CN116215515A

CN116215515A - Vehicle control method and device, whole vehicle controller and vehicle

Info

Publication number: CN116215515A
Application number: CN202111471057.6A
Authority: CN
Inventors: 彭浩
Original assignee: Haomo Zhixing Technology Co Ltd
Current assignee: Haomo Zhixing Technology Co Ltd
Priority date: 2021-12-03
Filing date: 2021-12-03
Publication date: 2023-06-06

Abstract

The embodiment of the invention provides a vehicle control method, a device, a whole vehicle controller and a vehicle, comprising the following steps: determining a turnout region adjacent to the edge lane in the case that the vehicle is in the edge lane; determining a lane region adjacent to the obstacle region, and splicing part of the lane region and the turnout region to form a target region; acquiring a target object in a target area and a first motion parameter corresponding to the target object; and when the first motion parameter and the second motion parameter of the vehicle meet the avoidance condition, adjusting the running speed and/or the running direction of the vehicle. According to the embodiment of the invention, the motion parameters of the target object on the other side of the isolation belt and in the turnout in the isolation belt can be obtained when the vehicle is in the edge lane, so that whether the target object is likely to collide with the vehicle or not is judged, and the vehicle is timely controlled to avoid the target object when the target object is likely to exit from the turnout and collide with the vehicle, so that the driving safety is greatly improved.

Description

Vehicle control method and device, whole vehicle controller and vehicle

Technical Field

The invention relates to the technical field of automobiles, in particular to a vehicle control method and device, a whole vehicle controller and a vehicle.

Background

As the number of motor vehicles is increased, the complexity of the road matched with the motor vehicles is also higher. In actual roads, isolation belts are often arranged between lanes, and branch road junctions are also arranged on the isolation belts, so that due to the influence of the isolation belts on the sight of a driver, when other traffic participants are about to exit from the branch road junctions, the driver cannot always find out in time, and the driver is easy to collide with other traffic participants exiting the branch road junctions.

In the related art, some vehicles are equipped with an active braking (AEB) function, which detects an obstacle in front of a lane on which the vehicle is traveling, determines whether a collision occurs according to the speed of the obstacle and the speed of the vehicle when the obstacle occurs in front, and then, after determining that the collision occurs, performs an emergency braking operation on the vehicle to avoid the collision with the obstacle in front.

However, when other traffic participants exit from the turnout, they may suddenly appear in front of the vehicle, and at this time, the vehicle distance may be relatively short, and even if a braking operation is performed, collision cannot be avoided, so that it is difficult to effectively avoid the other traffic participants that suddenly exit from the turnout, and the driving safety is poor.

Disclosure of Invention

In view of the above, the present invention aims to provide a vehicle control method, a device, a vehicle controller and a vehicle, so as to solve the problem that in the prior art, it is difficult for a driver to effectively avoid other traffic participants suddenly driving out from a turnout.

In order to achieve the above purpose, the technical scheme of the invention is realized as follows:

a vehicle control method applied to a vehicle controller of a vehicle, the apparatus comprising:

determining a turnout region adjacent to an edge lane if the vehicle is in the edge lane; wherein the turnout region is formed by a region between adjacent barrier regions;

determining a lane region adjacent to the obstacle region, and splicing part of the lane region and the turnout region to form a target region; the lane areas and the edge lanes are respectively positioned at two sides of the obstacle area;

acquiring a target object in the target area and a first motion parameter corresponding to the target object;

and when the first motion parameter and the second motion parameter of the vehicle meet the avoidance condition, adjusting the running speed and/or the running direction of the vehicle so as to control the vehicle to avoid the target object.

A vehicle control apparatus, the apparatus comprising:

a turnout determining module for determining a turnout region adjacent to an edge lane in a case where the vehicle is in the edge lane; wherein the turnout region is formed by a region between adjacent barrier regions;

the area determining module is used for determining a lane area adjacent to the obstacle area and splicing part of the lane area and the turnout area to form a target area; the lane areas and the edge lanes are respectively positioned at two sides of the obstacle area;

the target determining module is used for acquiring a target object in the target area and a first motion parameter corresponding to the target object;

and the avoidance module is used for adjusting the running speed and/or the running direction of the vehicle when the first motion parameter and the second motion parameter of the vehicle meet the avoidance condition so as to control the vehicle to avoid the target object.

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

A vehicle comprises the whole vehicle controller.

Compared with the prior art, the vehicle control method, the device, the whole vehicle controller and the vehicle have the following advantages:

in summary, an embodiment of the present invention provides a vehicle control method, including: determining a turnout region adjacent to the edge lane in the case that the vehicle is in the edge lane; wherein the turnout region is formed by a region between adjacent barrier regions; determining a lane region adjacent to the obstacle region, and splicing part of the lane region and the turnout region to form a target region; the lane area and the edge lanes are respectively positioned at two sides of the obstacle area; acquiring a target object in a target area and a first motion parameter corresponding to the target object; and when the first motion parameter and the second motion parameter of the vehicle meet the avoidance condition, adjusting the running speed and/or the running direction of the vehicle so as to control the vehicle control target object. According to the embodiment of the invention, the motion parameters of the target object on the other side of the isolation belt and in the turnout in the isolation belt can be obtained when the vehicle is in the edge lane, so that whether the target object is likely to collide with the vehicle or not is judged, and the vehicle is timely controlled to avoid the target object when the target object is likely to exit from the turnout and collide with the vehicle, so that the driving safety is greatly improved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention. In the drawings:

FIG. 1 is a flow chart of steps of a vehicle control method according to an embodiment of the present invention;

FIG. 2 is a schematic view of a road scene according to an embodiment of the present invention;

FIG. 3 is a schematic view of another road scene according to an embodiment of the present application;

FIG. 4 is a flowchart illustrating steps of another vehicle control method according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of a target object track according to an embodiment of the present application;

FIG. 6 is a flowchart illustrating steps of a method for controlling a vehicle according to an embodiment of the present invention;

fig. 7 is a block diagram of a vehicle control apparatus according to an embodiment of the present invention;

fig. 8 is a block diagram showing another vehicle control apparatus according to the embodiment of the invention.

Detailed Description

It should be noted that, without conflict, the embodiments of the present invention and features of the embodiments may be combined with each other.

The invention will be described in detail below with reference to the drawings in connection with embodiments.

Referring to fig. 1, a flow chart of steps of a vehicle control method according to an embodiment of the present invention is shown.

The vehicle control method provided by the embodiment of the invention is applied to a vehicle controller (VCU, vehicle control unit), a vehicle body controller (BCM, body Control Module) or other controllers for controlling the running speed and/or running direction of a vehicle. In the embodiment of the application, the user can turn on or off the avoidance function executed in the subsequent step through a physical switch on the vehicle and a virtual switch in the man-machine interaction node.

Step 101, determining a turnout region adjacent to an edge lane when the vehicle is in the edge lane; wherein the turnout region is formed by a region between adjacent barrier regions.

While the vehicle is traveling on a road, there may be obstacle regions on both sides of the vehicle, wherein the obstacle regions may be isolation belts, green belts, or other objects that may affect the driver's vision. When a vehicle is traveling proximate to an obstacle region, other traffic participants may travel from the turnout at any time into the lane in which the vehicle is traveling, as the obstacle region is not coherent, where a turnout may be present. However, due to the factors such as the shielding of the sight of the obstacle area or the light of the opposite vehicle, the driver of the vehicle cannot timely notice other traffic participants who will drive into the lane where the vehicle is located from the turnout, and the collision cannot be timely predicted to avoid in advance, and often, when the driver of the vehicle finds that other traffic participants are in front of the vehicle, the collision cannot be avoided by adopting the avoidance actions such as braking again.

Referring to fig. 2, fig. 2 is a schematic view of a road scene according to an embodiment of the present invention, as shown in fig. 2, the driving directions of vehicles on the lanes R1 and R2 are opposite, and due to the shielding of the left green belt (the oblique line area in the drawing), the driver of the vehicle C1 located on the lane R1 cannot notice the vehicle C2 driving into the lane R1 from the lane R2 in time, and after a period of time, the driver of the vehicle C1 continues to drive, and after the vehicle C2 enters the lane R1, the vehicle C2 appears right in front of the driving direction of the vehicle C1, and at this time, traffic accidents may be caused due to the fact that the distance between the two vehicles is too close, or the vehicle C2 just enters the lane R1 from the fork when the vehicle C1 passes through the fork, so that the vehicle C2 collides with the side of the vehicle C1.

Since the above-described potential safety hazard generally occurs only in the case where the vehicle is traveling in the edge lane, it is possible to search for the turnout region on both sides of the lane in the vehicle traveling direction in the case where it is determined that the vehicle is in the edge lane, thereby further evaluating the movement condition of the target object in the vicinity of the turnout region. The edge lanes refer to lanes adjacent to the obstacle region on at least one side, for example, leftmost lanes, rightmost lanes, auxiliary lanes in urban roads, and the like.

Referring to fig. 3, fig. 3 is a schematic view of another road scenario according to an embodiment of the present application, as shown in fig. 3, the road is a bidirectional 8-lane, which includes lanes R1 to R8, lanes R1 and R8 are auxiliary lanes inside the green belt, and a separation belt is present between lanes R4 and R5, so that at least one side of lanes R1, R2, R4, R5, R7 and R8 can be regarded as an obstacle area. The region between the green belt G1 and the green belt G2 may form a turnout region H1, the region between the green belt G3 and the green belt G4 may form a turnout region H2, and the region between the isolation belt E1 and the isolation belt E2 may form a turnout region H3.

102, determining a lane area adjacent to the obstacle area, and splicing part of the lane area and the turnout area to form a target area; the lane areas and the edge lanes are respectively located at two sides of the obstacle area.

In order to identify a target object that may pass through the crossing area and affect normal running of the vehicle, a target area where the target object is acquired may be first determined. The target object may be any movable object, such as a pedestrian, an automobile, a bicycle, an animal, or the like.

Specifically, a lane region adjacent to the obstacle region may be determined first, wherein the lane region is a region located on the other side of the obstacle region from the edge lane in which the vehicle is traveling, and as shown in fig. 3, when the vehicle is traveling in the lane R1, the lane region may be a region from the lane R2 on the other side of the green belt G1 and the green belt G2 to the lane R4. After the lane area is determined, the turnout area and the lane area can be spliced to form a target area.

Step 103, obtaining a target object in the target area and a first motion parameter corresponding to the target object.

After determining the target area, the target area may be scanned by a camera and/or a radar (for example, millimeter wave radar, laser radar, etc.), sensor information (for example, optical image, radar image and laser lattice cloud image) corresponding to the target area may be generated, then, feature analysis may be performed on one image of the sensor information or fusion feature analysis may be performed on multiple images of the sensor information, so as to identify the target object in the target area, and then, according to the sensor information obtained at different moments, the first motion parameters of each target object may be determined.

The first motion parameter may include a type, a motion speed, a motion direction, and the like of the target object, and further, in order to more accurately predict a travel path of the target object according to the first motion parameter, the first motion parameter may further include parameters such as an acceleration, an angular acceleration (the angular acceleration may be used to indicate a change speed of the motion direction of the target object), and the like of the target object.

It should be noted that, after the target area is determined, the identification of the target object and the determination of the first motion parameter in the target area may be continuously performed, and the first motion parameter of the target object is continuously updated, so that the following prediction result of the motion path of the target object may be more accurate.

And 104, when the first motion parameter and the second motion parameter of the vehicle meet the avoidance condition, adjusting the running speed and/or the running direction of the vehicle so as to control the vehicle to avoid the target object.

After determining the target area, a second motion parameter of the vehicle needs to be acquired in real time, wherein the second motion parameter may include a type, a motion speed, a motion direction and the like of the vehicle, and further, in order to more accurately predict a running path of the vehicle according to the second motion parameter, the second motion parameter may further include parameters such as acceleration, angular acceleration (angular acceleration may be used to indicate a change speed of the motion direction of the vehicle) and the like of the vehicle.

And predicting future running tracks of the target object and the vehicle through the first motion parameter and the second motion parameter, so as to calculate whether the target object collides with the vehicle.

If it is determined that the target object collides with the own vehicle, the power output of the vehicle may be interrupted, and a braking force may be output to reduce the traveling speed of the vehicle so that the target object has traveled off the edge lane when the vehicle travels near the turnout region, thereby avoiding the collision. If the collision cannot be avoided even though the vehicle is decelerating, the vehicle can be stopped, and the warning light is turned on to prompt the safety of the rear vehicle.

The steering system of the vehicle may also be controlled to output a steering torque that deflects the direction of travel of the vehicle so as to bypass the target object to avoid a collision.

It should be noted that, collision avoidance may be divided into two stages, where the first stage may only send out collision warning information composed of sound, vibration or image to the user, so as to remind the user that a collision may occur in front of the user, please notice avoidance, and if the second motion parameter and the first motion parameter still satisfy the avoidance condition after sending out the collision warning information and passing through the preset safety time, that is, the target object collides with the vehicle, then direct intervention may be performed on the running speed and/or the running direction of the vehicle according to the above adjustment policy, so as to avoid the collision.

In addition, the user can adjust the prompting time of the collision warning information through the man-machine interaction interface according to the use habit of the user, for example, the prompting time can be divided into a plurality of modes such as excitation, normal and the like. The aggressive mode refers to sending collision warning information to the user as late as possible.

Referring to fig. 4, a flowchart of steps of another vehicle control method according to an embodiment of the present invention is shown.

Step 201, obtaining positioning information of the vehicle.

For the acquisition of the vehicle positioning information, two cases can be distinguished:

in the first case, where the vehicle is outdoors, good satellite positioning data can be obtained, at which time accurate current positioning information of the vehicle can be calculated from the satellite positioning data.

In the second case, the vehicle is in a room, especially when the vehicle is in the ground, the vehicle cannot acquire satellite positioning data or satellite positioning signals are poor due to the shielding of the building, and the accurate position of the vehicle cannot be determined through the satellite positioning data. However, since the mobile communication signal has stronger penetrating power than the satellite positioning signal, and a communication base station is usually built in the building, the vehicle can receive the communication signal of the communication base station to perform base station positioning, so as to determine the current specific position of the vehicle.

And 202, comparing the positioning information with a road map, and determining that the vehicle is in an edge lane under the condition that the comparison result indicates that one side of the lane where the vehicle is not adjacent to other lanes.

The road map may refer to a high-precision map containing roads on which the vehicle is currently traveling, in which each lane in the roads is included. The road map may be stored locally on the vehicle or may be obtained from a server.

The positioning information may be input into the road map, lane information corresponding to the positioning information in the road map may be determined, and if the lane information indicates that the attribute of the lane is an edge lane, it may be determined that the vehicle is in the edge lane. The lane environment corresponding to the positioning information in the road map can be judged, and if the distance between one side of the lane corresponding to the positioning information and other lanes exceeds the preset obstacle width, which indicates that an obstacle exists between the current lane of the vehicle and the adjacent lane, the current lane of the vehicle can be determined to be the edge lane.

It should be noted that, the vehicle map may also be stored in a server, the vehicle may send its own positioning information to the server, the server compares the positioning information with the road map, and returns the comparison result to the vehicle.

And 203, determining the intersection positions at two sides of the edge lane according to the positioning information of the vehicle and the road map.

In the road map, if a road junction exists in front of the current road on which the vehicle is traveling, the road junction is reflected in the road map in the form of a branching route, so that the road junction position on the edge lane in the traveling direction of the vehicle can be acquired from the road map by the positioning information of the vehicle.

Specifically, the current position of the vehicle can be marked in the road map according to the positioning information of the vehicle, then the intersection positions at two sides of the edge lane within a certain distance from the vehicle in the running direction of the vehicle are determined, and then the intersection distance from each intersection position to the current position of the vehicle is determined according to the corresponding scale of the road map. Therefore, the turnout region can be further searched in the actual road scene according to the intersection distance.

And 204, acquiring barrier areas on two sides of the edge lane.

Since the crossing area is generally located where the barrier area is discontinuous. Therefore, it is necessary to first acquire obstacle regions on both sides of the edge lane, and then determine the intersection region from the obstacle regions.

Specifically, the two sides of the edge lane where the vehicle is located can be scanned through a camera, a radar and the like, and an obstacle area model of the two sides of the edge lane where the vehicle is located is built.

Step 205, determining a second probability of existence of the turnout region at the intersection position according to the gap width of the obstacle region at the intersection position.

After the obstacle region models on two sides of the edge lane where the vehicle is located are obtained, determining the intersection position in the obstacle region models according to the intersection distance, and calculating the obstacle region gap in the preset search distance near the intersection position, wherein the obstacle region consists of adjacent obstacle subregions, and the obstacle region gap is the gap between the adjacent obstacle subregions on the same side of the edge lane where the vehicle is located.

After finding the gap of the obstacle region near the intersection position, determining the gap width of the gap of the obstacle region, and determining the second probability that the position of the gap of the obstacle region is the turnout region according to the gap width of the obstacle region, wherein the larger the gap width of the obstacle region is, the larger the second probability that the position of the gap of the obstacle region is the turnout region is.

And 206, determining a turnout region according to the clearance space of the obstacle region at the intersection position under the condition that the second probability is larger than or equal to a second preset probability.

The vehicle may be preset with a second preset probability for comparison with the second probability to determine whether to determine a gap space of the obstacle region at the intersection position as the turnout region.

The clearance space refers to the space between two adjacent obstacle subregions positioned on the same side of the edge lane where the vehicle is positioned. As shown in fig. 3, the green belt G1 and the green belt G2 are two adjacent obstacle subregions, and the region H1 between the green belt G1 and the green belt G2 is a turnout region.

And step 207, splicing part of the lane area and the turnout area to form a target area.

Optionally, step 207 may further include:

substep 2071, determining an area within a preset width of the obstacle area on the side facing away from the edge lane as a lane area adjacent to the obstacle area.

Since the target region is a region where a target object that may collide with the vehicle appears, the target region may include a region on the side of the obstacle region facing away from the edge lane where the vehicle is located, and a turnout region. Referring to fig. 5, a schematic diagram of a track of a target object according to an embodiment of the present application is shown, as shown in fig. 5, in which a vehicle C1 travels in a lane R1, and then the target object may travel from a turnout area into the lane R1 through three tracks a, b, and C.

Specifically, an area within a preset width of the obstacle area on the side facing away from the edge lane where the vehicle is located may be first determined as a lane area adjacent to the obstacle area. The target object in the lane area may suddenly appear in front of the edge lane where the vehicle is located through the turnout area, so that the position of the target object in the lane area needs to be predicted in advance to control the vehicle to avoid in time in advance.

Sub-step 2072, splicing the lane area within a preset distance from the turnout area with the turnout area to form a target area.

After determining the lane region, the lane region within a preset distance from the turnout region in the lane region can be intercepted by taking the turnout region as a starting point, and the lane region and the turnout region are spliced to obtain the target region. As shown in fig. 5, the longitudinal line area is a lane area within a preset distance from the turnout area, the transverse line area is a turnout area, and the longitudinal line area and the transverse line area jointly form a target area.

Step 208, obtaining a target object in the target area and a first motion parameter corresponding to the target object.

Specifically, the obstacle images on two sides of the vehicle can be obtained through the camera, the types of the obstacles on two sides of the edge lane where the vehicle is located are identified, if the obstacle images indicate that the obstacle area is a low-light-transmittance obstacle such as a green belt and a partition wall, the laser radar can be further started, and the target object in the target area shielded by the obstacle area and the first motion parameter corresponding to the target object are obtained through the small gaps in the obstacle area by the laser radar.

Because the point cloud density generated by the laser radar is higher and each point contains distance information, points (points which are formed by objects outside the target area) which are smaller than the distance range (the probability of the points being caused by the shielding of the obstacle area) in the point cloud image generated by the laser radar can be removed according to the distance range between the target area and the vehicle, points (points formed by objects outside the target area) which are beyond the distance range are removed, so that the point cloud image which only contains the objects in the target area is obtained, and the target object in the target area which is shielded by the obstacle area and the first motion parameter corresponding to the target object can be determined according to the point cloud image.

If the obstacle image indicates that the obstacle area is an isolation net or a metal grille lamp with high light transmittance, the target object in the target area and the first motion parameter corresponding to the target object can be obtained only through the camera.

It is easy to understand that, in order to improve the accuracy of acquiring the target object and the first motion parameter corresponding to the target object, a mode of fusing a camera, millimeter wave radar and laser radar may be adopted, for example, 5 millimeter wave radars may be adopted to acquire radar images around the vehicle, 1 camera may be adopted to acquire visual images around the vehicle, and 1 laser radar may be adopted to acquire point cloud images around the vehicle, the radar images, the visual images and the point cloud images are fused to obtain a fused image, then a target area is determined from the fused image, the target object in the target area is identified, and the first motion parameter of the target object is acquired.

Optionally, step 208 may further include:

a substep 2081 of obtaining sensor information of the target area; wherein the sensor information includes at least one of millimeter wave radar information, camera information, and laser radar information.

Sub-step 2082, determining a target object in the target area and a first motion parameter corresponding to the target object according to the sensor information; wherein the first motion parameter comprises at least one of a position, a motion speed and a motion direction.

Since a large amount of operation resources are consumed in determining the first motion parameter of the target object and then predicting the target object trajectory according to the first motion parameter, in order to reduce the operation pressure, a preset number (for example, 1) of target objects closest to the turnout region may be selected from the target objects and the first motion parameters thereof may be acquired, and then the subsequent steps are performed on the preset number of target objects.

Step 209, when the first motion parameter and the second motion parameter of the vehicle meet the avoidance condition, adjusting the running speed and/or running direction of the vehicle to control the vehicle to avoid the target object.

When the target object is avoided, two avoidance strategies can be adopted, one is to avoid the target object by changing the speed of the vehicle, for example, the vehicle is decelerated or stopped; and secondly, avoiding the target object by changing the running direction of the vehicle, for example, enabling the vehicle to bypass the target object.

Optionally, step 209 may further include:

step 2091 predicts a collision probability of the target object with the vehicle based on the first motion parameter and the second motion parameter.

The future position of the vehicle can be predicted according to the second motion parameter of the vehicle, the future position of the target object can be predicted according to the first motion parameter, the nearest distance between the position of the target object and the position of the vehicle at the same time in the future can be obtained, the collision probability of the target object and the vehicle can be determined according to the nearest distance, and the smaller the nearest distance is, the larger the collision probability is according to the principle.

Step 2092, calculating an arrival time of the vehicle at the turnout region according to the second motion parameter, in a case that the collision probability is greater than a third probability threshold.

A third probability threshold may be stored in the vehicle, which may be determined experimentally by a skilled person. Meanwhile, the severity of the consequences caused by the collision of the vehicle at different speeds is different, so that the third probability threshold value can dynamically change along with the speed of the vehicle, the third probability threshold value can be smaller when the speed of the vehicle is higher, and the third probability threshold value can be larger when the speed of the vehicle is lower.

When the collision probability is detected to be larger than the third probability threshold value, the arrival time when the vehicle arrives at the edge lane where the vehicle is located at the turnout area can be calculated according to the second motion parameter, and the avoidance strategy to be executed can be further determined according to the arrival time.

Step 2093, calculating a target distance of the target object entering the edge lane at the arrival time according to the first motion parameter.

In order to avoid potential safety hazards caused by emergency braking of the vehicle, for example, situations such as out-of-control and rear-end collision of the vehicle, the target distance of the target object entering the edge lane at the arrival time can be calculated according to the first motion parameters, if the target distance of the target object entering the edge lane at the arrival time is shorter, the degree of shielding the driving route of the vehicle by the target object is lighter, and the vehicle can bypass the target object by adopting a strategy of deflecting the driving direction so as to avoid potential safety hazards caused by emergency braking.

Step 2094, adjusting a driving direction of the vehicle to control the vehicle to avoid the target object when the target distance is smaller than a second preset distance and an avoidance space exists at a side of the edge lane away from the obstacle region.

Specifically, since the target object is driven into the edge lane from the side of the edge lane close to the obstacle region, it can be further determined whether an avoidance space exists on the side of the edge lane away from the obstacle region when the target distance is smaller than the second preset distance, and the driving direction of the vehicle can be adjusted when the avoidance space exists on the side of the edge lane away from the obstacle region, so that the vehicle is deflected to the side of the edge lane away from the obstacle region, and the target object is bypassed to avoid collision.

Step 2095, reducing the running speed of the vehicle to control the vehicle to avoid the target object when the target distance is greater than or equal to a second preset distance and/or an avoidance space does not exist on the side, away from the obstacle region, of the edge lane.

If the target distance is greater than or equal to the second preset distance, the vehicle needs to turn at a large angle to possibly avoid the target object, however, the vehicle is extremely easy to be out of control due to the large-angle turning of the vehicle, so that in order to avoid secondary accidents, the vehicle speed can be reduced to avoid the target object under the condition that the target distance is greater than or equal to the second preset distance.

It is easy to understand that if there is no avoidance space on the side of the edge lane away from the obstacle region, the target vehicle cannot be avoided by changing the driving direction of the vehicle, and at this time, the target object can be avoided by reducing the vehicle speed.

Further, in the process of reducing the vehicle speed, the collision probability with the target object may be continuously determined, and if it is determined that the collision probability with the target object is smaller than the third probability threshold, the vehicle speed reduction may be stopped, and the vehicle speed may be restored to the running speed before the vehicle actively reduces the vehicle speed after passing through the turnout region.

Referring to fig. 6, a flowchart of steps of yet another vehicle control method according to an embodiment of the present invention is shown.

Step 301, lane line information of a road where the vehicle is located and obstacle information on two sides of the vehicle are obtained.

Due to the influences of factors such as topography, cloud cover and buildings, a vehicle sometimes cannot perform positioning operation in the driving process, positioning information cannot be obtained, communication with a server cannot be performed when a network is poor, and whether a lane where the vehicle is currently located is an edge lane or not can not be determined through the positioning information and a road map. At this time, whether the vehicle is in an edge lane may be determined by information acquired by a sensor (e.g., a camera, millimeter wave radar, lidar, etc.) of the vehicle.

Specifically, lane line information of a road on which the vehicle is traveling and obstacle information on both sides of the vehicle may be obtained through a camera and/or a radar.

Step 302, determining a first probability that the vehicle is in an edge lane according to the lane line information and the obstacle information.

Determining whether adjacent other lanes exist on two sides of a lane where the vehicle runs according to lane line information, if at least one of the two sides of the lane where the vehicle runs does not exist adjacent other lanes, determining the type of the obstacle on one side of the adjacent other lanes according to obstacle information, wherein the type of the obstacle can comprise objects of green belts, metal railings, pavement trees and the like which are often used as isolation belts for separating the lanes, and if the type of the obstacle is determined to be the object forming the isolation belt, determining that the vehicle is in the edge lane.

Since the decision module typically outputs a probability as a decision result in an actual decision process, for example, in a decision to determine whether there are other adjacent lanes on both sides of a lane on which the vehicle is traveling, the probability that the output value may be that there are no other lanes on at least one side is 95%, and in a decision to determine the type of obstacle, the probability that the output value may be that the type of obstacle is a green belt is 98%, these two probability values may be multiplied to obtain a first probability that the vehicle is in an edge lane.

Step 303, determining that the vehicle is in an edge lane when the first probability is greater than or equal to a first preset probability.

And 304, obtaining barrier areas on two sides of the edge lane, wherein the barrier areas comprise barrier sub-areas.

Due to the influences of factors such as topography, cloud cover and buildings, a vehicle sometimes cannot perform positioning operation in the running process, cannot obtain positioning information, cannot communicate with a server when a network is poor, and possibly cannot determine a road junction area through the positioning information and a road map. At this time, the turnout region may be determined by information acquired by a sensor (e.g., camera, millimeter wave radar, lidar, etc.) of the vehicle.

The device for acquiring the obstacle regions at both sides of the edge lane may specifically refer to step 204, which is not described in detail in the embodiment of the present application.

Step 305, determining a second probability of existence of a turnout region between adjacent barrier subregions according to the distance between the adjacent barrier subregions.

After the obstacle region models on both sides of the edge lane are obtained, the distance between the adjacent obstacle subregions can be calculated in the region models, and the larger the distance between the adjacent obstacle subregions is, the higher the second probability that a turnout region exists between the adjacent subregions is.

And 306, determining the region between the adjacent barrier subareas as a turnout region in the case that the second probability is greater than or equal to a second preset probability.

And step 307, splicing part of the lane area and the turnout area to form a target area.

Step 308, obtaining a target object in the target area and a first motion parameter corresponding to the target object.

And 309, when the first motion parameter and the second motion parameter of the vehicle meet the avoidance condition, adjusting the running speed and/or running direction of the vehicle so as to control the vehicle to avoid the target object.

In summary, an embodiment of the present invention provides still another vehicle control method, including: determining a turnout region adjacent to the edge lane in the case that the vehicle is in the edge lane; wherein the turnout region is formed by a region between adjacent barrier regions; determining a lane region adjacent to the obstacle region, and splicing part of the lane region and the turnout region to form a target region; the lane area and the edge lanes are respectively positioned at two sides of the obstacle area; acquiring a target object in a target area and a first motion parameter corresponding to the target object; and when the first motion parameter and the second motion parameter of the vehicle meet the avoidance condition, adjusting the running speed and/or the running direction of the vehicle so as to control the vehicle control target object. According to the embodiment of the invention, the motion parameters of the target object on the other side of the isolation belt and in the turnout in the isolation belt can be obtained when the vehicle is in the edge lane, so that whether the target object is likely to collide with the vehicle or not is judged, and the vehicle is timely controlled to avoid the target object when the target object is likely to exit from the turnout and collide with the vehicle, so that the driving safety is greatly improved.

On the basis of the embodiment, the embodiment of the invention also provides a vehicle control device.

Referring to fig. 7, a block diagram of a vehicle control apparatus according to an embodiment of the present invention is shown:

a turnout determination module 401, configured to determine a turnout region adjacent to an edge lane when the vehicle is in the edge lane; wherein the turnout region is formed by a region between adjacent barrier regions;

a region determining module 402, configured to determine a lane region adjacent to the obstacle region, and splice a part of the lane region and the turnout region to form a target region; the lane areas and the edge lanes are respectively positioned at two sides of the obstacle area;

a target determining module 403, configured to obtain a target object in the target area and a first motion parameter corresponding to the target object;

and the avoidance module 404 is configured to adjust a running speed and/or a running direction of the vehicle when the first motion parameter and the second motion parameter of the vehicle meet an avoidance condition, so as to control the vehicle to avoid the target object.

Optionally, the apparatus further includes:

the first information acquisition module is used for acquiring positioning information of the vehicle;

The first lane judging module is used for comparing the positioning information with a road map, and determining that the vehicle is positioned in an edge lane under the condition that the comparison result indicates that one side of the lane where the vehicle is positioned is not adjacent to other lanes.

Optionally, the apparatus further includes:

the second information acquisition module is used for acquiring lane line information of a road where the vehicle is located and barrier information on two sides of the vehicle;

the first probability module is used for determining a first probability that the vehicle is in an edge lane according to the lane line information and the obstacle information;

the second vehicle road judging module is used for determining that the vehicle is in the edge lane under the condition that the first probability is greater than or equal to a first preset probability.

Optionally, the fork determining module includes:

the intersection determination submodule is used for determining intersection positions at two sides of the edge lane through the positioning information of the vehicle and a road map;

a first obstacle region acquisition sub-module for acquiring obstacle regions on both sides of the edge lane;

the intersection second probability submodule is used for determining the second probability of existence of the turnout region at the intersection position according to the gap width of the obstacle region at the intersection position;

And the first determination submodule of the crossing is used for determining a crossing region according to the clearance space of the barrier region at the crossing position under the condition that the second probability is larger than or equal to the second preset probability.

Optionally, the fork determining module includes:

a second obstacle region acquisition sub-module, configured to acquire obstacle regions on both sides of the edge lane, where the obstacle regions include obstacle sub-regions;

the obstacle region second probability submodule is used for determining the second probability of the existence of a turnout region between adjacent obstacle subregions according to the distance between the adjacent obstacle subregions by the obstacle region;

and the second determination submodule of the turnout junction is used for determining the area between the adjacent barrier subareas as the turnout junction area under the condition that the second probability is larger than or equal to a second preset probability.

Optionally, the area determining module includes:

a lane region submodule, configured to determine a region within a preset width of one side, facing away from the edge lane, of the obstacle region as a lane region adjacent to the obstacle region;

and the target area submodule is used for splicing the lane area within a preset distance from the turnout area with the turnout area to form a target area.

Optionally, the target determining module includes:

the sensor information sub-module is used for acquiring sensor information of the target area; the sensor information comprises at least one of millimeter wave radar information, camera information and laser radar information;

the motion parameter sub-module is used for determining a target object in the target area and a first motion parameter corresponding to the target object according to the sensor information; wherein the first motion parameter comprises at least one of a position, a motion speed and a motion direction.

Optionally, the avoidance module includes:

a collision probability sub-module for predicting a collision probability of the target object with the vehicle according to the first motion parameter and the second motion parameter;

the arrival time submodule is used for calculating the arrival time of the vehicle at the turnout region according to the second motion parameter under the condition that the collision probability is larger than a third probability threshold value;

the target distance ion module is used for calculating the target distance of the target object entering the edge lane at the arrival time according to the first motion parameter;

the first avoidance strategy submodule is used for adjusting the running direction of the vehicle to control the vehicle to avoid the target object when the target distance is smaller than a second preset distance and an avoidance space exists at one side of the edge lane away from the obstacle region;

And the second avoidance strategy submodule is used for reducing the running speed of the vehicle so as to control the vehicle to avoid the target object under the condition that the target distance is greater than or equal to a second preset distance and/or an avoidance space does not exist on one side of the edge lane away from the obstacle region.

In summary, an embodiment of the present invention provides a vehicle control device, including: determining a turnout region adjacent to the edge lane in the case that the vehicle is in the edge lane; wherein the turnout region is formed by a region between adjacent barrier regions; determining a lane region adjacent to the obstacle region, and splicing part of the lane region and the turnout region to form a target region; the lane area and the edge lanes are respectively positioned at two sides of the obstacle area; acquiring a target object in a target area and a first motion parameter corresponding to the target object; and when the first motion parameter and the second motion parameter of the vehicle meet the avoidance condition, adjusting the running speed and/or the running direction of the vehicle so as to control the vehicle control target object. According to the embodiment of the invention, the motion parameters of the target object on the other side of the isolation belt and in the turnout in the isolation belt can be obtained when the vehicle is in the edge lane, so that whether the target object is likely to collide with the vehicle or not is judged, and the vehicle is timely controlled to avoid the target object when the target object is likely to exit from the turnout and collide with the vehicle, so that the driving safety is greatly improved.

On the basis of the embodiment, the embodiment of the invention also provides another vehicle control device.

Referring to fig. 8, a block diagram of another vehicle control apparatus according to an embodiment of the present invention is shown. Comprising the following steps: the system comprises an information acquisition module 501, an information processing module 502, a avoidance decision module 503, a vehicle body control module 504 and a human-computer interaction module 505. The information obtaining module 501 may obtain a visual image through a camera, obtain a radar image through a millimeter wave radar, obtain a laser point cloud image through a laser radar, and determine a second motion parameter of the vehicle through a sensor set by the vehicle itself; the information processing module 502 may receive various information acquired by the information acquisition module 501, and acquire lane line information in a current road, and objects around the vehicle and corresponding motion parameters; the avoidance decision module 503 may determine whether the lane in which the current vehicle is located is an edge lane, and may further determine a target object in the target area and a corresponding first motion parameter, perform collision prediction, and select an avoidance policy; the vehicle body control module 504 may perform an avoidance action according to an avoidance strategy, and control the vehicle to perform a lateral avoidance (change a vehicle driving direction) and/or a longitudinal avoidance (change a vehicle driving speed); the man-machine interaction module 505 may respond to an input operation of a user, turn on or off a turnout avoidance function, and/or adjust a trigger timing of collision early warning.

The embodiment of the invention also provides a whole vehicle controller, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, and is characterized in that the processor executes the vehicle control method.

The embodiment of the invention also provides a vehicle, which comprises the whole vehicle controller.

It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing apparatus embodiments, and are not repeated herein.

The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.

The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.

Claims

1. A vehicle control method applied to an overall vehicle controller of a vehicle, the method comprising:

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

acquiring positioning information of the vehicle;

and comparing the positioning information with a road map, and determining that the vehicle is positioned in an edge lane under the condition that the comparison result indicates that one side of the lane where the vehicle is positioned is not adjacent to other lanes.

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

the method comprises the steps of obtaining lane line information of a road where a vehicle is located and barrier information on two sides of the vehicle;

determining a first probability that the vehicle is in an edge lane according to the lane line information and the obstacle information;

and determining that the vehicle is in an edge lane under the condition that the first probability is greater than or equal to a first preset probability.

4. The method of claim 1, wherein the determining a turnout region adjacent to the edge lane comprises:

determining intersection positions at two sides of the edge lane through the positioning information of the vehicle and a road map;

obtaining barrier areas on two sides of the edge lane;

determining a second probability of existence of the turnout region at the intersection position according to the gap width of the obstacle region at the intersection position;

and determining a turnout region according to the clearance space of the obstacle region at the intersection position under the condition that the second probability is larger than or equal to a second preset probability.

5. The method of claim 1, wherein the determining a turnout region adjacent to the edge lane comprises:

Acquiring barrier areas on two sides of the edge lane, wherein the barrier areas comprise barrier sub-areas;

determining a second probability of a turnout region existing between adjacent barrier subregions according to the distance between the adjacent barrier subregions;

and determining the area between the adjacent barrier subareas as a turnout area under the condition that the second probability is larger than or equal to a second preset probability.

6. The method of claim 1, wherein the stitching a portion of the lane region and the turnout region to form a target region comprises:

determining an area within a preset width of one side, away from the edge lane, of the obstacle area as a lane area adjacent to the obstacle area;

and splicing the lane region within a preset distance from the turnout region with the turnout region to form a target region.

7. The method according to claim 1, wherein adjusting the running speed and/or running direction of the vehicle to control the vehicle to avoid the target object when the first motion parameter and the second motion parameter of the vehicle satisfy an avoidance condition comprises:

Predicting the collision probability of the target object and the vehicle according to the first motion parameter and the second motion parameter;

calculating the arrival time of the vehicle at the turnout region according to the second motion parameter under the condition that the collision probability is larger than a third probability threshold;

calculating the target distance of the target object entering the edge lane at the arrival time according to the first motion parameter;

when the target distance is smaller than a second preset distance and an avoidance space exists at one side of the edge lane away from the obstacle area, adjusting the running direction of the vehicle to control the vehicle to avoid the target object;

and reducing the running speed of the vehicle to control the vehicle to avoid the target object under the condition that the target distance is greater than or equal to a second preset distance and/or an avoidance space does not exist on one side of the edge lane away from the obstacle region.

8. A vehicle control apparatus, characterized in that the apparatus comprises:

9. A vehicle control unit comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the vehicle control method according to any one of claims 1 to 8 when executing the computer program.

10. A vehicle comprising a vehicle control unit according to claim 9.