CN114684120A

CN114684120A - Vehicle control method based on obstacle running track prediction

Info

Publication number: CN114684120A
Application number: CN202011637642.4A
Authority: CN
Inventors: 王清品; 罗沄; 夏敬初; 张磊磊; 史学豹
Original assignee: Hella Shanghai Electronics Co Ltd
Current assignee: Hella Shanghai Electronics Co Ltd
Priority date: 2020-12-31
Filing date: 2020-12-31
Publication date: 2022-07-01

Abstract

The invention provides a vehicle control method based on obstacle running track prediction, which comprises the following steps: the method comprises the steps that multiple sensors of a vehicle detect running state information of obstacles around the vehicle in real time; calculating and predicting the running track of the barrier according to the running state information; calculating a dynamic safety boundary of safe driving of the vehicle according to the running track of the obstacle; directing driving of the vehicle according to the dynamic safety boundary and the driving state of the vehicle. By the technical scheme, collision risks can be prompted, guidance can be provided for vehicle driving according to a safe driving boundary, the response is more sensitive and accurate, and safe driving is effectively guaranteed.

Description

Vehicle control method based on obstacle running track prediction

Technical Field

The invention relates to the field of vehicle driving safety, in particular to a vehicle control method based on obstacle running track prediction.

Background

The collision during driving is often caused by that the driver or the automatic driving vehicle does not predict the running track of other vehicles, pedestrians, isolation belts and other peripheral obstacles or the information of the relative position of the vehicle and other peripheral obstacles in time and accuracy, so that the traffic accident is caused. Therefore, it is necessary to determine whether or not an obstacle around the vehicle collides with the own vehicle, thereby reducing the occurrence of an accident. In the prior art, the movement information of an obstacle is identified through a millimeter wave radar, and whether the vehicle and the obstacle have collision risks or not is judged by calculating the longitudinal meeting time and the corresponding transverse relative distance of the vehicle and the obstacle; if so, controlling the LED light source in the vehicle high beam corresponding to the current position of the obstacle to flicker so as to perform collision early warning. However, the technical scheme can only prompt the existence of the collision risk, and cannot give specific driving guidance opinions, and particularly, no corresponding measures are taken when the collision risk exists, so that the driving safety cannot be effectively guaranteed.

Therefore, the invention provides a vehicle control method based on the obstacle running track prediction, which predicts the track of the obstacle by detecting the running state information of the obstacle, calculates the safety boundary of vehicle driving based on the running track of the obstacle, provides guidance for the vehicle driving, can also carry out risk prompt, provides corresponding measures when the risk exists, and effectively ensures the driving safety.

Disclosure of Invention

In order to solve the above problems, an object of the present invention is to provide a vehicle control method based on obstacle trajectory prediction, which predicts a motion trajectory by detecting operation state information of all stationary or moving obstacles around, calculates a safe driving boundary of a vehicle according to the motion trajectory of the obstacles, provides guidance for driving the vehicle, and can also provide risk indication to ensure driving safety.

Specifically, one aspect of the present invention provides a vehicle control method based on obstacle trajectory prediction, including the steps of: the method comprises the steps that multiple sensors of a vehicle detect running state information of obstacles around the vehicle in real time; calculating and predicting the running track of the barrier according to the running state information; calculating a dynamic safety boundary of safe driving of the vehicle according to the running track of the obstacle; directing driving of the vehicle according to the dynamic safety boundary and the driving state of the vehicle.

Preferably, the method of guiding the driving of the vehicle according to the dynamic safety margin and the driving state of the vehicle includes: judging whether unavoidable collision exists according to the dynamic safety boundary and the driving state of the vehicle; if the unavoidable collision does not exist, determining a driving strategy according to the dynamic boundary of the safe driving of the vehicle; and if the unavoidable collision exists, executing a collision early warning strategy.

Preferably, the collision warning strategy in the above method includes: sending collision early warning prompts to other traffic participants; and/or control vehicle external airbag ejection to provide cushioning for the collision.

Preferably, the operating state information of the obstacle in the above method includes position information, operating speed, acceleration, direction, and/or indicator light information.

Preferably, in the above method, the step of calculating and predicting the trajectory of the obstacle according to the operating state information includes: establishing a unified three-dimensional coordinate system; performing data fusion on the operation state information of the obstacle, which is obtained by the detection of the multiple sensors, in a unified three-dimensional coordinate system, and calculating the current operation track of the obstacle; and predicting the future running track of the barrier according to the current running track and the running state information.

Preferably, in the above method, the multiple sensors include a millimeter wave radar, a laser radar, and a binocular camera.

Preferably, in the above method, when data fusion is performed on the operating state information of the obstacle detected and obtained by the multiple sensors in a unified three-dimensional coordinate system, data fusion is performed according to the operating characteristics, the operating state, and the weather factors of the multiple sensors.

Preferably, in the above method, after the dynamic safety boundary of the safe driving of the vehicle is calculated according to the moving track of the obstacle, the dynamic safety boundary is verified and adjusted in real time according to the real-time detected moving state information of the obstacle.

Preferably, the driving strategy in the above method includes maintaining a constant speed, accelerating, decelerating, braking, and changing lanes.

Preferably, the method is as described above wherein the balloon is coated with a light reflective layer.

After the technical scheme is adopted, compared with the prior art, the method has the following beneficial effects:

1. providing driving directions to a vehicle through a safe driving boundary

2. The unavoidable collision risk is prompted, and a countermeasure is provided to ensure the driving safety.

Drawings

FIG. 1 is a flow chart of a method for vehicle control based on obstacle trajectory prediction in accordance with a preferred embodiment of the present invention;

fig. 2 is a flowchart of a vehicle control method based on obstacle trajectory prediction according to another preferred embodiment of the present invention.

Detailed Description

The advantages of the invention are further illustrated in the following description of specific embodiments in conjunction with the accompanying drawings.

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

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

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

In the following description, suffixes such as "module", "component", or "unit" used to denote elements are used only for facilitating the explanation of the present invention, and have no specific meaning in themselves. Thus, "module" and "component" may be used in a mixture.

Referring to fig. 1, a flow chart of a vehicle control method based on obstacle trajectory prediction according to a preferred embodiment of the present invention is shown, which includes the following steps: firstly, a plurality of sensors on a vehicle detect the running state information of obstacles around the vehicle in real time, wherein the obstacles around the vehicle comprise all people or objects in a moving state, such as an isolation belt, pedestrians, the vehicle and the like, and the sensors on the vehicle detect the running state information of the obstacles in real time; after the running state information of the barrier is obtained, the running track of the corresponding barrier is calculated and predicted according to the running state information; after the running track of the peripheral obstacle is obtained, calculating the dynamic safety boundary of safe driving of the vehicle according to the running track; and guiding the driving of the vehicle according to the dynamic safety boundary and the driving state of the vehicle.

In the driving process of the vehicle, a driver needs to constantly pay attention to obstacles, pedestrians, vehicles and the like around the vehicle, and the driver is easily influenced by various external factors in the driving process, so that the driver neglects the coming vehicle or the pedestrians in a certain direction, and accidents are caused. Therefore, in the technical solution of the present invention, firstly, the running state information of the obstacles is detected in real time through the sensor, the running track of the obstacles can be calculated and predicted through the detected running state information, the safe driving boundary of the vehicle is divided based on the running track of the obstacles, i.e. the vehicle is safe to drive in the boundary, and the outside of the boundary is the running track range of the obstacles, and the running state of the obstacles, especially the vehicle or the pedestrians, may be changed, so the detection of the running state information is real-time, and the safe driving boundary is dynamic. Based on the dynamic safety boundary, guidance such as acceleration, deceleration, direction change and the like can be provided for driving by combining the driving state of the vehicle such as the current direction and speed of the vehicle.

Based on the above embodiment, in a preferred embodiment consistent with the present invention, after the dynamic safety boundary of the safe driving of the vehicle is calculated according to the moving track of the obstacle, the dynamic safety boundary is verified and adjusted in real time according to the real-time detected moving state information of the obstacle. According to the technical scheme, the accuracy of the prediction of the moving track of the obstacle can be further improved, and the driving safety is guaranteed.

The technical scheme of the invention is different from the prior art that the collision possibility is calculated by simultaneously utilizing the motion state information of the vehicle and the obstacle, on one hand, the variation is too much in the scheme, the calculation cannot be accurate, the calculation of the collision possibility is deviated no matter the vehicle changes or the motion state of the obstacle changes, and on the other hand, the scheme only can give collision prompt but cannot give driving guidance and countermeasures. According to the technical scheme, firstly, only the running state information of the obstacle is monitored, the variable of the vehicle is not introduced, the running track of the obstacle is calculated through the running state information of the obstacle, and then the safe driving boundary of the vehicle is obtained. By the technical scheme, driving safety can be effectively guaranteed.

Based on the foregoing embodiments, in a preferred embodiment consistent with the present invention, the step of guiding the driving of the vehicle according to the dynamic safety margin and the driving state of the vehicle includes: judging whether unavoidable collision exists according to the dynamic safety boundary and the driving state of the vehicle; if the unavoidable collision does not exist, determining a driving strategy according to the dynamic boundary of the safe driving of the vehicle, and driving within the safe driving boundary; if there is an unavoidable collision, that is, if the obstacle is running in the running track without changing the running state, even if the vehicle is immediately decelerated, accelerated, steered or any other measures cannot avoid the collision, a collision warning strategy is executed, for example, collision warning is performed, and collision countermeasures are performed to reduce damage and loss after the collision occurs.

Based on the above embodiment, in a preferred embodiment consistent with the present invention, the driving strategy includes maintaining a constant speed, accelerating, decelerating, braking, and changing lanes, and the driving of the vehicle within the safe driving boundary is ensured by the corresponding driving strategy, so as to ensure the driving safety.

Based on the above embodiment, in a preferred embodiment consistent with the present invention, the collision warning policy includes: sending collision early warning prompts to other traffic participants; and/or control the vehicle outer airbag to pop up to provide cushioning for the collision. The unavoidable collision is that even if the vehicle immediately decelerates, accelerates, turns or takes any other measures to avoid the collision under the condition that the obstacle does not change the running state and runs in the running track, the collision can not be avoided. And the collision side outer air bag is popped out in advance, so that the buffer can be provided for inevitable collision, the personal safety is protected, and the loss caused by collision is reduced. Preferably, the air bag is coated with a reflective layer, which can effectively remind other drivers or pedestrians at night.

Based on the above embodiments, in a preferred embodiment consistent with the present invention, the operation state information of the obstacle includes position information, operation speed, acceleration, direction and/or indicator light information, the operation track of the obstacle can be accurately predicted through the position information, the operation speed information, the acceleration information and the steering information, and the change of the operation track can be predicted in advance through the indicator lights such as brake lights and steering light information, so as to more effectively guarantee driving safety. It should be noted that all of the operation state information is not required, and different obstacles and operation states may be determined according to different operation state information, such as for an immovable obstacle, position information, and an operation speed, where the operation speed is 0.

Based on the foregoing embodiment, in a preferred embodiment consistent with the present invention, the step of calculating and predicting the operation trajectory of the obstacle according to the operation state information includes: establishing a unified three-dimensional coordinate system; carrying out data fusion on the operation state information of the obstacles, which is obtained by the detection of the multiple sensors, in a unified three-dimensional coordinate system, and calculating the current operation track of the obstacles; and predicting the future running track of the barrier according to the current running track and the running state information. In this embodiment, the future operation trajectory of the obstacle is predicted not only by the current operation state information, but also by considering the current operation trajectory of the obstacle, so that the future operation trajectory of the obstacle is predicted more accurately.

The invention preferably detects through a plurality of sensors, and further preferably, the sensors are located at different positions of the vehicle, such as a front double-angle radar and a rear double-angle radar, and can detect obstacles at different positions and different angles. Further preferably, the sensors belong to different categories, such as millimeter wave radar, laser radar, binocular cameras and the like, the sensors detect the operation state of the obstacle according to the characteristics and the position of the sensors, and if coincident obstacle operation state information exists, verification or data fusion can be performed, so that the detection accuracy is improved, and the driving safety is guaranteed.

Referring to fig. 2, a flowchart of a vehicle control method based on obstacle trajectory prediction according to another preferred embodiment of the present invention is shown, in which a vehicle uses a millimeter wave radar, a laser radar and a binocular infrared camera to establish a uniform three-dimensional coordinate system for a three-dimensional environment around the vehicle, and in a vehicle driving process, multiple sensors are used to detect vehicle pedestrians on both sides of a road and obstacles on both sides of the road, and to track and predict the trajectories of the vehicle and the pedestrians in real time, and a safety boundary is defined in real time for the vehicle according to the real-time tracking and prediction of the obstacles on both sides of the road and the trajectories of the vehicle and the pedestrians, so as to provide a safe passing area for the vehicle, and to provide guidance for vehicle driving through the dynamic safety boundary. For example, when the vehicle changes lane, the vehicle condition of the target lane is scanned in advance, the vehicle of the target lane is tracked and predicted, and safe opportunity is provided for the vehicle to change lane. The method has the advantages that track tracking and prediction are carried out on pedestrians and vehicles passing transversely and vehicles passing through the auxiliary road, and even if the vehicles or obstacles block the auxiliary road in the passing process, early warning can be provided for the driving of the vehicles. Meanwhile, the camera can identify the lane change indicator light of the vehicle in the running process and identify and predict the vehicle behavior by combining the running track, and in addition, the vehicle can identify and predict according to the running track even if the lane change indicator light is not turned on in the lane change process, so that the safety risk of the vehicle caused by the sudden lane change of the vehicle on the safe running of the vehicle is effectively reduced. Further, whether unavoidable collision exists or not is judged, and when the unavoidable collision exists but certain collision risk exists, the vehicle speed is controlled in advance, the collision risk is reduced, and meanwhile the safety of personnel in the vehicle is improved. When the unavoidable collision of the vehicle is predicted, the collision side vehicle outer airbag is popped out in advance, so that the unavoidable collision is buffered, the personal safety is protected, and the loss caused by the collision is reduced. Meanwhile, the popped air bag is coated with a reflective layer to remind other drivers at night.

Preferably, when data fusion is performed on the operating state information of the obstacle detected and obtained by the multiple sensors in the unified three-dimensional coordinate system, the data fusion is performed according to the operating characteristics, the operating state and the weather factors of the multiple sensors. The weight of the camera may decrease in rainy or foggy weather, the weight is 0 when the sensor fails, and so on.

By adopting the technical scheme of the invention, the track of the obstacle is predicted by detecting the running state information of the obstacle, and the safety boundary of vehicle driving is calculated based on the running track, so that on one hand, guidance can be provided for vehicle driving, on the other hand, the collision risk can be predicted according to the safety driving boundary and the running state of the vehicle, and risk prompt, driving guidance or response measures can be provided in time, thereby being beneficial to avoiding the possible risk in the vehicle driving process and ensuring the driving safety.

It should be noted that the embodiments of the present invention have been described in terms of preferred embodiments, and not by way of limitation, and that those skilled in the art can make modifications and variations of the embodiments described above without departing from the spirit of the invention.

Claims

1. A vehicle control method based on obstacle trajectory prediction is characterized by comprising the following steps:

the method comprises the steps that multiple sensors of a vehicle detect running state information of obstacles around the vehicle in real time;

calculating and predicting the running track of the barrier according to the running state information;

calculating a dynamic safety boundary of safe driving of the vehicle according to the running track of the obstacle;

directing driving of the vehicle according to the dynamic safety boundary and the driving state of the vehicle.

2. The vehicle control method of claim 1, wherein directing the driving of the vehicle in accordance with the dynamic safety boundary and the driving state of the vehicle comprises:

judging whether unavoidable collision exists according to the dynamic safety boundary and the driving state of the vehicle;

if the unavoidable collision does not exist, determining a driving strategy according to the dynamic boundary of the safe driving of the vehicle;

and if the unavoidable collision exists, executing a collision early warning strategy.

3. The vehicle control method according to claim 2, wherein the collision warning strategy includes:

sending collision early warning prompts to other traffic participants; and/or

And controlling the vehicle outer airbag to pop up so as to provide buffering for collision.

4. A vehicle control method according to any one of claims 1 to 3, characterized in that the operating state information of the obstacle includes position information, operating speed, acceleration, direction, and/or indicator light information.

5. The vehicle control method according to claim 4, wherein the step of calculating and predicting the running locus of the obstacle based on the running state information includes:

establishing a unified three-dimensional coordinate system;

performing data fusion on the operation state information of the obstacle, which is obtained by the detection of the multiple sensors, in a unified three-dimensional coordinate system, and calculating the current operation track of the obstacle;

and predicting the future running track of the barrier according to the current running track and the running state information.

6. The vehicle control method according to claim 5, wherein the multiple sensors include a millimeter wave radar, a laser radar, and a binocular camera.

7. The vehicle control method according to claim 6, wherein data fusion is performed according to an operating characteristic, an operating state, and a weather factor of the multi-sensor when data fusion is performed on the operating state information of the obstacle detected by the multi-sensor in a unified three-dimensional coordinate system.

8. The vehicle control method according to claim 1, characterized by further comprising:

and after calculating the dynamic safety boundary of the safe driving of the vehicle according to the running track of the obstacle, checking and adjusting the dynamic safety boundary in real time according to the running state information of the obstacle detected in real time.

9. A vehicle control method as claimed in claim 2, wherein the driving strategies include holding constant speed, accelerating, decelerating, braking and lane changing.

10. A method of controlling a vehicle according to claim 3, wherein the airbag is coated with a light reflecting layer.