for acquiring point cloud data acquired by the laser radar and the position of the vehicle;

the first determining module is used for determining the information of each obstacle according to the point cloud data, wherein the information of each obstacle comprises the position and the speed of each obstacle; determining a lane where the vehicle is located according to the position of the vehicle, and determining a lane coordinate system taking the lane as a reference according to the lane;

the second determination module is used for determining a dynamic parameter corresponding to each obstacle, and determining a transverse safe distance and a longitudinal safe distance between the obstacle and the vehicle in the lane coordinate system according to the lane coordinate system, the dynamic parameter and the speed of the obstacle;

a third determination module, configured to determine a safety impact characteristic value of the obstacle on the vehicle in the lateral direction according to the lateral safety distance and the position of the obstacle, and/or determine a safety impact characteristic value of the obstacle on the vehicle in the longitudinal direction according to the longitudinal safety distance and the position of the obstacle;

the selection module is used for selecting at least one target obstacle from the obstacles according to the determined safety influence representation values of the obstacles;

and the first control module is used for controlling the vehicle according to the information of the target obstacle and the position of the vehicle.

The present specification provides a vehicle control method, including:

acquiring a position, a predicted track and a planned track of a vehicle, wherein the predicted track is a track which is obtained by predicting the vehicle and does not refer to information of obstacles in the surrounding environment of the vehicle, and the planned track is a track which is obtained by planning the vehicle and avoids the obstacles;

determining a lane where the vehicle is located according to the position of the vehicle, and determining a lane coordinate system taking the lane as a reference according to the lane;

determining the difference between the predicted track and the planned track in the lane coordinate system according to the lane coordinate system, the information of the predicted track and the information of the planned track;

for each region divided into the surrounding environment of the vehicle in advance, determining a safety influence characteristic value of the region on the vehicle according to the difference, wherein the safety influence characteristic value is inversely related to the difference;

and controlling the vehicle according to the safety influence representation value of each region on the vehicle.

Optionally, determining a difference between the predicted trajectory and the planned trajectory in the lane coordinate system according to the lane coordinate system, the information of the predicted trajectory, and the information of the planned trajectory specifically includes:

respectively sampling the predicted track and the planned track according to a preset time interval;

taking the sampling points in the predicted track as predicted sampling points, and taking the sampling points in the planning track as planning sampling points;

according to the time when the vehicle reaches each sampling point, determining a predicted sampling point and a planned sampling point at the same time in each sampling point;

and determining the difference between the predicted track and the planned track in the lane coordinate system according to the positions of the predicted sampling point and the planned sampling point at the same moment.

Optionally, determining the difference according to the positions of the predicted sampling point and the planned sampling point at the same time in the lane coordinate system specifically includes:

for each moment, determining the transverse distance between the predicted sampling point and the planned sampling point at the moment in the lane coordinate system according to the positions of the predicted sampling point and the planned sampling point at the moment, and taking the transverse distance as the transverse distance corresponding to the moment;

and determining the difference according to the corresponding transverse distance at each moment.

Optionally, determining the difference according to the lateral distance corresponding to each time, specifically including:

determining a first specified time and a second specified time;

determining a sum of the lateral distances corresponding to the times before the first designated time as a first sum, and determining a sum of the lateral distances corresponding to the times before the second designated time as a second sum;

determining the difference based on the first sum and the second sum.

determining the change degree of the transverse distance corresponding to any adjacent time according to the transverse distance corresponding to each time;

determining the difference based on the degree of change.

Optionally, determining a safety influence characterization value of the region on the vehicle specifically includes:

determining the acceleration of each planning sampling point;

determining the number of the planning sampling points with the accelerated speed smaller than a preset accelerated speed threshold value according to the accelerated speed of each planning sampling point;

and determining the safety influence representation value of each area on the vehicle according to the quantity and the difference.

Optionally, controlling the vehicle according to the safety influence characterization value of each region on the vehicle, specifically including:

according to the safety influence characteristic value of each area on the vehicle, determining the area with the minimum safety influence characteristic value on the vehicle as a target area in each area;

and controlling the vehicle according to the information of each obstacle in the target area.

The present specification provides a vehicle control apparatus, the apparatus including:

the device comprises an acquisition track module, a prediction track module and a planning track module, wherein the acquisition track module is used for acquiring the position of a vehicle where the device is located, the prediction track is a track which is obtained by predicting the vehicle and does not refer to information of obstacles in the surrounding environment of the vehicle, and the planning track is a track which is obtained by planning the vehicle and avoids the obstacles;

the lane determining module is used for determining a lane where the vehicle is located according to the position of the vehicle and determining a lane coordinate system which takes the lane as a reference according to the lane;

the difference determining module is used for determining the difference between the predicted track and the planned track in the lane coordinate system according to the lane coordinate system, the information of the predicted track and the information of the planned track;

the safety determination module is used for determining a safety influence characteristic value of each region on the vehicle according to the difference aiming at each region divided into the surrounding environment of the vehicle in advance, and the safety influence characteristic value is negatively related to the difference;

and the second control module is used for controlling the vehicle according to the safety influence representation value of each region on the vehicle.

The present specification provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the above-described vehicle control method.

The vehicle device provided by the specification comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor realizes the vehicle control method when executing the program.

The embodiment of the specification adopts at least one technical scheme which can achieve the following beneficial effects:

in this specification, a vehicle is equipped with a laser radar, which can acquire point cloud data corresponding to the surrounding environment of the vehicle and the position of the vehicle, the information of each obstacle is determined according to the point cloud data, the information of the obstacle includes the position and the speed of the obstacle, the lane where the vehicle is located is determined according to the position of the vehicle, a lane coordinate system with the lane as a reference is determined according to the lane, a dynamic parameter corresponding to the obstacle is determined for each obstacle, a transverse safe distance and a longitudinal safe distance between the obstacle and the vehicle in the lane coordinate system are determined according to the lane coordinate system, the dynamic parameter and the speed of the obstacle, a safe influence representation value of the obstacle on the vehicle in the transverse direction is determined according to the transverse safe distance and the position of the obstacle, and/or the longitudinal safe distance and the position of the obstacle are determined according to the transverse safe influence representation value, determining safety influence characteristic values of the obstacles on the vehicle in the longitudinal direction, selecting at least one target obstacle from the obstacles according to the determined safety influence characteristic values of the obstacles, and controlling the vehicle according to the information of the target obstacles and the position of the vehicle. By the method, the transverse safe distance and the longitudinal safe distance between the obstacles in the surrounding environment of the vehicle and the vehicle on the lane dimension can be determined, so that the target obstacles which threaten the driving safety of the vehicle can be screened out according to the information such as the speed of each obstacle, and the like, and the effect of more reasonably controlling the vehicle is achieved in a complex driving scene.

Drawings

The accompanying drawings, which are included to provide a further understanding of the specification and are incorporated in and constitute a part of this specification, illustrate embodiments of the specification and together with the description serve to explain the specification and not to limit the specification in a non-limiting sense. In the drawings:

FIG. 1 is a flow chart of a vehicle control method provided by an embodiment of the present disclosure;

fig. 2 is a schematic position diagram of a vehicle and an obstacle in a lane coordinate system according to an embodiment of the present disclosure;

FIG. 3 is a flow chart of another vehicle control method provided by the embodiments herein;

fig. 4 is a schematic diagram of a predicted trajectory and a planned trajectory in a lane coordinate system according to an embodiment of the present disclosure;

fig. 5 is a schematic structural diagram of a vehicle control device provided in an embodiment of the present specification;

fig. 6 is a schematic structural diagram of another vehicle control device provided in the embodiment of the present disclosure;

fig. 7 is a schematic diagram of a vehicle device corresponding to fig. 1 provided in an embodiment of the present specification.

Detailed Description

In order to make the objects, technical solutions and advantages of the present disclosure more clear, the technical solutions of the present disclosure will be clearly and completely described below with reference to the specific embodiments of the present disclosure and the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present disclosure, and not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present specification without any creative effort belong to the protection scope of the present specification.

The existing vehicle safety module generally uses an Automatic Emergency Braking (AEB) system, and the AEB system is explained in a national standard document as follows: the method comprises the steps of monitoring the driving environment in front of the vehicle in real time, and automatically starting a vehicle braking system to decelerate the vehicle when a collision danger possibly occurs so as to avoid the collision or relieve the collision result. Therefore, firstly, the AEB system only considers the driving environment in front of the vehicle, and in an actual driving scene, the driving vehicle needs to consider not only the driving environment in front to avoid a traffic accident such as a collision with the vehicle in front and take responsibility for the traffic accident, but also the driving environments on the left side, the right side and the rear to avoid a traffic accident such as a collision with any obstacle around the vehicle, so as to ensure the safety of the vehicle during driving. Secondly, the AEB system automatically starts the vehicle braking system when there is a risk of collision, so as to avoid collision or reduce the consequences of collision, that is, the AEB system cannot ensure that the vehicle will not collide with other obstacles such as other vehicles, and therefore, the vehicle in driving still has safety problems such as possible collision.

The present specification provides a vehicle control method, which establishes a lane coordinate system according to a position of a vehicle, determines a lateral safe distance and a longitudinal safe distance between each obstacle and the vehicle according to information of obstacles in a surrounding environment of the vehicle, determines a safe influence characteristic value of each obstacle, selects a target obstacle according to the safe influence characteristic value of each obstacle, and controls the vehicle according to the information of the target obstacle and the position of the vehicle.

In addition, the present specification further provides another vehicle control method, which includes establishing a lane coordinate system by using the acquired position of the vehicle, the predicted trajectory and the planned trajectory, determining a difference between the predicted trajectory and the planned trajectory in the lane coordinate system, determining a safety influence characteristic value of each region, which is divided into the surrounding environment of the vehicle in advance, on the vehicle according to the difference, and controlling the vehicle based on the safety influence characteristic value of each region on the vehicle.

The two vehicle control methods provided by the specification can be used independently or together to ensure the safe running of the vehicle. That is, the first vehicle control method may be used alone, or the second vehicle control method may be used alone to solve the disadvantages of the existing AEB system, and in the course of using the first vehicle control method, the second vehicle control method may be used to determine the target area, and the first vehicle control method may be used to determine the target obstacle in the target area, so as to control the vehicle according to the target obstacle in the target area.

The technical solutions provided by the embodiments of the present description are described in detail below with reference to the accompanying drawings.

Fig. 1 is a flowchart of a vehicle control method provided in an embodiment of the present disclosure, which may specifically include the following steps:

s100: and acquiring the point cloud data acquired by the laser radar and the position of the vehicle.

In this specification, the vehicle may include a general vehicle and an unmanned device, and the unmanned device mainly includes an intelligent unmanned device such as an unmanned vehicle and an unmanned aerial vehicle, and is mainly used for replacing manual goods distribution, for example, transporting sorted goods in a large goods storage center, or transporting goods from a certain place to another place.

The mountable has lidar on the vehicle, and lidar can include mechanical lidar, solid-state lidar etc. because mechanical lidar can scan vehicle surrounding environment information, obtains panorama point cloud data, consequently, mechanical lidar can place the top at the vehicle, because solid-state lidar's theory of operation, for obtaining panorama point cloud data, can place a plurality of solid-state lidar on the vehicle, in this description, to lidar's kind, quantity, the position of placing on the vehicle, do not do the restriction.

Therefore, in this specification, the laser radar may acquire point cloud data corresponding to a vehicle surrounding environment, where the vehicle surrounding environment refers to environment information around the vehicle, and may include a static obstacle, a dynamic obstacle, a lane, and the like, with the vehicle as a center.

A Positioning module, such as a Global Positioning System (GPS), may be mounted on the vehicle, and the Positioning module is used to locate the position of the vehicle. Besides, the vehicle can be provided with an image sensor and the like, and the current position of the vehicle can be determined in a computer vision mode. In this specification, there is no particular limitation on how the vehicle position is determined.

The vehicle can be provided with a processor, the point cloud data acquired by the laser radar is acquired through the processor, and the vehicle is controlled through operations such as processing the point cloud data. Since the execution subject of the vehicle control method provided by the present specification may be a vehicle, specifically, a processor and other components on the vehicle, for convenience of description, the execution subject is collectively referred to as a vehicle hereinafter.

In addition, the vehicle may further include a communication device, for example, a WIreless FIdelity (WiFi) module, a bluetooth module, and the like, and the communication device may send the point cloud data acquired by the laser radar, the position of the vehicle, and the like to the server, and the server may control the vehicle according to the received point cloud data, the position of the vehicle, and the like. That is, the execution subject of the vehicle control method provided in the present specification may also be a server. Therefore, for convenience of description, the vehicle control method will be described below taking a vehicle as an execution subject.

S102: determining information of each obstacle according to the point cloud data, wherein the information of the obstacles comprises the position and the speed of the obstacle; and determining the lane where the vehicle is located according to the position of the vehicle, and determining a lane coordinate system taking the lane as a reference according to the lane.

After the vehicle acquires the point cloud data, the point cloud data can be subjected to data processing to obtain information of each obstacle in the surrounding environment of the vehicle.

Specifically, the vehicle can perform target detection on the point cloud data and determine information such as the type, position, speed and the like of each obstacle in the point cloud data. For example, the point cloud data may be input into a pre-trained target detection model, and information such as bounding box information of each target and types of each target in the point cloud data is obtained through the target detection model, where the target is an obstacle, the types of the obstacle may include a static obstacle and a dynamic obstacle, and the dynamic obstacle may be classified into a bicycle, an automobile, a motorcycle, a pedestrian, and the like. After the vehicle detects the point cloud data, information such as the position and the speed of each obstacle in the world coordinate system or the geographic coordinate system is obtained, and the vehicle positioning module positions the vehicle at the position in the world coordinate system or the geographic coordinate system. The location may be represented by longitude and latitude, Universal Transverse Mercator Grid System (UTM), etc.

In addition, the vehicle can also use other existing manners to perform target detection on the point cloud data, which is only one implementation manner provided above, and the description is not repeated for the process of performing target detection on the point cloud data by using other existing manners.

Meanwhile, the vehicle can determine the lane where the vehicle is located according to the position of the vehicle.

Specifically, a map, for example, a high-precision map, a three-dimensional map, or the like, may be stored in the vehicle in advance. According to the current position of the vehicle and the map information, the lane where the vehicle is located or the road where the vehicle is located can be determined.

After determining the lane in which the vehicle is located, the vehicle may determine a lane coordinate system with reference to the lane according to the lane.

Specifically, a lane coordinate system can be established according to the lane where the vehicle is located in the map, wherein the vertical axis of the coordinate system is parallel to the lane, and the horizontal axis of the coordinate system is perpendicular to the lane. The lane coordinate system can be a two-dimensional plane coordinate system, a plane where the coordinate system is located is parallel to the ground, and the lane coordinate system can also be a three-dimensional stereo coordinate system. In combination with the actual situation, the lane coordinate system is a two-dimensional plane coordinate system in general.

Or the vehicle can determine the center line of the road where the vehicle is located according to the map information, and when a lane coordinate system is established, the longitudinal axis of the lane coordinate system can be parallel to the center line of the road, and the transverse axis of the lane coordinate system is perpendicular to the center line of the road.

In a preferred case, the origin of the lane coordinate system may be a center point of the vehicle. The present description is not limited with respect to the origin of the lane coordinate system.

Fig. 2 is a schematic position diagram of a vehicle and an obstacle in a lane coordinate system according to an embodiment of the present disclosure. In fig. 2, two lanes are separated by a dotted line, a is a vehicle in this specification, B is an obstacle in the environment around the vehicle, the longitudinal axis direction of the lane coordinate system is the traveling direction of the vehicle parallel to the lanes, and the lateral axis direction of the lane coordinate system is the left side direction of the vehicle perpendicular to the lanes. The black frame around the vehicle A is the minimum external information of the vehicle and the surrounding environment determined by the vehicle according to the size and the current position of the vehicle, and the black frame around the obstacle B is the minimum external information of the obstacle B and the surrounding environment determined by the vehicle according to the target detection result and represents the position of the obstacle B.

S104: and determining a dynamic parameter corresponding to each obstacle, and determining a transverse safe distance and a longitudinal safe distance between the obstacle and the vehicle in the lane coordinate system according to the lane coordinate system, the dynamic parameter and the speed of the obstacle.

After determining information of each obstacle in the vehicle surroundings, for each obstacle, first, a dynamic parameter corresponding to the obstacle may be determined.

In particular, the dynamic parameters may include lateral dynamic parameters as well as longitudinal dynamic parameters, such as lateral maximum acceleration, lateral minimum acceleration, longitudinal maximum acceleration, longitudinal minimum acceleration, lateral maximum deceleration, lateral minimum deceleration, longitudinal maximum deceleration, longitudinal minimum deceleration, and the like. Different types of obstacles may correspond to different dynamic parameters. Therefore, the vehicle can determine the correspondence between each obstacle type and the dynamic parameter in advance. For example, since the acceleration of the vehicle is generally greater than the acceleration of the bicycle, the obstacle of the vehicle type corresponds to one dynamic parameter, the obstacle of the bicycle type corresponds to another dynamic parameter, and the value of the dynamic parameter can be preset according to the type of the obstacle and the actual situation.

Therefore, for each obstacle, the vehicle can select the dynamic parameter corresponding to the obstacle type of the obstacle as the dynamic parameter corresponding to the obstacle according to the obstacle type of the obstacle and the correspondence between each obstacle type and the dynamic parameter.

Then, according to the lane coordinate system, the dynamic parameters and the speed of the obstacle, a transverse safe distance and a longitudinal safe distance between the obstacle and the vehicle under the lane coordinate system are determined.

Specifically, the vehicle can acquire the speed of the vehicle, determine the vehicle transverse speed and the vehicle longitudinal speed of the vehicle in a lane coordinate system according to the speed of the vehicle, determine the obstacle transverse speed and the obstacle longitudinal speed of the obstacle in the lane coordinate system according to the speed of the obstacle, determine the transverse safe distance according to the vehicle transverse speed, the obstacle transverse speed and the dynamic parameters, and determine the longitudinal safe distance according to the vehicle longitudinal speed, the obstacle longitudinal speed and the dynamic parameters.

That is, the vehicle may perform speed decomposition on the speed of the vehicle and the speed of the obstacle in the lane coordinate system to obtain a vehicle lateral speed, a vehicle longitudinal speed, an obstacle lateral speed, and an obstacle longitudinal speed. And determining the transverse safe distance according to the transverse speed of the vehicle, the transverse speed of the obstacle and the dynamic parameters. And determining the longitudinal safe distance according to the longitudinal speed of the vehicle, the longitudinal speed of the obstacle and the dynamic parameters.

In determining the lateral safety distance, since the dynamic parameters may include lateral dynamic parameters as well as longitudinal dynamic parameters, and the lateral dynamic parameters may include lateral maximum acceleration, lateral minimum acceleration, lateral maximum deceleration, lateral minimum deceleration, etc., the vehicle may determine the lateral safety distance according to the lane coordinate system, the lateral dynamic parameters, and the speed of the obstacle.

Specifically, the reaction time and the dynamic parameters of the vehicle may be preset, the vehicle and the obstacle are close to each other with a lateral acceleration during the reaction time, and then are decelerated with a lateral deceleration, and the distance between the vehicle and the obstacle, which is a distance between the vehicle and the obstacle and is not involved in a traffic accident such as a collision, is determined as the lateral safe distance, wherein the lateral acceleration may be a lateral maximum acceleration or a lateral minimum acceleration, and the lateral deceleration may be a lateral maximum deceleration or a lateral minimum deceleration. Therefore, the lateral safety distance can be as shown in equation (1).

（1）

Wherein the content of the first and second substances,

in order to be a lateral safety distance,

is the minimum distance between the vehicle and the obstacle, takes a non-negative value,

is the current vehicle lateral speed of the vehicle,

in order to achieve the reaction time,

the vehicle lateral velocity after the vehicle has accelerated with a lateral acceleration in the reaction time,

is the lateral deceleration of the vehicle,

is the current obstacle lateral velocity of the obstacle,

the lateral velocity of the obstacle after acceleration with lateral acceleration in the reaction time,

is the lateral deceleration of the obstacle.

In determining the longitudinal safety distance, the longitudinal dynamic parameter may include a longitudinal maximum acceleration, a longitudinal minimum acceleration, a longitudinal maximum deceleration, a longitudinal minimum deceleration, etc., and thus the vehicle may determine the longitudinal safety distance according to the lane coordinate system, the longitudinal dynamic parameter, and the speed of the obstacle.

Specifically, when the longitudinal safe distance is determined, the calculation mode of the longitudinal safe distance is different according to different scenes where the vehicle and the obstacle are located.

When the vehicle and the obstacle are traveling with the vehicle in the longitudinal direction, that is, the vehicle and the obstacle are traveling in the longitudinal direction, taking the vehicle behind the obstacle as an example, the vehicle is accelerated at a longitudinal acceleration and then decelerated at a longitudinal deceleration during the reaction time, and when the obstacle is decelerated at a maximum deceleration, the distance at which the vehicle and the obstacle have no traffic accident such as collision is determined as the longitudinal safe distance, and the longitudinal safe distance may be as shown in formula (2).

（2）

Wherein the content of the first and second substances,

the longitudinal safe distance between the vehicle and the obstacle when the vehicle follows the vehicle in the longitudinal direction,

is the current vehicle longitudinal speed of the vehicle,

is the longitudinal acceleration of the vehicle over the reaction time,

is the longitudinal deceleration of the vehicle,

for the longitudinal deceleration of the obstacle,

is the current obstacle longitudinal velocity of the obstacle.

When the vehicle and the obstacle are running in a meeting manner in the longitudinal direction, that is, the vehicle and the obstacle are running in the opposite direction in the longitudinal direction, and the vehicle and the obstacle are accelerated and then decelerated at the longitudinal acceleration and deceleration respectively in the reaction time, the distance between the vehicle and the obstacle, which is not involved in a traffic accident such as a collision, is determined as the longitudinal safe distance, and the longitudinal safe distance may be as shown in formula (3).

（3）

Wherein the content of the first and second substances,

the longitudinal safe distance when the vehicle meets the obstacle in the longitudinal direction is provided,

is the vehicle longitudinal speed after the vehicle has accelerated with longitudinal acceleration in the reaction time,

is the longitudinal velocity of the obstacle after acceleration with longitudinal acceleration during the reaction time.

The foregoing provides for a manner of determining a lateral safe distance and a longitudinal safe distance between a vehicle and an obstacle in accordance with embodiments of the present disclosure, in this specification, in addition to the above, other ways may be adopted to determine the lateral safe distance and the longitudinal safe distance between the obstacle and the vehicle in the lane coordinate system according to the lane coordinate system, the dynamic parameters and the speed of the obstacle, in the present specification, however, the lateral safe distance is determined in any manner, it is required to satisfy that the lateral safe distance between the vehicle and the obstacle is inversely related to the lateral relative speed, the transverse relative speed is a difference value between the transverse speed of the vehicle and the transverse speed of the obstacle in the lane coordinate system, namely, the larger the transverse relative speed is, the smaller the transverse safe distance is, and the smaller the transverse relative speed is, the larger the transverse safe distance is. The transverse speed of the vehicle and the obstacle under the lane coordinate system can be determined, so that the transverse safe distance between the vehicle and the obstacle can be determined only by satisfying the negative correlation of the transverse safe distance and the transverse relative speed.

Also, in this specification, when the vehicle runs with the obstacle in a meeting or following manner, the longitudinal safe distance between the vehicle and the obstacle is inversely related to the longitudinal relative speed, which is the difference between the longitudinal speed of the vehicle and the longitudinal speed of the obstacle in the lane coordinate system.

In addition, for the dynamic parameter corresponding to each obstacle type, the vehicle may set two different parameter values for the dynamic parameter in advance, which may be recorded as a first dynamic parameter and a second dynamic parameter. Likewise, the dynamic parameters of the vehicle may also be preset with two different parameter values. The first dynamic parameter may be a maximum value of the dynamic parameter, and the second dynamic parameter may be a minimum value of the dynamic parameter. Or setting a value interval of the dynamic parameter, namely, the value interval is greater than or equal to the second dynamic parameter and less than or equal to the first dynamic parameter. The value intervals of different dynamic parameters are related to the type of the obstacle, and taking the longitudinal maximum acceleration corresponding to the type of the automobile as an example, the maximum value of the longitudinal maximum acceleration corresponding to the type of the automobile can be set to be 2.7 by the vehicle

The minimum value of the longitudinal maximum acceleration corresponding to the type of the vehicle is 0.5

That is, the first dynamic parameter is 2.7

The second dynamic parameter is 0.5

。

In this specification, two parameter values are set for a dynamic parameter corresponding to the same obstacle type, which are a first dynamic parameter and a second dynamic parameter, and a transverse safe distance and/or a longitudinal safe distance between the obstacle of the obstacle type and the vehicle can be determined according to the above contents regardless of the first dynamic parameter and the second dynamic parameter. That is, a first lateral safety distance and a first longitudinal safety distance between the obstacle and the vehicle in the lane coordinate system are determined according to the lane coordinate system, the first dynamic parameter and the speed of the obstacle, and a second lateral safety distance and a second longitudinal safety distance between the obstacle and the vehicle in the lane coordinate system are determined according to the lane coordinate system, the second dynamic parameter and the speed of the obstacle.

However, the first dynamic parameter is the maximum value of the dynamic parameter, which indicates that the safety distance between the obstacle and the vehicle is determined to be short, so that the driving safety of the vehicle is ensured in a relatively aggressive manner, and the second dynamic parameter is the minimum value of the dynamic parameter, which indicates that the safety distance between the obstacle and the vehicle is determined to be long, so that the driving safety of the vehicle is ensured in a relatively comfortable manner. Therefore, the first transverse safety distance may be taken as the minimum transverse safety distance, the second transverse safety distance as the maximum transverse safety distance, the first longitudinal safety distance as the minimum longitudinal safety distance, and the second longitudinal safety distance as the maximum longitudinal safety distance.

In addition, because the dynamic parameters of the vehicle and the obstacle can be set with two different parameter values, four transverse safe distances can be obtained according to the formulas (1) to (3), one transverse safe distance can be selected from the four transverse safe distances to be used as the transverse safe distance between the vehicle and the obstacle, or two transverse safe distances are selected to be used as the maximum transverse safe distance and the minimum transverse safe distance between the vehicle and the obstacle respectively. Four longitudinal safety distances are obtained according to the above equations (1) to (3), and one of the four longitudinal safety distances may be selected as the longitudinal safety distance between the vehicle and the obstacle, or two longitudinal safety distances may be selected as the maximum longitudinal safety distance and the minimum longitudinal safety distance between the vehicle and the obstacle, respectively. The mode of selecting the transverse safe distance from the four transverse safe distances or selecting the longitudinal safe distance from the four longitudinal safe distances may be random selection, or sorting first, selecting according to a sorting result, and the like.

S106: and determining a safety influence characteristic value of the obstacle on the vehicle in the transverse direction according to the transverse safety distance and the position of the obstacle, and/or determining a safety influence characteristic value of the obstacle on the vehicle in the longitudinal direction according to the longitudinal safety distance and the position of the obstacle.

After determining the lateral safety distance and the longitudinal safety distance between the vehicle and the obstacle in the lane coordinate system, a safety impact characteristic value of the obstacle on the vehicle may be determined, wherein the safety impact characteristic value of the obstacle on the vehicle may include a safety impact characteristic value of the obstacle on the vehicle in the lateral direction and a safety impact characteristic value of the obstacle on the vehicle in the longitudinal direction.

Firstly, the safety influence characteristic value of the obstacle on the vehicle in the transverse direction can be determined by the vehicle according to the transverse safety distance and the position of the obstacle.

First, the vehicle may determine a current distance between the vehicle and the obstacle according to the position of the obstacle and the position of the vehicle.

Specifically, the information of the boundary frame of the obstacle can be determined from the result of the target detection on the point cloud, and the information of the boundary frame of the vehicle can be determined from data such as the size of the vehicle. Therefore, according to the boundary frame information of the vehicle and the obstacle, the current distance between the vehicle and the obstacle can be determined. Wherein the current distance includes a current lateral distance and a current longitudinal distance.

The current lateral distance between the vehicle and the obstacle is the distance between one side of the bounding box of the vehicle and a different side of the bounding box of the obstacle. When the vehicle is located on the left side of the obstacle, the current transverse distance is the distance between the right side of the boundary frame of the vehicle and the left side of the boundary frame of the obstacle, and when the vehicle is located on the right side of the obstacle, the current transverse distance is the distance between the left side of the boundary frame of the vehicle and the right side of the boundary frame of the obstacle. When there is an overlap between the boundary frame of the obstacle and the projection of the boundary frame of the vehicle in the lateral direction, the current lateral distance between the obstacle and the vehicle may be set to zero. Likewise, the current longitudinal distance between the vehicle and the obstacle is the distance between one side of the vehicle's bounding box and a different side of the obstacle's bounding box. When the vehicle is located in front of the obstacle, the current longitudinal distance is the distance between the lower side of the boundary frame of the vehicle and the upper side of the boundary frame of the obstacle, and when the vehicle is located behind the obstacle, the current longitudinal distance is the distance between the upper side of the boundary frame of the vehicle and the lower side of the boundary frame of the obstacle. When the boundary frame of the obstacle and the boundary frame of the vehicle overlap in the projection in the longitudinal direction, the current longitudinal distance between the obstacle and the vehicle may be set to zero.

According to the current transverse distance and the transverse safe distance, the vehicle can determine a safe influence characteristic value of the obstacle on the vehicle in the transverse direction, wherein the safe influence characteristic value of the obstacle on the vehicle in the transverse direction is positively correlated with the current transverse safe distance. That is, the larger the current lateral safety distance is, the larger the safety influence characteristic value of the obstacle on the vehicle in the lateral direction is, the more the obstacle is safe for the vehicle to run in the lateral direction, and the more the obstacle is safe for the vehicle to run in the lateral direction.

In addition, the vehicle can also determine a safety influence representation value of the obstacle on the vehicle in the transverse direction according to the first transverse safety distance, the second transverse safety distance and the position of the obstacle.

Specifically, the vehicle may determine a ratio of a logarithm of a difference between the current lateral distance and the first lateral safety distance to a logarithm of a difference between the first lateral safety distance and the second lateral safety distance as a safety impact characteristic value of the obstacle on the vehicle in the lateral direction, as shown in equation (4).

（4）

Wherein the content of the first and second substances,

a safety impact characterizing value for the obstacle in the lateral direction on the vehicle,

as a result of the current lateral distance,

is the first lateral safety distance and is,

a second lateral safety distance.

And determining the safety influence characteristic value of the obstacle on the vehicle in the longitudinal direction by the vehicle according to the longitudinal safety distance and the position of the obstacle.

According to the current longitudinal distance and the longitudinal safety distance, the vehicle can determine a safety influence characteristic value of the obstacle on the vehicle in the longitudinal direction, wherein the safety influence characteristic value of the obstacle on the vehicle in the longitudinal direction is positively correlated with the current longitudinal safety distance. That is, the larger the current longitudinal safety distance is, the larger the safety influence characteristic value of the obstacle on the vehicle in the longitudinal direction is, the more the obstacle has no threat on the running safety of the vehicle in the longitudinal direction, and the more the obstacle is safe on the vehicle in the longitudinal direction when the vehicle runs.

In addition, the vehicle can also determine a safety influence representation value of the obstacle on the vehicle in the longitudinal direction according to the first longitudinal safety distance, the second longitudinal safety distance and the position of the obstacle.

Specifically, the vehicle may determine a ratio of a logarithm of a difference between the current longitudinal distance and the first longitudinal safety distance to a logarithm of a difference between the first longitudinal safety distance and the second longitudinal safety distance as a safety influence characterization value of the obstacle on the vehicle in the longitudinal direction, as shown in equation (5).

（5）

Wherein the content of the first and second substances,

a safety impact characterizing value for the obstacle in the longitudinal direction on the vehicle,

as a result of the current longitudinal distance,

is a first longitudinal safety distance in the form of a first longitudinal safety distance,

a second longitudinal safety distance.

In addition to the above, in this specification, a safety model may be trained in advance, the transverse safety distance and the position of the obstacle may be input to the safety model trained in advance, a safety influence characteristic value of the obstacle output by the safety model on the vehicle in the transverse direction may be obtained, and the longitudinal safety distance and the position of the obstacle may be input to the safety model, and a safety influence characteristic value of the obstacle output by the safety model on the vehicle in the longitudinal direction may be obtained. Wherein, when the safety model is pre-trained, supervised training or unsupervised training can be adopted, and the safety model can be a machine learning model, such as a neural network model. For specific contents of training the security model, reference may be made to an existing training method, and details are not repeated in this specification.

S108: and selecting at least one target obstacle from the obstacles according to the determined safety influence characteristic value of each obstacle.

S110: and controlling the vehicle according to the information of the target obstacle and the position of the vehicle.

After determining the safety impact indicator for each obstacle, the vehicle may select at least one target obstacle among the obstacles based on the safety impact indicator for each obstacle.

Specifically, first, the vehicle divides the vehicle surroundings into regions in advance, for example, the vehicle front, the vehicle left, and the vehicle right.

The vehicle may then select a target zone in each zone. And determining each obstacle in the target area according to the relative position of the vehicle and each obstacle. And selecting the target barrier according to the safety influence characteristic value of each barrier in the target area. That is, the vehicle may first select a target region, which herein refers to a region having an influence on the driving safety of the vehicle, and then select a target obstacle in the target region. Alternatively, the vehicle may classify the obstacles according to the relative positions of the vehicle and the obstacles, that is, the obstacles located in the same area are classified into one type. And sorting the obstacles in the class according to the safety influence characteristic value of each obstacle in the class aiming at the obstacles in each class, and selecting a target obstacle from the obstacles in the class according to a sorting result, namely, selecting the target obstacle in each area by the vehicle.

First, a first mode is described in which a target area is selected and a vehicle is controlled according to the target area. Fig. 3 is a flowchart of another vehicle control method provided in the embodiment of the present disclosure, which may specifically include the following steps:

s200: the method comprises the steps of obtaining the position of a vehicle, a predicted track and a planned track, wherein the predicted track is a track which is obtained by prediction of the vehicle and does not refer to information of obstacles in the surrounding environment of the vehicle, and the planned track is a track which is obtained by planning of the vehicle and avoids the obstacles.

In this specification, the same contents are not repeated, and the above contents may be referred to, and for example, the execution subject may be a vehicle, a server, or the like.

The vehicle may obtain a predicted trajectory as well as a planned trajectory. The predicted track is a track predicted by the vehicle according to the historical track. When the vehicle obtains the predicted trajectory, the information of the obstacles in the vehicle surroundings is not taken into account, that is, when the vehicle travels along the predicted trajectory, the vehicle cannot avoid the obstacles in the surroundings, and when the vehicle encounters an obstacle during the travel of the vehicle, the vehicle stops. Therefore, the predicted trajectory is intuitively a straight line with speed information in the lane coordinate system, and the vehicle does not finally travel according to the predicted trajectory.

The planned track is a track which is obtained by planning the vehicle according to the information of each obstacle in the surrounding environment and avoids each obstacle. That is, when the vehicle obtains the planned trajectory, the information of the obstacles in the vehicle surroundings is taken into consideration, that is, when the vehicle travels along the planned trajectory, the vehicle can avoid the obstacles in the surroundings. The planned trajectory is likewise a trajectory with speed information.

S202: and determining a lane where the vehicle is located according to the position of the vehicle, and determining a lane coordinate system taking the lane as a reference according to the lane.

S204: and determining the difference between the predicted track and the planned track in the lane coordinate system according to the lane coordinate system, the information of the predicted track and the information of the planned track.

After the predicted track and the planned track are obtained, the vehicle can respectively sample the predicted track and the planned track according to a preset time interval, a sampling point in the predicted track is used as a predicted sampling point, a sampling point in the planned track is used as a planned sampling point, and the predicted sampling point and the planned sampling point at the same moment are determined in each sampling point according to the moment when the vehicle reaches each sampling point.

Referring to fig. 2, fig. 4 is a schematic diagram of a predicted trajectory and a planned trajectory in a lane coordinate system according to an embodiment of the present disclosure. In fig. 4, the thicker broken line is the predicted trajectory, the thinner broken line is the planned trajectory, X1 and X2 are two sampling points on the planned trajectory, Y1 and Y2 are two sampling points on the predicted trajectory, and the time when the vehicle reaches X1 is the same as the time when the vehicle reaches Y1, so X1 and Y1 are the planned sampling point and the predicted sampling point corresponding to the same time. X2 represents the planned sampling point and the predicted sampling point at the same time as Y2 represents the planned sampling point and the predicted sampling point. Since the time when the vehicle arrives at Y1 and the time when the vehicle arrives at Y2 are adjacent times, Y1 and Y2 are predicted sampling points at the adjacent times, and X1 and X2 are planned sampling points at the adjacent times.

According to the positions of the predicted sampling point and the planned sampling point at the same time, the vehicle can determine the difference between the predicted track and the planned track in the lane coordinate system.

Specifically, for each time, according to the positions of the predicted sampling point and the planned sampling point of the time, the transverse distance between the predicted sampling point and the planned sampling point of the time in the lane coordinate system is determined, the transverse distance is used as the transverse distance corresponding to the time, and the difference is determined according to the transverse distance corresponding to each time.

Of course, the vehicle may also determine a longitudinal distance between the predicted sampling point and the planned sampling point at the time in the lane coordinate system, as the longitudinal distance corresponding to the time, and determine the difference according to the longitudinal distance corresponding to each time.

Considering that the longitudinal distance and the transverse distance corresponding to the time can both be used to determine the difference, the process of determining the difference will be described below by taking the transverse distance as an example.

The present description may provide two ways of determining the difference based on the lateral distance corresponding to each time instant.

The first mode is described below.

The vehicle can determine a first designated time and a second designated time, determine a sum of lateral distances corresponding to times before the first designated time as a first sum, determine a sum of lateral distances corresponding to times before the second designated time as a second sum, and determine the difference based on the first sum and the second sum.

Specifically, the vehicle may determine that the second designated time is after the first designated time, and if the number of the sampling points of the planned trajectory and the number of the sampling points of the predicted trajectory are both N before the first designated time, and the number of the sampling points of the planned trajectory and the number of the sampling points of the predicted trajectory are both N before the second designated time, the difference may be as shown in equation (6).

（6）

Wherein the content of the first and second substances,

to account for the differences between the predicted trajectory and the planned trajectory,

for the ith planned sampling point,

is the ith predicted sample point.

In addition, in addition to the method shown in formula (6), the vehicle may randomly select n planning sampling points in each planning sampling point, and determine the prediction sampling point corresponding to the n planning sampling points in each prediction sampling point. Or the sampling points of the n planned tracks and the sampling points of the n predicted tracks are sampling points between the first specified time and the second specified time, and the like. Regarding the selection of the sampling points in the above description, the description is not repeated.

The second mode is described below.

The vehicle can determine the change degree of the transverse distance corresponding to any adjacent time according to the transverse distance corresponding to each time. Wherein the degree of variation of the transverse distance

As shown in equation (7).

（7）

Determining differences according to the change degrees, wherein the differences are positively correlated with the change degrees. That is, the greater the degree of change, the greater the difference, and the smaller the degree of change, the smaller the difference. Therefore, the difference can be determined by determining the degree of change in the lateral distance corresponding to any adjacent time according to equation (7). In a more preferred manner, the maximum degree of variation can be taken as the difference.

S206: and aiming at each region divided into the surrounding environment of the vehicle in advance, determining a safety influence characteristic value of the region on the vehicle according to the difference, wherein the safety influence characteristic value is in negative correlation with the difference.

After determining the difference between the predicted trajectory and the planned trajectory, the vehicle may determine, for each area, each sample point located within the area based on the location of each sample point.

Specifically, the manner in which each region is divided into the surroundings of the vehicle in advance can be referred to above. Since the difference is determined in two ways, when the safety influence representation value of the area on the vehicle is determined according to the difference, the difference can be determined in two ways.

For the first mode, since the first mode of determining the difference is a ratio of sum values of lateral distances of the sampling points, each sampling point located in the area can be determined according to the position of each sampling point, when determining the difference, the sum value of the lateral distances between all the sampling points can be used as a second sum value, the sum value of the lateral distances between the planning sampling point located in the area and the prediction sampling points corresponding to each planning sampling point can be used as a first sum value, and the difference between the prediction track and the planning track in the area can be determined according to the first sum value and the second sum value. And determining a safety influence representation value of the area on the vehicle according to the difference between the predicted track and the planned track in the area. For example, a region weight may be set, and the product of the difference between the predicted trajectory and the planned trajectory in the region and the region weight is used as a safety influence characterization value of the region on the vehicle. Since the safety-related characteristic value is inversely related to the difference, the smaller the difference, the larger the safety-related characteristic value, and the higher the safety of the vehicle traveling in the area.

In the second mode, since the second mode of determining the difference is determined by the degree of change in the lateral distance of the sampling point, the greater the degree of change, the greater the difference, the smaller the safety-affected value, and the lower the safety of the vehicle traveling in the area. Therefore, the change degree of the sampling points in the area can be determined according to the information of the sampling points in the area, the difference between the predicted track and the planned track in the area is determined according to the change degree of the sampling points in the area, and the reciprocal of the difference is used as a safety influence value. In this specification, as long as the difference is determined, the safety-affected value can be determined from the relationship in which the difference is negatively correlated with the safety-affected value.

In addition, in this specification, since each sampling point is in the lane coordinate system, a sign of a variation degree of the sampling point (that is, whether the variation degree of the sampling point takes a positive value or a negative value) can also be used as a basis for determining the target area. Along the above example, in fig. 4, if the origin of coordinates of the lane coordinate system is located at the center of the vehicle, and the values of the variation degrees of the sampling points determined by the sampling points X1, X2, Y1, and Y2 are positive values, then the left front of the vehicle is a safety region, and the right front of the vehicle is a danger region, that is, the target region is the right front region of the vehicle, and the vehicle needs to avoid the right front of the vehicle during driving.

In addition, in this specification, the vehicle may further determine an acceleration of each planned sampling point, determine the number of planned sampling points of which the acceleration is smaller than a preset acceleration threshold according to the acceleration of each planned sampling point, and determine a safety influence characterization value of each area on the vehicle according to the number and the difference.

Specifically, for each region, the planned sampling points located in the region may be determined, and the number of planned sampling points in the region where the acceleration is smaller than the acceleration threshold is determined according to the acceleration of each planned sampling point, where the acceleration is actually the acceleration of the brake, that is, the deceleration mentioned above, and according to the above expression, the number of planned sampling points in the region where the deceleration is larger than the deceleration threshold may be determined. The quantity is inversely related to the safety influence characteristic value, that is, the more the quantity is, the more the braking times of the vehicle running in the area are, the smaller the safety influence characteristic value is, the greater the threat of the area to the running safety of the vehicle is, and the less safe the vehicle runs in the area. The safety impact-characterizing value of the area on the vehicle can be determined by determining the number of planned sampling points in the area where the deceleration is greater than the deceleration threshold and the difference between the planned trajectory and the predicted trajectory in the area.

S208: and controlling the vehicle according to the safety influence representation value of each region on the vehicle.

After the safety influence characteristic value of each area on the vehicle is determined, a target area can be determined in each area according to the safety influence characteristic value of each area on the vehicle, and then the vehicle can be controlled according to the information of each obstacle in the target area.

Specifically, the regions may be sorted according to the magnitude of the safety influence characteristic value of each region on the vehicle, and the region with the minimum safety influence characteristic value is selected as the target region according to the sorting result, because the smaller the safety influence characteristic value is, the smaller the safety of the vehicle running in the region is, that is, the more likely the region is to threaten the vehicle running safety. Of course, the target region may also be randomly selected among the regions. In addition, in the present specification, the number of selected target regions may be one or more.

After the target area is selected, information on obstacles in the target area can be specified, and the vehicle can be controlled based on information such as the position and speed of each obstacle. The information of the obstacle in the target area is determined, and the above contents may be referred to.

In addition, for each area, the maximum change degree in the area and the value information of the maximum change degree in the area in the lane coordinate system can be determined, the driving direction of the vehicle in the area can be determined according to the positive and negative values of the value of the maximum change degree in the area, and the vehicle can be controlled according to the driving direction of the vehicle in the area.

The above is the first method, that is, the target area is determined first, then the obstacles in the target area are determined, and the vehicle is controlled based on the information of each obstacle in the target area.

Next, a second mode is described, in which a target obstacle is selected for each area, and the vehicle is controlled according to the target obstacle.

For each area, each obstacle located in the area can be identified based on the position of each obstacle. The target obstacle can be determined according to the safety influence characteristic value of each obstacle, and the vehicle is controlled according to information such as the position, the speed and the position of the vehicle of the target obstacle.

Specifically, for each obstacle in the area, the comprehensive safety-impact characteristic value of the obstacle is determined according to the safety-impact characteristic values of the obstacle to the vehicle in the transverse direction and the longitudinal direction, for example, the sum of the safety-impact characteristic value of the obstacle to the vehicle in the transverse direction and the safety-impact characteristic value of the obstacle to the vehicle in the longitudinal direction may be used as the comprehensive safety-impact characteristic value of the obstacle, or the minimum of the safety-impact characteristic value of the obstacle to the vehicle in the transverse direction and the safety-impact characteristic value of the obstacle to the vehicle in the longitudinal direction may be used as the comprehensive safety-impact characteristic value of the obstacle.

And sequencing the obstacles according to the comprehensive safety influence characteristic value of each obstacle in the area. And determining the target obstacle in each obstacle according to the sequencing result. For example, the obstacle with the smallest overall safety impact characteristic value may be selected as the target obstacle because the obstacle with the smallest overall safety impact characteristic value is most dangerous to the running vehicle. Of course, the target obstacle may be randomly selected among the obstacles.

In addition, in the present specification, the traveling direction of the vehicle may be determined based on the safety-related-influence characterizing values of the selected target obstacle for the vehicle in the lateral direction and the longitudinal direction, and the vehicle may be controlled based on the traveling direction of the vehicle.

One or more target obstacles may be selected in this description. After a plurality of target obstacles are selected in this specification, the target obstacles may be ranked according to the safety influence characteristic value of each target obstacle on the vehicle in the lateral direction, and a target obstacle having the smallest safety influence characteristic value on the vehicle in the lateral direction, that is, a target obstacle most dangerous to the vehicle in the lateral direction, is selected, so as to determine whether the vehicle needs to avoid the target obstacle in the lateral direction, thereby implementing control over the vehicle, for example, determining whether the vehicle needs to change the driving direction, and controlling the vehicle according to the determination result. In addition, the vehicle can also sequence the target obstacles according to the safety influence characteristic value of each target obstacle on the vehicle in the longitudinal direction, select the target obstacle with the smallest safety influence characteristic value on the vehicle in the longitudinal direction, that is, select the target obstacle most dangerous to the vehicle in the longitudinal direction, so as to determine whether the vehicle needs to avoid the target obstacle in the longitudinal direction, thereby realizing the control on the vehicle, for example, judging whether the vehicle needs to change the driving direction or reduce the speed of the vehicle, and the like, and controlling the vehicle according to the judgment result.

The vehicle control method provided in the present specification is particularly applicable to a field of delivery using an unmanned aerial vehicle, for example, a scene of delivery such as express delivery and takeout using an unmanned aerial vehicle. Specifically, in the above-described scenario, delivery may be performed using an unmanned vehicle fleet configured with a plurality of unmanned devices.

Based on the vehicle control method shown in fig. 1, the embodiment of the present specification further provides a schematic structural diagram of a vehicle control device, as shown in fig. 4.

Fig. 5 is a schematic structural diagram of a vehicle control device provided in an embodiment of the present specification, where the device includes:

an obtaining module 501, configured to obtain point cloud data collected by the laser radar and a position of the vehicle;

a first determining module 502, configured to determine information of each obstacle according to the point cloud data, where the information of each obstacle includes a position and a speed of each obstacle; determining a lane where the vehicle is located according to the position of the vehicle, and determining a lane coordinate system taking the lane as a reference according to the lane;

a second determining module 503, configured to determine, for each obstacle, a dynamic parameter corresponding to the obstacle, and determine, according to the lane coordinate system, the dynamic parameter, and a speed of the obstacle, a lateral safe distance and a longitudinal safe distance between the obstacle and the vehicle in the lane coordinate system;

a third determining module 504, configured to determine a safety impact characteristic value of the obstacle on the vehicle in the lateral direction according to the lateral safety distance and the position of the obstacle, and/or determine a safety impact characteristic value of the obstacle on the vehicle in the longitudinal direction according to the longitudinal safety distance and the position of the obstacle;

a selecting module 505, configured to select at least one target obstacle from the obstacles according to the determined safety influence characterization values of the obstacles;

a first control module 506, configured to control the vehicle according to the information of the target obstacle and the position of the vehicle.

Optionally, the information of the obstacle comprises an obstacle type;

the second determining module 503 is specifically configured to determine the dynamic parameter corresponding to the obstacle according to a predetermined correspondence between each obstacle type and the dynamic parameter and the obstacle type of the obstacle.

Optionally, the second determining module 503 is specifically configured to obtain a speed of the vehicle; determining the vehicle transverse speed and the vehicle longitudinal speed of the vehicle in the lane coordinate system according to the speed of the vehicle, and determining the obstacle transverse speed and the obstacle longitudinal speed of the obstacle in the lane coordinate system according to the speed of the obstacle; and determining the transverse safe distance according to the vehicle transverse speed, the obstacle transverse speed and the dynamic parameters, and determining the longitudinal safe distance according to the vehicle longitudinal speed, the obstacle longitudinal speed and the dynamic parameters.

the second determining module 503 is specifically configured to determine the lateral safe distance according to the lane coordinate system, the lateral dynamic parameter, and the speed of the obstacle, and determine the longitudinal safe distance according to the lane coordinate system, the longitudinal dynamic parameter, and the speed of the obstacle.

the second determining module 503 is specifically configured to determine, according to the lane coordinate system, the first dynamic parameter, and the speed of the obstacle, a first lateral safe distance and a first longitudinal safe distance between the obstacle and the vehicle in the lane coordinate system; and determining a second transverse safe distance and a second longitudinal safe distance between the obstacle and the vehicle in the lane coordinate system according to the lane coordinate system, the second dynamic parameter and the speed of the obstacle.

Optionally, the third determining module 504 is specifically configured to determine a safety influence representation value of the obstacle on the vehicle in the lateral direction according to the first lateral safety distance, the second lateral safety distance, and the position of the obstacle;

the third determining module 504 is specifically configured to determine a safety impact characterization value of the obstacle on the vehicle in the longitudinal direction according to the first longitudinal safety distance, the second longitudinal safety distance, and the position of the obstacle.

Optionally, the selecting module 505 is specifically configured to classify each obstacle according to a relative position of the vehicle and each obstacle; sequencing the obstacles in each class according to the safety influence characteristic values of the obstacles in the class aiming at the obstacles in each class; according to the sorting result, a target obstacle is selected from the obstacles in the class.

Based on the vehicle control method shown in fig. 3, the embodiment of the present specification further provides a schematic structural diagram of another vehicle control device, as shown in fig. 6.

Fig. 6 is a schematic structural diagram of another vehicle control device provided in an embodiment of the present specification, where the device includes:

an obtaining trajectory module 601, configured to obtain a position of a vehicle, a predicted trajectory and a planned trajectory, where the predicted trajectory is a trajectory predicted for the vehicle and not referring to information of an obstacle in an environment around the vehicle, and the planned trajectory is a trajectory planned for the vehicle and avoiding the obstacle;

a lane determining module 602, configured to determine a lane where the vehicle is located according to the position of the vehicle, and determine a lane coordinate system with the lane as a reference according to the lane;

a difference determining module 603, configured to determine, according to the lane coordinate system, the information of the predicted trajectory, and the information of the planned trajectory, a difference between the predicted trajectory and the planned trajectory in the lane coordinate system;

a safety determination module 604, configured to determine, for each region that is divided into the surrounding environment of the vehicle in advance, a safety influence characterization value of the region on the vehicle according to the difference, where the safety influence characterization value is negatively correlated with the difference;

and the second control module 605 is configured to control the vehicle according to the safety influence characterization values of the regions on the vehicle.

Optionally, the difference determining module 603 is specifically configured to sample the predicted trajectory and the planned trajectory according to a preset time interval, respectively; taking the sampling points in the predicted track as predicted sampling points, and taking the sampling points in the planning track as planning sampling points; according to the time when the vehicle reaches each sampling point, determining a predicted sampling point and a planned sampling point at the same time in each sampling point; and determining the difference between the predicted track and the planned track in the lane coordinate system according to the positions of the predicted sampling point and the planned sampling point at the same moment.

Optionally, the difference determining module 603 is specifically configured to, for each time, determine, according to the positions of the predicted sampling point and the planned sampling point at the time, a transverse distance between the predicted sampling point and the planned sampling point at the time in the lane coordinate system as a transverse distance corresponding to the time; and determining the difference according to the corresponding transverse distance at each moment.

Optionally, the difference determining module 603 is specifically configured to determine a first specified time and a second specified time; determining a sum of the lateral distances corresponding to the times before the first designated time as a first sum, and determining a sum of the lateral distances corresponding to the times before the second designated time as a second sum; determining the difference based on the first sum and the second sum.

Optionally, the difference determining module 603 is specifically configured to determine, according to the lateral distance corresponding to each time, a change degree of the lateral distance corresponding to any adjacent time; determining the difference based on the degree of change.

Optionally, the determining security module 604 is specifically configured to determine an acceleration of each planned sampling point;

determining the number of the planning sampling points with the accelerated speed smaller than a preset accelerated speed threshold value according to the accelerated speed of each planning sampling point; and determining the safety influence representation value of each region on the vehicle according to the quantity.

Optionally, the second control module 605 is specifically configured to, according to the safety influence characteristic value of each region on the vehicle, determine, in each region, a region with a minimum safety influence characteristic value on the vehicle as a target region; and controlling the vehicle according to the information of each obstacle in the target area.

The embodiment of the specification also provides a computer readable storage medium, and the storage medium stores a computer program, and the computer program can be used for executing the vehicle control method provided by the above-mentioned fig. 1.

Based on the vehicle control method shown in fig. 1, the embodiment of the present specification also proposes a schematic configuration diagram of the vehicle device shown in fig. 7. As shown in fig. 7, the vehicle device includes a processor, an internal bus, a network interface, a memory, and a nonvolatile memory, and may include hardware required for other services. The processor reads a corresponding computer program from the nonvolatile memory into the memory and then runs the computer program to implement the vehicle control method described above with reference to fig. 1.

Of course, besides the software implementation, the present specification does not exclude other implementations, such as logic devices or a combination of software and hardware, and the like, that is, the execution subject of the following processing flow is not limited to each logic unit, and may be hardware or logic devices.

In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Language Description Language), traffic, pl (core unified Programming Language), HDCal, JHDL (Java Hardware Description Language), langue, Lola, HDL, laspam, hardsradware (Hardware Description Language), vhjhd (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.

The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.

The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functions of the various elements may be implemented in the same one or more software and/or hardware implementations of the present description.

As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The description has been presented with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the description. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

This description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

The above description is only an example of the present specification, and is not intended to limit the present specification. Various modifications and alterations to this description will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification should be included in the scope of the claims of the present specification.

Claims

1. The vehicle control method is characterized in that a laser radar is mounted on a vehicle and used for collecting point cloud data corresponding to the surrounding environment of the vehicle; the method comprises the following steps:

2. The method of claim 1, wherein the information of the obstacle includes an obstacle type;

3. The method according to claim 1, wherein determining a lateral safe distance and a longitudinal safe distance between the obstacle and the vehicle in the lane coordinate system based on the lane coordinate system, the dynamic parameters, and a speed of the obstacle comprises:

acquiring the speed of the vehicle;

4. The method of claim 1, wherein the dynamic parameters include lateral dynamic parameters and longitudinal dynamic parameters;

5. The method of claim 1, wherein the dynamic parameters comprise a first dynamic parameter and a second dynamic parameter;

6. The method of claim 5, wherein determining a safety impact characterizing value of the obstacle on the vehicle in the lateral direction based on the lateral safety distance and the position of the obstacle comprises:

7. The method of claim 1, wherein selecting at least one target obstacle among the obstacles based on the lateral safety probability and the longitudinal safety probability of each obstacle comprises:

8. Vehicle control device, its characterized in that, install lidar on the vehicle at device place, lidar is used for gathering the corresponding point cloud data of vehicle surrounding environment, the device includes:

9. A computer-readable storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, implements the method of any of the preceding claims 1-7.

10. A vehicle device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the method of any of claims 1-7.