CN113581207B

CN113581207B - Automatic lane changing optimization control method for vehicle based on automatic driving or auxiliary driving

Info

Publication number: CN113581207B
Application number: CN202110889621.XA
Authority: CN
Inventors: 王军德; 周风明; 郝江波; 高晟
Original assignee: Wuhan Kotei Informatics Co Ltd
Current assignee: Wuhan Kotei Informatics Co Ltd
Priority date: 2021-08-03
Filing date: 2021-08-03
Publication date: 2022-10-25
Anticipated expiration: 2041-08-03
Also published as: CN113581207A

Abstract

The invention provides a vehicle automatic lane changing optimization control method based on automatic driving or auxiliary driving, which aims at the technical problems in the prior art and comprises the steps of arranging a plurality of lane information acquisition cameras on a vehicle, arranging one or more middle and long focus cameras at the intersection of the roof of the vehicle and two B pillars of the vehicle, starting lane changing preparation when an automatic lane changing trigger signal is received, controlling the vehicle to transversely run towards a target lane direction in the current lane without crossing a lane line of the current lane, keeping a fixed distance or a distance range with the lane line to obtain the wider visual field information of the current lane and the target lane, and carrying out image fusion and analyzing and judging whether lane changing conditions are met or not according to comprehensive information acquired by the lane information acquisition cameras and the middle and long focus cameras. The invention provides a visual sensor arrangement scheme and an application strategy, which optimize the detection effect of a vehicle in front of the opposite side when an automatic driving vehicle changes lanes.

Description

Automatic lane changing optimization control method for vehicle based on automatic driving or auxiliary driving

Technical Field

The invention relates to the technical field of automatic driving and advanced assistant driving of vehicles, in particular to an automatic lane changing optimization control method of a vehicle based on automatic driving or assistant driving.

Background

In the existing vehicle vision sensor arrangement scheme, the problems of limited sight lines exist in the selection and installation positions of forward-looking and around-looking cameras when a vehicle changes lanes, so that lane changing, overtaking and doubling are difficult and even safety risks exist. The reason is that the adjacent lane in front and even the next adjacent lane need to be observed during lane changing, but the common forward-looking camera is installed on the longitudinal axis of the vehicle body, so that the adjacent lane is easy to be blocked by the vehicle in front and the vehicle in front of the side when being observed, and the existing looking-around or side camera is used for blind area monitoring, namely observing the vehicle in the rear of the side, so that the detection of the front of the side, particularly the front of the far side, is difficult during lane changing.

Disclosure of Invention

The invention provides a vehicle automatic lane changing optimization control method based on automatic driving or auxiliary driving, aiming at the technical problems in the prior art, and provides a visual sensor arrangement scheme and an application strategy to optimize the detection effect of a vehicle in front of the opposite side when the automatic driving vehicle changes lanes.

The technical scheme for solving the technical problems is as follows: a vehicle automatic lane changing optimization control method based on automatic driving or auxiliary driving comprises the steps that a plurality of lane information collecting cameras are arranged on a vehicle, one or more middle-long focus cameras are respectively arranged at the intersection of the roof of the vehicle and two B pillars of the vehicle, the object condition in a target lane needing to be changed is collected through the arranged middle-long focus cameras, when an automatic lane changing trigger signal is received, lane changing preparation is started, the vehicle is controlled to transversely run towards the direction of the target lane in the current lane but not to cross the lane line of the current lane, the vehicle keeps running at a fixed distance or within a distance range from the lane line to obtain wider visual field information of the current lane and the target lane, image fusion is carried out according to comprehensive information collected by the lane information collecting cameras and the middle-long focus cameras, whether lane changing conditions are met or not is analyzed, automatic lane changing is carried out if the lane changing conditions are met, otherwise, lane changing is abandoned and the current lane is kept running in the middle, and a next lane changing signal is waited.

On the basis of the technical scheme, the invention can be improved as follows.

Optionally, the lane information collecting camera includes a forward-looking camera and a look-around camera, and when the frequencies of collecting the image information by the forward-looking camera, the look-around camera and the mid-long-focus camera are not consistent, the image information is fused by adopting a frame interpolation algorithm.

It can be understood that the medium and long focus cameras installed in the scheme are high-speed cameras, and need to be subjected to image fusion with the original camera arrangement scheme. When the time synchronization and the space synchronization are carried out, if the sampling frequency is higher than that of other cameras, a prediction algorithm can be used for frame insertion, namely, the frame insertion algorithm is used for processing, so that the perception precision is improved.

Optionally, the automatic lane change triggering signal is derived from at least one of an in-vehicle automatic driving system, an auxiliary driving system, a vehicle machine system, a voice control instruction, and an action instruction.

It can be understood that the automatic lane change triggering signal may be started in a variety of ways, and this embodiment only exemplifies the above centralized triggering way for this situation, and other triggering ways may also be set in the practical application process, such as a front vehicle light signal (for performing avoidance by automatic lane change in an emergency avoidance situation), and the like.

Optionally, the automatic lane change triggering signal is associated with an automatic cruise system, and determines whether a lane change condition is met according to a current vehicle speed of the automatic cruise system, and automatically adjusts a vehicle cruise speed.

It can be understood that the situation lies in that the running speed of the vehicle, the running speed of the vehicle in the target lane and the running speeds of the preceding vehicle and the following vehicle in the lane are combined, and when the current vehicle speed cannot reach the lane change condition through calculation and analysis, the running speed can be adjusted within an allowable range to enable the current vehicle speed to reach the lane change condition, so that lane change is performed; in an autonomous driving or assisted driving environment, the vehicle speed is controlled by an auto-cruise system in most cases, and thus, the present solution is to feedback-control the running speed by the auto-cruise system.

Optionally, when information included in the image information acquired by the lane information acquisition camera reaches a set condition lower limit, the vehicle is controlled to directly perform automatic lane changing; or automatically changing the channel after rechecking and confirming the image information acquired by the middle and long-focus camera.

It can be understood that, in a general case, when the image information that can be collected by the camera of the vehicle itself can be judged that the current situation meets the lane change condition, the lane change can be directly performed, or the lane change can be performed after the image information of the middle-long-focus camera is verified. Further improve the driving safety in the lane change process.

Optionally, the lane change condition is associated with road map information, and when the determination is made, comprehensive analysis is performed by combining the speed limit of the current road section and the condition that whether the lane change is allowed on the road.

It can be understood that the lane change condition needs to consider fixed conditions and abnormal conditions of the road in addition to the vehicle conditions before and after the vehicle in the road and the vehicle conditions in the adjacent and the next adjacent lanes, the fixed conditions include road speed limit, directional lane, turning, intersection, traffic signal lamp and the like, and other factors need to be judged when the data condition meets the lane change condition.

Optionally, a time interval is set between the abandonment of lane change and the next automatic lane change.

It will be appreciated that a time interval may be provided between two starts of the automatic lane change procedure to prevent dangerous guidance of the following vehicle on the rear side by the high frequency lane change.

Optionally, the FOV of the middle telephoto camera is 40 degrees, the resolution at least reaches 8M, the detection distance is at least 100M, and the sampling frequency is at least 50Hz.

It can be understood that the middle and long focus camera is a high speed camera for accurately capturing objects moving at high speed and in a long distance.

Optionally, after the lane change preparation is started, the displacement distance of the vehicle in the current lane in the process of driving transversely to the direction of the target lane but not crossing the lane line of the current lane is 50-60cm.

It can be understood that when the vehicle is displaced 50-60cm in the transverse direction, the safe distance of about 35cm is still left between the lane lines of the adjacent lanes (lane width is 3.5-3.75 m in national standard, and the width of each side is 85-95cm when the vehicle runs in the middle). After the transverse displacement is 50-60cm, the shielding of the vehicle in front of the current lane of the vehicle can be basically avoided, and the conditions of the far position of the current lane, the adjacent lane and the next adjacent lane are detected; of course, in this case, the vehicle maintains a forward traveling state rather than directly traversing.

Drawings

Fig. 1 is a schematic diagram of a lane change control flow of an automatic lane change optimization control method for a vehicle based on automatic driving or auxiliary driving according to the present invention.

Detailed Description

The following detailed description of embodiments of the present invention is provided in connection with the accompanying drawings and examples. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.

In the description of the present invention, unless otherwise specified and limited, it is to be noted that the terms "mounted," "connected," and "connected" are to be interpreted broadly, and may be, for example, a mechanical connection or an electrical connection, a communication between two elements, a direct connection, or an indirect connection via an intermediate medium, and specific meanings of the terms may be understood by those skilled in the art according to specific situations.

Fig. 1 is a diagram of an automatic lane change optimization control method for a vehicle based on automatic driving or assisted driving according to the present invention, and as shown in fig. 1, the automatic lane change optimization control method for a vehicle based on automatic driving or assisted driving disclosed in this embodiment includes: the method comprises the following steps that a plurality of lane information acquisition cameras are arranged on a vehicle, one or more middle and long-focus cameras are respectively arranged at the intersection of the roof of the vehicle and two B pillars of the vehicle, and the arranged middle and long-focus cameras are used for acquiring object conditions in a target lane to be changed, including obstacles, vehicle conditions in adjacent lanes, pedestrian conditions and the like; in addition, the information in the current lane is automatically collected by an automatic driving system or an auxiliary driving system, when an automatic lane changing trigger signal is received, lane changing preparation is started, the vehicle is controlled to transversely run towards the direction of a target lane in the current lane but not to cross the lane line of the current lane, the vehicle is kept to run at a fixed distance or a distance range with the lane line to obtain wider visual field information of the current lane and the target lane, image fusion is carried out according to the comprehensive information collected by the lane information collecting camera and the middle and long-focus camera, whether lane changing conditions are met or not is analyzed and judged, automatic lane changing is carried out if the lane changing conditions are met, otherwise lane changing is abandoned and the current central lane is kept running, and a next lane changing signal is waited.

It can be understood that, based on the defects in the background art, the embodiment of the present invention provides an automatic lane change optimization control method for a vehicle based on automatic driving or auxiliary driving, based on the schemes of a forward looking camera and a looking around camera, a middle long-focus camera is installed at the intersection of the roof and the B pillar of the vehicle, where the vehicle refers to a common vehicle such as a car or SUV vehicle, as an example, in the embodiment, a middle long-focus camera is respectively arranged at the intersection of the roof and the B pillars on both sides, the roof is basically the highest point of the vehicle, and the scheme of the middle long-focus camera is adopted, so that the effective sight line during lane change can be enlarged to the maximum extent. By combining with a specific strategy for preparing to implement lane changing, the problem of vision limitation is solved optimally through the scheme, and the higher success rate of the vehicles during lane changing can be obviously achieved.

It can be understood that the medium and long focus cameras installed in the scheme are high-speed cameras, and need to be subjected to image fusion with the original camera arrangement scheme. When the time synchronization and the space synchronization are carried out, if the sampling frequency is higher than that of other cameras, a prediction algorithm can be used for frame insertion, namely, the frame insertion algorithm is used for processing, so that the sensing precision is improved.

Optionally, the automatic lane change trigger signal is associated with an automatic cruise system, and determines whether a lane change condition is met according to a current vehicle speed of the automatic cruise system, and automatically adjusts a vehicle cruise speed.

It can be understood that the situation lies in that the running speed of the vehicle, the running speed of the vehicle in the target lane and the running speeds of the preceding vehicle and the following vehicle in the lane are combined, and when the current vehicle speed cannot reach the lane change condition through calculation and analysis, the running speed can be adjusted within an allowable range to enable the current vehicle speed to reach the lane change condition, so that lane change is performed; in an autonomous driving or assisted driving environment, the vehicle speed is controlled by an automatic cruise system in most cases, and thus, the present solution consists in feedback-controlling the driving speed by an automatic cruise system.

Optionally, when the information contained in the image information acquired by the lane information acquisition camera reaches a set condition lower limit, controlling the vehicle to directly perform automatic lane changing; or automatically changing the channel after rechecking and confirming the image information acquired by the middle and long-focus camera.

It can be understood that, in a general case, when the image information that can be collected by the camera of the vehicle itself can be judged that the current situation meets the lane change condition, the lane change can be directly performed, or the lane change can be performed after the image information of the middle-long-focus camera is verified. Further improve the driving safety in the course of changing lanes.

Optionally, the lane change condition is associated with road map information, and when the determination is made, the speed limit of the current road section and whether the lane change condition of the road is allowed or not are combined to perform comprehensive analysis.

Optionally, a time interval is set between the time when the lane change is abandoned and the time when the lane change is performed next time.

It will be appreciated that a time interval may be provided between two starts of the auto-lane-change procedure to prevent dangerous guidance of the trailing vehicle on the rear side by high frequency lane changes.

It can be understood that the middle and long focus cameras are high-speed cameras and are used for accurately capturing objects moving at high speed and in a long distance.

It will be appreciated that when the vehicle is positioned 50-60cm laterally, there is still a safe distance of about 35cm from the lane line of the adjacent lane (lane width of 3.5-3.75 m in national standard, and vehicle width of 85-95cm on each side when running centrally). After the transverse displacement is 50-60cm, the shielding of the vehicle in front of the current lane of the vehicle can be basically avoided, and the conditions of the far position of the current lane, the adjacent lane and the next adjacent lane are detected; of course, in this case, the vehicle maintains a forward traveling state rather than directly traversing.

In a possible embodiment, the method for controlling automatic lane changing optimization of a vehicle based on automatic driving or assisted driving provided by the embodiment is applied to an automatic driving or assisted driving system of the vehicle, and the specific application mode is as follows: an additional middle long-focus camera is arranged at the intersection of the roof of the vehicle and the B column, and the specific parameters of the middle long-focus camera are as follows: FOV is 40 degree, resolution is at least 8M, detecting distance is at least 100M, and sampling frequency is at least 50Hz. Image information collected by a front-view camera, a look-around camera and an added middle-long-focus camera in a vehicle auxiliary driving system or an automatic driving system is fused by an image fusion technology, and the time and the space of the image information collected by three or more devices are synchronized; if the sampling frequency is inconsistent, the perception precision is improved by predicting and carrying out frame interpolation, namely, the frame interpolation algorithm is used for correcting and processing.

Specifically, when the system receives an automatic driving system, an auxiliary driving system, a vehicle machine system or a voice command and an action command (such as a gesture command) from a vehicle, an automatic lane change is triggered, lane change preparation is started, in the lane change preparation process, a vehicle is transversely displaced from the current lane to the side (namely a target lane) by about 50-60cm, and at the moment, a safe distance of about 35cm is still left between the vehicle and the line of the adjacent lane (the width of the lane in national standard is 3.5-3.75 m, and the width of each of two sides is 85-95cm when the vehicle runs in the middle). After the transverse displacement is 50-60cm, the shielding of the vehicle in front of the current lane of the vehicle can be basically avoided, and the conditions of the far position of the current lane, the adjacent lane and the next adjacent lane can be detected. And (4) integrating the detection results of the front-looking, the around-looking and the side-front long-focus cameras to judge the lane change safety. Between yes and no of the decision results, it is very common that there is an intermediate state of "non-high certainty". The purpose of continuing to drive along the direction of the lane line of the bicycle after the lateral displacement to the lane changing direction is to enlarge the detection range, particularly the sight line of the long-focus camera in the front side under the condition of ensuring the safe driving without pressing the line in the intermediate state so as to better detect the condition of the adjacent lane.

In another possible embodiment, two middle long-focus cameras are respectively arranged at the intersection of the vehicle roof and the vehicle B column, wherein the two middle long-focus cameras are respectively used for collecting image information of a front visual angle and a rear visual angle of the vehicle, and in the process, the image information collected by the plurality of middle long-focus cameras is fused and fused with image information collected by other lane information collecting cameras in the vehicle auxiliary driving system or the automatic driving system to form a complete scene picture which is displayed through the vehicle equipment and is provided for a driver to view.

It should be noted that, in the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to relevant descriptions of other embodiments for parts that are not described in detail in a certain embodiment.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention 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 present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. 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 computer, 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.

While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.

It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.

Claims

1. An automatic lane-changing optimization control method for a vehicle based on automatic driving or auxiliary driving is characterized by comprising the following steps:

arranging a plurality of lane information acquisition cameras on a vehicle, and respectively arranging one or more middle and long-focus cameras at the intersection of the roof of the vehicle and two B columns of the vehicle;

collecting the object condition in a target lane to be changed by the arranged middle and long focus cameras, starting lane change preparation when receiving an automatic lane change trigger signal, controlling a vehicle to transversely drive towards the direction of the target lane in the current lane without crossing a lane line of the current lane, and keeping a fixed distance or a distance range from the lane line to obtain wider visual field information of the current lane and the target lane;

and carrying out image fusion and analysis according to the comprehensive information acquired by the lane information acquisition camera and the middle and long-focus camera to judge whether the lane change condition is met, implementing automatic lane change if the lane change condition is met, otherwise giving up lane change and keeping the current lane running in the middle and waiting for the next lane change signal.

2. The automatic lane changing optimization control method for the vehicle based on the automatic driving or the auxiliary driving is characterized in that the lane information collecting cameras comprise a forward-looking camera and a look-around camera, and when the frequencies of the image information collected by the forward-looking camera, the look-around camera and the long-focus camera are not consistent, the image information is fused by adopting a frame interpolation algorithm.

3. The automatic lane-changing optimization control method for the vehicle based on the automatic driving or the auxiliary driving as claimed in claim 1, wherein the automatic lane-changing trigger signal is derived from at least one of an in-vehicle automatic driving system, an auxiliary driving system, an in-vehicle system, a voice control command and an action command.

4. The automatic lane-changing optimization control method for the vehicle based on the automatic driving or the auxiliary driving as claimed in any one of claims 1 to 3, wherein the automatic lane-changing trigger signal is associated with an automatic cruise system, and the automatic lane-changing trigger signal is used for judging whether a lane-changing condition is met or not according to the current vehicle speed of the automatic cruise system and automatically adjusting the cruise speed of the vehicle.

5. The automated driving-or driving-assistance-based vehicle automatic lane change optimization control method according to claim 1,

and when the information contained in the image information acquired by the lane information acquisition camera reaches the set condition lower limit, controlling the vehicle to directly perform automatic lane changing or automatically changing the lane after rechecking and confirming the image information acquired by the middle and long-focus camera.

6. The automatic driving or driving-assisted vehicle automatic lane change optimization control method according to claim 1, wherein the lane change condition is associated with road map information, and the determination needs to be performed by comprehensive analysis in combination with the speed limit of the current road section and whether the lane change condition is allowed or not.

7. The automatic driving or driving-assistance-based vehicle automatic lane change optimization control method according to claim 1, wherein a time interval is provided between the next automatic lane change and the lane change after the lane change is abandoned.

8. The automatic driving or driving-assisted vehicle lane change optimization control method according to claim 1, wherein the FOV of the intermediate long-focus camera is 40 degrees, the resolution is at least 8M, the detection distance is at least 100 meters, and the sampling frequency is at least 50Hz.

9. The automated driving-or driving-assistance-based vehicle automatic lane change optimization control method according to claim 1, wherein after starting lane change preparation, a displacement distance of the vehicle during traveling laterally in a current lane toward a target lane direction without crossing a lane line of the current lane is 50-60cm.