CN112677964A - Obstacle avoidance method, apparatus, device and medium based on lane keeping auxiliary function - Google Patents

Abstract

The embodiments of the present application disclose an obstacle avoidance method, device, device and medium based on a lane keeping assist function, which relate to the technical field of intelligent driving. Wherein, the method includes: when the lane keeping assist function is turned on, when an obstacle is detected in front of the vehicle, obtaining a change curve of the steering torque of the steering wheel with time within a set period of time and road conditions within the set period of time; according to the change curve and Road conditions, determine the category of steering torque; if the steering torque is a driving category, apply the steering torque to the vehicle's control execution system in real time, and do not exit the lane keeping function, and do not exit the lane keeping function, for the control execution system to adjust the driving direction. In this embodiment, when the lane keeping assist function is turned on, the type of steering torque can be accurately identified, and obstacles can be avoided in time.

Description

Obstacle avoidance method, device, device and medium based on lane keeping assist function

technical field

The embodiments of the present application relate to intelligent driving technologies, and in particular, to an obstacle avoidance method, device, device, and medium based on a lane keeping assist function.

Background technique

The lane keeping assist system belongs to one of the intelligent driving assistance systems. During the driving process of the vehicle, the marking line of the driving lane is identified based on the visual sensor, and the vehicle will keep the vehicle according to the distance between the vehicle and the lane lines on both sides. Drive in the center of the vehicle.

When the vehicle is driving, when the lane keeping assist function is turned on, if the torque applied by the driver on the steering wheel is less than the set threshold, it will not respond to the torque, but continue to keep the vehicle in the center of the lane; if the driver exerts the torque on the steering wheel If the torque is greater than or equal to the set threshold, the lane keeping assist function is exited and the driver takes over the vehicle.

At present, when there is an obstacle in front of the lane, the user needs to fine-tune the driving direction of the vehicle, that is, apply a torque not greater than the set threshold, then the torque for fine-tuning the driving direction of the vehicle will not be transmitted to the vehicle system, and it cannot effectively avoid obstacles and collisions , at this time, the driver needs to apply a torque greater than the set threshold to exit the lane keeping function, and then fine-tune the vehicle to avoid the obstacles ahead. After the driver applies torque to exit the lane keeping function, he needs to reduce the steering torque immediately, because the inertia of the driver's steering torque will make the body posture unstable. After passing the obstacle section ahead, the driver needs to reactivate the lane keeping function again, which is very inconvenient, affects the functional comfort, affects road traffic safety, and reduces consumer satisfaction.

SUMMARY OF THE INVENTION

The embodiments of the present application provide an obstacle avoidance method, device, device, and medium based on the lane keeping assist function, so as to accurately identify the type of steering torque when the lane keep assist function is turned on, avoid obstacles in time, and improve lane keeping The comfort of auxiliary functions reduces the frequency of function withdrawal when the function is running normally, ensures driving safety, and improves consumer satisfaction with the function.

In a first aspect, an embodiment of the present application provides an obstacle avoidance method based on a lane keeping assist function, including:

When the lane keeping assist function is turned on, when an obstacle is detected in front of the vehicle, the curve of the steering torque of the steering wheel over time within the set time period and the road conditions within the set time period are obtained;

determining the category of the steering torque according to the change curve and road conditions;

If the steering torque is in the driving category, apply the steering torque to the control execution system of the vehicle in real time, and do not exit the lane keeping function, so that the control execution system can adjust the driving direction;

The control execution system applying the steering torque to the vehicle in real time includes:

predicting the driving trajectory of the vehicle according to the time-varying curve of the steering torque;

judging whether the travel trajectory can avoid the obstacle;

If the driving trajectory can avoid the obstacle, the steering torque is applied to the control execution system of the vehicle in real time, and after passing the road section where the obstacle ahead is located, the lane keeping function continues to operate without reactivation.

In a second aspect, an embodiment of the present application further provides an obstacle avoidance device based on a lane keeping assist function, including:

an acquisition module, configured to acquire the time-varying curve of the steering torque of the steering wheel within a set period of time and the road conditions within the set period of time when an obstacle is detected in front of the vehicle when the lane keeping assist function is turned on;

a determination module, configured to determine the category of the steering torque according to the change curve and road conditions;

an applying module, configured to apply the steering torque to the control execution system of the vehicle in real time if the steering torque is in the driving category and the lane keeping function is not exited, so that the control execution system can adjust the driving direction;

When applying the steering torque to the control execution system of the vehicle in real time, the application module is specifically used for: predicting the driving trajectory of the vehicle according to the change curve of the steering torque with time; judging whether the driving trajectory can be Avoid the obstacle; if the driving trajectory can avoid the obstacle, apply the steering torque to the control execution system of the vehicle in real time, after passing the road section where the obstacle ahead is located, the lane keeping function continues to maintain run without reactivation.

In a third aspect, an embodiment of the present application further provides an electronic device, the electronic device comprising:

one or more processors;

memory for storing one or more programs,

When the one or more programs are executed by the one or more processors, the one or more processors implement the obstacle avoidance method based on the lane keeping assist function of any embodiment.

In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, implements the obstacle avoidance method based on the lane keeping assist function described in any one of the embodiments .

This embodiment provides an obstacle avoidance method executed by a driver when the lane keeping assist function is turned on. When an obstacle is detected in front of the vehicle, the time-varying curve of the steering torque of the steering wheel within a set period of time and all According to the road conditions within the set time period, the category of steering torque is determined according to the change curve and road conditions, and the actual driving situation is fully considered to improve the accuracy of category determination; when the steering torque is determined as the driving category, the steering torque is determined in real time It is applied to the control execution system of the vehicle, thereby avoiding obstacles in time, improving the comfort of the lane keeping assist function, reducing the function exit frequency when the function is running normally, ensuring driving safety and improving consumer satisfaction with the function .

Description of drawings

In order to illustrate the specific embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the specific embodiments or the prior art. Obviously, the accompanying drawings in the following description The drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

1 is a flowchart of an obstacle avoidance method based on a lane keeping assist function provided by an embodiment of the present invention;

FIG. 2 is a steering torque curve diagram of a driving category provided by an embodiment of the present invention;

3 is a steering torque curve diagram of a supervision category provided by an embodiment of the present invention;

4 is a flowchart of another obstacle avoidance method based on a lane keeping assist function provided by an embodiment of the present invention;

5 is a schematic diagram of a vehicle kinematics model provided by an embodiment of the present invention;

6 is a schematic diagram of a future driving trajectory of a vehicle provided by an embodiment of the present invention;

7 is a schematic structural diagram of an obstacle avoidance device based on a lane keeping assist function provided by an embodiment of the present application;

FIG. 8 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

Detailed ways

In order to make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be described clearly and completely below. Obviously, the described embodiments are only some, but not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present invention.

In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. The indicated orientation or positional relationship is based on the orientation or positional relationship shown in the accompanying drawings, which is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the indicated device or element must have a specific orientation or a specific orientation. construction and operation, and therefore should not be construed as limiting the invention. Furthermore, the terms "first", "second", and "third" are used for descriptive purposes only and should not be construed to indicate or imply relative importance.

In the description of the present invention, it should also be noted that, unless otherwise expressly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it may be a fixed connection or a connectable connection. Detachable connection, or integral connection; may be mechanical connection or electrical connection; may be direct connection, or indirect connection through an intermediate medium, or internal communication between two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood in specific situations.

An embodiment of the present application provides an obstacle avoidance method based on a lane keeping assist function, the flowchart of which is shown in FIG. 1 , which can be applied to the situation of obstacle avoidance when the lane keep assist function is turned on. This embodiment improves the intelligent driving industry application software of the intelligent driving assistance system, and modifies the software judgment and execution logic on the basis of the existing intelligent driving assistance system, so as to solve the problems existing in the prior art.

The method may be performed by an obstacle avoidance device based on the lane keeping assist function, which device may be constituted by software and/or hardware, and is generally integrated in an electronic device. 1, the method provided by this embodiment specifically includes:

S110. When the lane keeping assist function is enabled, and when an obstacle is detected in front of the vehicle, obtain a time-dependent curve of the steering torque of the steering wheel within a set period of time and road conditions within the set period of time.

A lane keeping assist system is installed in the vehicle of this embodiment, and the lane keeping assist system provides a lane keeping assist function, that is, during the driving process of the vehicle, the identification line of the driving lane is recognized based on the perception system, and at the same time, the vehicle will be based on the distance between the vehicle and the lane lines on both sides. Distance value to keep the vehicle in the center of the vehicle.

At present, the automatic driving system will screen out the main target according to the scene information and target information transmitted by the perception system, such as the selection of the target vehicle for the system to follow. The autopilot system has high accuracy for vehicle-level target detection and recognition, but for smaller-sized targets, such as used tires on the driveway, ice cream cones, or potholes on the ground, the perception system is highly accurate. The perception ability is insufficient, and the current automatic driving function cannot be used to automatically avoid small-sized obstacles. However, as the vehicle gradually approaches the small-sized obstacles in front, the perception system has a certain degree of accuracy in its detection and recognition. improve. Based on this, when the lane keeping assist function is turned on, the environmental information of the lane in front of the vehicle is detected through the on-board perception system, vision sensor, radar sensor, etc. When it is detected that there is an obstacle in front of the vehicle whose size is smaller than the set main target size threshold, the time-varying curve of the steering torque of the steering wheel within the set time period and the road conditions within the set time period are obtained. Among them, the set size threshold can be determined by the size that will not be recognized by the system as the main target.

The set duration can be calibrated through tests, and by performing obstacle avoidance tests under multiple durations, the duration with the required accuracy can be obtained as the set duration, for example, 2 seconds. Within the set time period, the time-dependent change curve of the steering torque of the steering wheel is obtained in real time; at the same time, the driving path of the vehicle within the set period of time is obtained through the Global Positioning System (GPS) and the vehicle's own inertial navigation, and according to the The road condition is determined by the electronic map and the driving route. Optionally, the road conditions include going straight, turning, and making a U-turn. Exemplarily, it is obtained through GPS that the vehicle travels on road section A within a set period of time, and it is obtained according to the electronic map that road section A belongs to a turning road section, and the road condition is turning.

S120. Determine the category of the steering torque according to the change curve and road conditions.

The categories of steering torque include driving category and regulatory category. FIG. 2 is a steering torque curve diagram of a driving category provided by an embodiment of the present invention, and FIG. 3 is a steering torque curve diagram of a supervision category provided by an embodiment of the present invention. In Figures 2 and 3, the abscissa is time, and the ordinate is steering torque. If the category of the steering torque is the driving category, it means that the driver expects to use the steering torque to drive the vehicle; if the category of the steering torque is the supervision category, it means that the driver expects to use the steering torque provided by the lane keeping assist function to control the vehicle. The steering torque on the steering wheel is used to demonstrate that the driver is not disengaged from the driving behavior, ensuring that the driver continues to supervise the vehicle while the function is running.

It should be noted that, compared with the prior art in which a threshold is used to distinguish torque types, this embodiment fully considers the actual situation. Different drivers have different physiological characteristics and different road conditions, resulting in some large torques applied to the steering wheel, and some The torque is small, and distinguishing by the threshold will reduce the accuracy. Based on this, this embodiment creatively improves the accuracy of category determination according to the driver's driving habits and road conditions.

S130. Determine that the steering torque category is a driving category or a supervision category. If the steering torque is in the driving category, skip to S140; if the steering torque is in the supervision category, skip to S150.

S140. Apply the steering torque to the control execution system of the vehicle in real time, and do not exit the lane keeping function, so that the control execution system can adjust the driving direction.

Specifically, the steering torque within the set time period is applied in real time. The control execution system controls the steering of the wheels according to the steering torque, thereby adjusting the driving direction of the vehicle. At the same time, with the improvement of the recognition and detection accuracy of the front obstacle by the perception system, the vehicle system will detect whether the steering torque applied by the current driver can effectively avoid the front obstacle. The size and position of the obstacle can be reasonably and effectively compensated based on the steering torque applied by the driver, so that the vehicle can safely and smoothly pass through the obstacle section ahead.

S150. Apply the steering torque provided by the lane keeping assist function to the control execution system of the vehicle, so that the control execution system controls the driving direction of the vehicle.

In this case, only the steering torque provided by the lane keeping assist function is applied to the control execution system of the vehicle, and no longer responds to the steering torque applied by the driver.

This embodiment provides an obstacle avoidance method executed by a driver when the lane keeping assist function is turned on, which solves the problem that the fine-tuning steering torque applied by the driver cannot be transmitted to the control execution system of the vehicle when the current lane keeping function is turned on. It is necessary to exit the lane keeping function before the driver's steering torque can be applied to the vehicle control execution system. When avoiding certain obstacles in front of the vehicle, it is often necessary to exit the lane keeping function first before the driver can steer to avoid the obstacles ahead. Torques are applied to the vehicle's control actuators, which are delayed for a period of time compared to normal driving behavior, which not only affects traffic safety, but also increases driver dissatisfaction with the function. Specifically, when an obstacle is detected in front of the vehicle, the time-dependent change curve of the steering torque of the steering wheel within the set time period and the road conditions within the set time period are obtained, and then the steering torque is determined according to the change curve and road conditions. It fully considers the actual driving situation and improves the accuracy of category determination; when the steering torque is determined to be the driving category, the steering torque is applied to the control execution system of the vehicle in real time, so as to avoid obstacles in time and improve lane keeping assistance The comfort of the function reduces the frequency of function withdrawal when the function is running normally, ensures the driving safety, and improves the consumer's satisfaction with the function.

In the above embodiment and the following embodiments, determining the category of the steering torque according to the change curve and road conditions includes: inputting the change curve and road conditions into a classification model, and obtaining all the output data of the classification model. The category of the steering torque; wherein, the classification model is obtained by training the steering torque variation curve samples belonging to the driving category and the steering torque variation curve samples belonging to the supervision category under different road conditions; the different road conditions include straight road conditions and turning road conditions.

Optionally, the classification model may be a deep learning-based neural network model, or a binary classification model such as a support vector machine (SVM). The change curve samples of the steering torque belonging to the driving category and the change curve samples of the steering torque belonging to the supervision category are separately collected in advance under the straight road conditions and the turning road conditions. Input the change curve samples and road conditions into the pre-built classification model, and use the torque type corresponding to the change curve samples as the target output to train the classification model.

Then, the change curve and road conditions are input into the trained classification model to obtain the output category of the steering torque.

In this embodiment, the classification of the steering torque is implemented by using the classification model, without paying attention to the influence principle of the change curve and road conditions on the classification result, and at the same time, the accuracy of the classification is improved.

4 is a flowchart of another obstacle avoidance method based on a lane keeping assist function provided by an embodiment of the present invention, which is further optimized for each embodiment, and specifically includes the following steps:

S210 , when the lane keeping assist function is enabled, and when an obstacle is detected in front of the vehicle, obtain a time-dependent curve of the steering torque of the steering wheel within a set period of time and road conditions within the set period of time.

S220. Determine the category of the steering torque according to the change curve and road conditions.

S230. Determine that the category of the steering torque is a driving category or a supervision category. If the steering torque is in the driving category, go to S240; if the steering torque is in the supervision category, go to S260.

S240. Predict the driving trajectory of the vehicle according to the time-varying curve of the steering torque. Continue to execute S241.

At present, the steering of the vehicle mostly relies on the electronic power steering system of the vehicle. By sensing the steering torque exerted by the driver on the steering wheel and the current steering angle of the steering wheel, the future driving trajectory of the vehicle can be predicted. Specifically, the steering angle and future trajectory are calculated according to the vehicle kinematics model (BICYCLE MODEL), as follows:

FIG. 5 is a schematic diagram of a vehicle kinematics model provided by an embodiment of the present invention. As shown in Figure 5, it is assumed that the vehicle has only two front and rear wheels, A and B, and C is the center of mass of the vehicle; the vehicle motion only considers the plane motion, and does not consider the influence of the Z direction, such as vehicle bumps, etc.; The effect of slip angle.

Under the above assumptions, δ _r and δ _f respectively represent the rotation angles of the rear wheels and front wheels relative to the longitudinal axis of the vehicle, which are determined by the steering wheel, and are specifically determined by the steering torque and the current steering angle of the steering wheel. Usually, the vehicle only relies on the front wheels for steering operation, so δ _r = 0 in practical applications. The distances from C to the front and rear tires A and B are l _f and l _r , the linear velocity vector of the center of mass C is represented as V, the direction β represents the angle with the longitudinal axis of the vehicle body, and ψ represents the angle between the longitudinal axis of the vehicle body and the X axis. Note: The X-axis here refers to the set forward direction, and the β here refers to the slip angle in the hypothetical condition. The β value is usually small at low speed, and can be ignored as 0. O is the instantaneous center of rotation of the three points A, B, and C (that is, the car body), and R is the distance between O and C.

△OCA and △OCB are obtained from the law of sine:

；（1）

;(1)

；（2）

;(2)

Combining the two can get:

；（3）

; (3)

；（4）

; (4)

According to the above formulas, the angular velocity of the center of mass C (that is, the car body) is obtained as:

；（5）

; (5)

The final state equation of the vehicle is:

；（6）

; (6)

According to the above calculation of the vehicle state, the future trajectory can be predicted according to the steering force distance and steering angle of the steering wheel. FIG. 6 is a schematic diagram of a future traveling trajectory of a vehicle according to an embodiment of the present invention. The predicted future driving trajectory obviously cannot avoid obstacles.

S241. Determine whether the travel trajectory can avoid the obstacle. If the driving trajectory can avoid the obstacle, go to S242; otherwise, go to S243.

Optionally, the distance between the vehicle and the obstacle is acquired in real time; when the distance is less than a set distance, the visual information of the obstacle is detected by a perception detection system, and the driving is judged according to the visual information. Whether the trajectory can avoid the obstacle; wherein, the set distance is determined according to the recognition accuracy requirement of the perception detection system.

Specifically, the perception detection system includes radar and cameras, etc. When the distance between the vehicle and the obstacle is different, the perception detection system has different recognition accuracy for the obstacle. Exemplarily, when the lidar is 300m away from the obstacle, the recognition accuracy is 10%, and when the distance from the obstacle is 150m, the recognition accuracy is 95%. The recognition accuracy requirement can be set to 95%, then the corresponding set distance is 150m. The visual information of the obstacle includes but is not limited to the shape and size of the obstacle.

If the driving trajectory passes through the obstacle, it is considered that the obstacle cannot be avoided; if the driving trajectory bypasses the obstacle, it is considered that the obstacle can be avoided.

S242 , applying the steering torque to the control execution system of the vehicle in real time, and after passing the road section where the obstacle ahead is located, the lane keeping function continues to operate without reactivation. Continue to execute S250.

If it is determined according to the visualized information that the driving trajectory can avoid obstacles, the steering torque is applied to the control execution system of the vehicle in real time.

S243 , the steering torque is compensated and applied to the control execution system of the vehicle in real time. Continue to execute S250.

If the driving trajectory cannot avoid the obstacle, take the shortest trajectory around the obstacle as the goal, and calculate the steering angle that needs to be compensated based on the current driving trajectory; then, calculate the torque to be compensated based on the steering angle, so that according to the compensated The driving trajectory predicted by the change curve of the steering torque can avoid the obstacle.

In this case, the steering torque applied by the driver and the compensated steering torque are jointly applied to the control execution system of the vehicle, so that the control execution system adjusts the driving trajectory of the vehicle. As shown in Figure 6, the compensated driving trajectory can avoid obstacles.

After passing the obstacle ahead, the compensation torque disappears automatically and the function continues to operate normally without reactivation.

This embodiment softens the exit function by detecting the visual information of the obstacle when the distance between the vehicle and the obstacle is less than the set distance, and performing torque compensation when the steering torque cannot avoid the obstacle instead of directly exiting the function. , to solve the problem in the prior art that when the lane keeping assist function is turned on, the system will not automatically avoid small obstacles in the non-vehicle, and will also shield the driver's micro-manipulation of the steering torque of the vehicle.

S250. If it is detected that there is no obstacle in front of the vehicle, obtain a time-varying curve and road conditions of the steering torque of the steering wheel within a set period of time.

Real-time detection of the environmental information of the lane in front of the vehicle through the on-board perception system, visual sensor, radar sensor, etc., when it is detected that there is no obstacle in front of the vehicle, the steering torque of the steering wheel within the set period of time and road conditions continue to be obtained.

S251. Determine the category of the steering torque according to the change curve and road conditions.

S252. If the steering torque is of the supervision category, ignore the steering torque provided by the driver, and apply the steering torque provided by the lane keeping assist function to the control execution system of the vehicle. End this operation.

Specifically, when the lane keeping assist function exits, if the steering torque is in the supervision category, the lane keeping assist function is restarted, the steering torque provided by the driver is ignored, and only the steering torque provided by the lane keeping assist function is applied to The control execution system of the vehicle; when the lane keeping assist function is supplemented, if the steering torque is in the supervision category, the vehicle is fully taken over by the lane keeping assist function, and the steering torque of the steering wheel is shielded.

S260. Apply the steering torque provided by the lane keeping assist function to the control execution system of the vehicle, so that the control execution system controls the driving direction of the vehicle.

On the basis of the above-mentioned embodiments, this embodiment adds an automatic restart operation of the lane keeping assist function after bypassing the obstacle, which does not require the user to manually start.

FIG. 7 is a schematic structural diagram of an obstacle avoidance device based on a lane keeping assist function provided by an embodiment of the present application. The embodiment of the present application is applicable to a situation in which obstacle avoidance is performed when the lane keeping assist function is enabled. With reference to FIG. 7 , the obstacle avoidance device based on the lane keeping assist function includes: an acquisition module 310 , a determination module 320 and an application module 330 .

The obtaining module 310 is configured to obtain the time-dependent curve of the steering torque of the steering wheel within a set period of time and the road conditions within the set period of time when an obstacle is detected in front of the vehicle when the lane keeping assist function is turned on;

a determination module 320, configured to determine the category of the steering torque according to the change curve and road conditions;

The applying module 330 is configured to apply the steering torque to the control execution system of the vehicle in real time if the steering torque is in the driving category, and does not exit the lane keeping function, so that the control execution system adjusts the driving direction.

When applying the steering torque to the control execution system of the vehicle in real time, the applying module 330 is specifically configured to: predict the driving trajectory of the vehicle according to the time-varying curve of the steering torque; determine whether the driving trajectory is Can avoid the obstacle; if the driving trajectory can avoid the obstacle, the steering torque is applied to the control execution system of the vehicle in real time, and the lane keeping function continues after passing the road section where the obstacle ahead is located Keep running, no need to activate again.

This embodiment provides an obstacle avoidance device executed by the driver when the lane keeping assist function is turned on, which solves the problem that the fine-tuning steering torque applied by the driver cannot be transmitted to the control execution system of the vehicle when the current lane keeping function is turned on. It is necessary to exit the lane keeping function before the driver's steering torque can be applied to the vehicle control execution system. When avoiding certain obstacles in front of the vehicle, it is often necessary to exit the lane keeping function first before the driver can steer to avoid the obstacles ahead. Torques are applied to the vehicle's control actuators, which are delayed for a period of time compared to normal driving behavior, which not only affects traffic safety, but also increases driver dissatisfaction with the function. Specifically, when an obstacle is detected in front of the vehicle, the time-dependent change curve of the steering torque of the steering wheel within the set time period and the road conditions within the set time period are obtained, and then the steering torque is determined according to the change curve and road conditions. It fully considers the actual driving situation and improves the accuracy of category determination; when the steering torque is determined to be the driving category, the steering torque is applied to the control execution system of the vehicle in real time, so as to avoid obstacles in time and improve lane keeping assistance The comfort of the function reduces the frequency of function withdrawal when the function is running normally, ensures the driving safety, and improves the consumer's satisfaction with the function.

Optionally, the determination module 320 is specifically configured to input the change curve and road conditions into a classification model to obtain the category of the steering torque output by the classification model; wherein, the classification model passes under different road conditions and belongs to The variation curve samples of the steering torque of the driving category and the variation curve samples of the steering torque belonging to the supervision category are obtained by training; the different road conditions include straight road conditions and turning road conditions.

Optionally, the device further includes: a compensation module, configured to compensate the steering torque and apply it to the control execution system of the vehicle in real time if the driving trajectory cannot avoid the obstacle; The driving trajectory predicted by the change curve of the steering torque can avoid the obstacle, and after passing the obstacle section ahead, the compensation torque disappears automatically, and the function continues to operate normally without reactivation.

Optionally, the applying module 330 is specifically used to obtain the distance between the vehicle and the obstacle in real time when judging whether the travel trajectory can avoid the obstacle; The detection system detects the visual information of the obstacle, and judges whether the driving trajectory can avoid the obstacle according to the visual information; wherein, the set distance is determined according to the recognition accuracy requirement of the perception detection system.

Optionally, the device further includes a restart module, configured to acquire the steering of the steering wheel within a set period of time if it is detected that there is no obstacle in front of the vehicle after the steering torque is applied to the control execution system of the vehicle in real time. Change curve of torque over time and road conditions; according to the change curve and road conditions, determine the category of the steering torque; if the steering torque is in the supervision category, ignore the steering torque provided by the driver, and use the lane keeping assist The steering torque provided by the function is applied to the control execution system of the vehicle.

Optionally, when the obtaining module 310 obtains the road conditions within the set time period, it is specifically used to: obtain the travel path of the vehicle within the set time period through the global positioning system and the vehicle's own inertial navigation; according to the electronic map and the travel path Determine the road conditions.

The obstacle avoidance device based on the lane keeping assist function provided by the embodiment of the present application can execute the obstacle avoidance method based on the lane keep assist function provided by any embodiment of the present application, and has functional modules and beneficial effects corresponding to the execution method.

FIG. 8 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. As shown in FIG. 8 , the device includes a processor 40, a memory 41, an input device 42, and an output device 43; the number of processors 40 in the device may be One or more, a processor 40 is taken as an example in FIG. 8; the processor 40, memory 41, input device 42 and output device 43 in the device can be connected through a bus or other means, and the connection through a bus is taken as an example in FIG. 8 .

As a computer-readable storage medium, the memory 41 can be used to store software programs, computer-executable programs and modules, such as program instructions/modules corresponding to the obstacle avoidance method based on the lane keeping assist function in the embodiment of the present invention (for example, based on the The acquisition module 310 , the determination module 320 and the application module 330 in the obstacle avoidance device of the lane keeping assist function). The processor 40 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 41 , that is, to implement the above-mentioned obstacle avoidance method based on the lane keeping assist function.

The memory 41 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. In addition, memory 41 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some instances, memory 41 may further include memory located remotely from processor 40, which may be connected to the device through a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

The input device 42 may be used to receive input numerical or character information and to generate key signal input related to user settings and function control of the device. The output device 43 may include a display device such as a display screen.

Embodiments of the present application further provide a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, implements the obstacle avoidance method based on the lane keeping assist function of any embodiment.

The computer storage medium of the embodiments of the present application may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or a combination of any of the above. More specific examples (non-exhaustive list) of computer readable storage media include: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), Erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

A computer-readable signal medium may include a propagated data signal in baseband or as part of a carrier wave, with computer-readable program code embodied thereon. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device .

Program code embodied on a computer readable medium may be transmitted using any suitable medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Computer program code for carrying out the operations of the present application may be written in one or more programming languages, including object-oriented programming languages—such as Java, Smalltalk, C++, but also conventional procedural languages, or a combination thereof. Programming Language - such as "C" language or similar programming language. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server. Where a remote computer is involved, the remote computer may be connected to the user's computer through any kind of network, including a local area network (LAN) or wide area network (WAN), or may be connected to an external computer (eg, using an Internet service provider to connect).

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, but not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: The technical solutions described in the foregoing embodiments can still be modified, or some or all of the technical features thereof can be equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the technical solutions of the embodiments of the present invention.

Claims (9)

1. An obstacle avoidance method based on a lane keeping assist function, characterized in that, comprising: When the lane keeping assist function is turned on, when an obstacle is detected in front of the vehicle, the curve of the steering torque of the steering wheel over time within the set time period and the road conditions within the set time period are obtained; determining the category of the steering torque according to the change curve and road conditions; If the steering torque is in the driving category, apply the steering torque to the control execution system of the vehicle in real time, and do not exit the lane keeping function, so that the control execution system can adjust the driving direction; The control execution system applying the steering torque to the vehicle in real time includes: predicting the driving trajectory of the vehicle according to the time-varying curve of the steering torque; judging whether the travel trajectory can avoid the obstacle; If the driving trajectory can avoid the obstacle, the steering torque is applied to the control execution system of the vehicle in real time, and after passing the road section where the obstacle ahead is located, the lane keeping function continues to operate without reactivation. 2 . The method according to claim 1 , wherein the determining the category of the steering torque according to the change curve and road conditions comprises: 2 . inputting the change curve and road conditions into a classification model to obtain the category of the steering torque output by the classification model; Wherein, the classification model is obtained by training the variation curve samples of steering torque belonging to the driving category and the variation curve samples of steering torque belonging to the supervision category under different road conditions; the different road conditions include straight road conditions and turning road conditions. 3. The method according to claim 1, wherein the method further comprises: If the driving trajectory cannot avoid the obstacle, the steering torque is compensated and applied to the control execution system of the vehicle in real time; Among them, the obstacle is avoided according to the driving trajectory predicted by the change curve of the compensated steering torque, and after passing the obstacle section ahead, the compensation torque disappears automatically, and the function continues to operate normally without reactivation. 4. The method according to claim 1, wherein the judging whether the travel trajectory can avoid the obstacle comprises: Obtain the distance between the vehicle and the obstacle in real time; When the distance is less than the set distance, the visual information of the obstacle is detected by the perception detection system, and whether the driving trajectory can avoid the obstacle is judged according to the visual information; Wherein, the set distance is determined according to the identification accuracy requirement of the perception detection system. 5. The method according to claim 1, wherein after applying the steering torque to a control execution system of the vehicle in real time, the method further comprises: If it is detected that there is no obstacle in front of the vehicle, obtain the change curve of the steering torque of the steering wheel over time and road conditions within the set period of time; determining the category of the steering torque according to the change curve and road conditions; If the steering torque is of the supervisory category, the steering torque provided by the driver is ignored, and the steering torque provided by the lane keeping assist function is applied to the control execution system of the vehicle. 6. The method according to any one of claims 1-5, wherein the acquiring road conditions within a set period of time comprises: Obtain the travel path of the vehicle within the set period of time through the global positioning system and the vehicle's own inertial navigation; The road conditions are determined according to the electronic map and the driving route. 7. An obstacle avoidance device based on a lane keeping assist function, characterized in that it comprises: an acquisition module, configured to acquire the time-varying curve of the steering torque of the steering wheel within a set period of time and the road conditions within the set period of time when an obstacle is detected in front of the vehicle when the lane keeping assist function is turned on; a determination module, configured to determine the category of the steering torque according to the change curve and road conditions; an applying module, configured to apply the steering torque to the control execution system of the vehicle in real time if the steering torque is in the driving category and the lane keeping function is not exited, so that the control execution system can adjust the driving direction; When applying the steering torque to the control execution system of the vehicle in real time, the application module is specifically used for: predicting the driving trajectory of the vehicle according to the change curve of the steering torque with time; judging whether the driving trajectory can be Avoid the obstacle; if the driving trajectory can avoid the obstacle, apply the steering torque to the control execution system of the vehicle in real time, after passing the road section where the obstacle ahead is located, the lane keeping function continues to maintain run without reactivation. 8. An electronic device, characterized in that, comprising: one or more processors; memory for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the obstacle avoidance method based on the lane keeping assist function according to any one of claims 1-6 . 9. A computer-readable storage medium having a computer program stored thereon, characterized in that, when the program is executed by a processor, the obstacle avoidance method based on the lane keeping assist function according to any one of claims 1-6 is implemented .

Images