Vehicle lane changing control method and system, vehicle-mounted equipment and storage medium

Abstract

The invention provides a vehicle lane changing control method and system, vehicle-mounted equipment and a storage medium, and the method comprises the steps: responding to a lane changing instruction, calculating first collision time between a target vehicle and a barrier vehicle, generating the lane changing instruction according to a lane changing gesture of a driver in the target vehicle in an automatic driving mode, the controller is used for controlling a target vehicle to execute automatic lane changing operation; if the first collision time is smaller than a preset first threshold value, stopping executing the automatic lane changing operation; if the first collision time is smaller than a first threshold value and it is monitored that the target vehicle enters the manual lane changing state, second collision time between the target vehicle and the obstacle vehicle is calculated; the first threshold value is adjusted according to the second collision time, and a decision is made for follow-up automatic lane changing operation of the target vehicle according to the adjusted first threshold value. By dynamically adjusting the lane changing decision threshold, the problem of decision conflict between manual lane changing and automatic lane changing of the system is effectively solved, and the intelligence and the self-adaption level of lane changing decision are improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving technology, and in particular to a vehicle lane change control method, system, vehicle-mounted equipment, and storage medium. Background Art

[0002] With the development of autonomous driving technology, autonomous vehicles have not only made significant progress in intelligent driving during on-road driving, but also demonstrated a high degree of intelligence and user-friendly design in the interaction between the driver and the vehicle's computer and other devices within the cockpit. This intelligent interaction has greatly enhanced the driver's experience of the convenience and comfort of the intelligent driving system. Currently, there are two main ways for intelligent driving vehicles to achieve lane changes: manual triggering by the driver using a lever, and automatic lane changes by the intelligent driving system. However, relevant research and technical practices have explored the possibility of using driver gestures to achieve automatic lane change control, thereby enhancing human-vehicle interaction.

[0003] In related technologies, there are significant differences in understanding and execution between manual lane changes and automated lane changes. For example, in certain scenarios, even if a system's risk assessment deems the current conditions unsuitable, some drivers may manually change lanes based on personal experience and intuition. Conversely, when an intelligent driving system safely executes a lane change based on precise data analysis and algorithmic models, some drivers may terminate the vehicle's automated lane change for safety reasons. Therefore, the vehicle's lane change decision-making process still has certain limitations in terms of intelligence and adaptability. Summary of the Invention

[0004] The present application discloses a vehicle lane change control method, system, vehicle-mounted device and storage medium, which are used to solve the technical problems of insufficient intelligent decision-making and dynamic adaptability in vehicle lane change control.

[0005] The present application provides a vehicle lane change control method, the method comprising: calculating a first collision time between a target vehicle and an obstacle vehicle in response to a lane change instruction, wherein the lane change instruction is generated based on a lane change gesture of a driver in the target vehicle in an automatic driving mode, and is used to control the target vehicle to perform an automatic lane change operation, and the obstacle vehicle includes a vehicle located in a pre-change lane of the target vehicle and behind the target vehicle; if the first collision time is less than a preset first threshold, terminating the automatic lane change operation; if the first collision time is less than the first threshold and the target vehicle is monitored to enter a manual lane change state, calculating a second collision time between the target vehicle and the obstacle vehicle; adjusting the first threshold based on the second collision time, and making a decision on a subsequent automatic lane change operation of the target vehicle based on the adjusted first threshold.

[0006] In one embodiment of the present application, the adjusting of the first threshold according to the second collision time includes: setting a second threshold, the second threshold being the minimum collision time allowed between the target vehicle and the obstacle vehicle when the target vehicle performs an automatic lane change operation, and the second threshold being less than the first threshold; under the condition that the second collision time is greater than or equal to the second threshold, lowering the first threshold according to the second collision time, so that the lowered first threshold is greater than or equal to the second collision time.

[0007] In one embodiment of the present application, the setting method of the second threshold includes: calculating a first critical collision time based on a preset rear vehicle braking deceleration threshold, the first critical collision time being the minimum collision time allowed between the target vehicle and the obstacle vehicle when the target vehicle performs an automatic lane change operation, under the condition that the braking deceleration of the obstacle vehicle is less than the rear vehicle braking deceleration threshold; determining the larger value of the first critical collision time and the preset second critical collision time as the second threshold, wherein the second critical collision time is set according to the collision time corresponding to the collision risk warning of the obstacle vehicle.

[0008] In one embodiment of the present application, after the target vehicle is monitored to enter a manual lane change state, the method further includes: recording longitudinal speed change information of the target vehicle during the lane change process, so as to control the target vehicle to perform an automatic lane change operation according to the longitudinal speed change information when deciding to perform an automatic lane change operation of the target vehicle.

[0009] In one embodiment of the present application, after calculating the second collision time between the target vehicle and the obstacle vehicle, the method further includes: recording multiple second collision times, and recording longitudinal speed change information of the target vehicle during lane change at each second collision time; constructing an automatic lane change decision model based on the multiple second collision times and the multiple longitudinal speed change information; and controlling the target vehicle to perform an automatic lane change operation based on the automatic lane change decision model.

[0010] In one embodiment of the present application, after calculating the first collision time between the target vehicle and the obstacle vehicle, it also includes: obtaining the driver's driving experience level; determining the target threshold corresponding to the driver based on the driving experience level and a preset threshold mapping relationship table, wherein the threshold mapping relationship table includes the correspondence between each driving experience level and different first thresholds; comparing the first collision time with the target threshold to make a decision on the automatic lane change operation of the target vehicle.

[0011] In one embodiment of the present application, the method for generating the lane change instruction includes: if the lane change gesture of the driver is monitored, identifying the current lane change scenario of the target vehicle, wherein the lane change gesture includes a right lane change gesture and a left lane change gesture, and the lane change scenario includes a right overtaking lane change scenario; if the lane change gesture is the left lane change gesture, generating a first lane change instruction for changing lanes to the left; if the lane change gesture is the right lane change gesture, generating a second lane change instruction for changing lanes to the right; if the lane change gesture is the right lane change gesture, and the lane change scenario is the right overtaking lane change scenario, generating a third lane change instruction for changing lanes to the left.

[0012] The present application also provides a vehicle lane change control system, the system comprising: a calculation module for calculating a first collision time between a target vehicle and an obstacle vehicle in response to a lane change instruction, wherein the lane change instruction is generated based on a lane change gesture of a driver in the target vehicle in an automatic driving mode, and is used to control the target vehicle to perform an automatic lane change operation, and the obstacle vehicle includes a vehicle located in a pre-change lane of the target vehicle and behind the target vehicle; a lane change control module for terminating the automatic lane change operation if the first collision time is less than a preset first threshold; a monitoring module for calculating a second collision time between the target vehicle and the obstacle vehicle if the first collision time is less than the first threshold and the target vehicle is detected to have entered a manual lane change state; the lane change control module is further used to adjust the first threshold according to the second collision time, and make a decision on a subsequent automatic lane change operation of the target vehicle based on the adjusted first threshold.

[0013] The present application also provides a vehicle-mounted device, comprising: a processor; a storage device for storing a program, wherein when the program is executed by the processor, the vehicle-mounted device implements the vehicle lane change control method described in the first aspect.

[0014] The present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor of a computer, the computer is caused to execute the vehicle lane change control method described above.

[0015] Beneficial effects of the present application: The present application provides a vehicle lane change control method, system, on-vehicle device and storage medium, which calculates the first collision time between the target vehicle and the obstacle vehicle by responding to a lane change instruction, and the lane change instruction is generated according to the lane change gesture of the driver in the target vehicle in the automatic driving mode, and is used to control the target vehicle to perform an automatic lane change operation, and the obstacle vehicle includes a vehicle located in the target vehicle's pre-change lane and behind the target vehicle. If the first collision time is less than a preset first threshold, the automatic lane change operation is terminated. If the first collision time is less than the first threshold and the target vehicle is detected to enter a manual lane change state, the second collision time between the target vehicle and the obstacle vehicle is calculated, and the second collision time is calculated according to the first collision time. The first threshold is adjusted before the second collision time to make decisions on the subsequent automatic lane changing operations of the target vehicle based on the adjusted first threshold. The lane changing decision parameters are dynamically adjusted according to the actual safety situation when the driver manually changes lanes, so that the lane changing decision changes according to the driver himself, that is, the lane changing decision process of the system is optimized according to the driver's habits. The safety considerations in the system lane changing decision also constrain the driver's manual lane changing operation, so that the system decision is in line with the driver's driving habits to the greatest extent while ensuring driving safety, narrowing the decision-making gap between man and machine, and achieving the effect of man-machine-environment integration, thereby realizing more intelligent human-machine interaction and adaptive control of vehicle lane changing, and improving user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be derived from these drawings without inventive effort.

[0017] In the attached figure:

[0018] Figure 1 is a schematic diagram of an implementation environment of a vehicle lane change control system shown in an exemplary embodiment of the present application;

[0019] Figure 2 is a flow chart of a vehicle lane change control method shown in an exemplary embodiment of the present application;

[0020] Figure 3 is a flow chart of another vehicle lane change control method shown in an exemplary embodiment of the present application;

[0021] Figure 4 is a block diagram of a vehicle lane change control system shown in an exemplary embodiment of the present application;

[0022] Figure 5This is a structural diagram of a vehicle-mounted device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0023] The following describes the embodiments of the present application through specific examples. Those skilled in the art can easily understand other advantages and functions of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments. The details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present application. The following embodiments and features in the embodiments can be combined with each other without conflict.

[0024] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application. The drawings only show components related to the present application and are not drawn according to the number, shape and size of components in actual implementation. In actual implementation, the form, quantity and proportion of each component may be changed at will, and the component layout may also be more complicated.

[0025] In the following description, a large number of details are discussed to provide a more thorough explanation of the embodiments of the present application. However, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present application difficult to understand.

[0026] With the advancement of autonomous driving technology, autonomous vehicles have not only made significant advances in on-road intelligence, but also demonstrated a high degree of intelligence and user-friendly design in the in-cabin interactions between the driver and the vehicle's computer and other devices. For example, Level 3 autonomous vehicles can interact with the in-cabin system through gestures, commanding the system to perform maneuvers such as lane changes while the vehicle is in motion. In Level 3 autonomous vehicles, the driver can drive hands-free to a certain extent, leaning back to one side of the seat. To change lanes using gestures, the driver can face the road ahead or look at a specific camera in the cabin and gesture with their hands to request a lane change. The camera recognizes the gesture and automatically changes lanes based on traffic flow. This intelligent interaction significantly enhances the driver's experience of the convenience and comfort of the intelligent driving system.

[0027] However, the inventors of this application have discovered significant differences in understanding and execution between manual lane changes and automated lane changes. For example, in certain scenarios, even if a system risk assessment deems the current conditions unsuitable for a lane change, some drivers may still manually change lanes based on their personal experience and intuition. Conversely, when the intelligent driving system safely executes the lane change based on precise data analysis and algorithmic models, some drivers may terminate the vehicle's automated lane change for safety reasons. Therefore, the vehicle's lane change decision-making process still has certain limitations in terms of intelligence and adaptability.

[0028] Therefore, see Figure 1 , Figure 1 FIG. 1 is a schematic diagram of an implementation environment of a vehicle lane change control system according to an exemplary embodiment of the present application. Figure 1 As shown, the implementation environment includes a vehicle 110 and a vehicle lane change control system 120, wherein the vehicle lane change control system 120 is embedded in the vehicle 110 and is used to implement lane change control of the vehicle 110. The vehicle lane change control system 120 includes but is not limited to a vehicle-mounted system, an on-board computer, etc., and dynamically adjusts lane change decision parameters according to the actual safety situation when the driver manually changes lanes, so that the lane change decision changes according to the driver himself, that is, the lane change decision process of the system is optimized according to the driver's habits. The safety considerations in the system lane change decision also constrain the driver's manual lane change operation, so that the system decision is in line with the driver's driving habits to the greatest extent while ensuring driving safety, narrowing the decision-making gap between man and machine, and achieving the effect of man-machine-environment integration, thereby realizing more intelligent human-machine interaction and adaptive control of vehicle lane change, and improving user experience.

[0029] See Figure 2 , Figure 2 This is a flow chart of a vehicle lane change control method shown in an exemplary embodiment of the present application. This method can be applied to Figure 1 The implementation environment shown is shown. It should be understood that the method can also be applied to other exemplary implementation environments, and this embodiment does not limit the implementation environment to which the method is applicable.

[0030] like Figure 2 As shown, in an exemplary embodiment, the vehicle lane change control method includes at least steps S210 to S240, which are described in detail as follows:

[0031] Step S210, in response to a lane change instruction, calculating a first collision time between the target vehicle and an obstacle vehicle, wherein the lane change instruction is generated based on a lane change gesture of a driver in the target vehicle in the automatic driving mode and is used to control the target vehicle to perform an automatic lane change operation, and the obstacle vehicle includes a vehicle located in the lane that the target vehicle intends to change and behind the target vehicle.

[0032] Step S220: If the first collision time is less than a preset first threshold, the automatic lane change operation is terminated.

[0033] Step S230: If the first collision time is less than the first threshold and the target vehicle is detected to have entered a manual lane change state, a second collision time between the target vehicle and the obstacle vehicle is calculated.

[0034] Step S240: adjusting the first threshold according to the second collision time, and making a decision on a subsequent automatic lane change operation of the target vehicle based on the adjusted first threshold.

[0035] Among them, the lane change gesture includes a right lane change gesture and a left lane change gesture. The lane change instruction may be a right lane change instruction or a left lane change instruction, that is, the lane change instruction carries control parameters for changing lanes right or left; the first collision time refers to the estimated time when the target vehicle may collide with the obstacle vehicle when changing lanes; the first threshold is the initial collision time threshold used to decide whether the vehicle can automatically change lanes.

[0036] Exemplarily, the lane change command can be generated by capturing the driver's gesture movements through a visual recognition system, such as collecting the driver's gesture images through an in-vehicle camera and using a deep learning algorithm to classify the gestures; the calculation of the first collision time and the second collision time can be based on the relative speed and relative distance between the target vehicle and the obstacle vehicle, and are calculated using a TTC (Time to Collision) model; the first threshold can be set through experimental data based on factors such as vehicle braking performance and road conditions; the monitoring of the manual lane change status can be achieved by monitoring the steering wheel angle status, turn signal status, etc.

[0037] In step S210, if a lane change gesture of the driver in the target vehicle is detected, a lane change instruction is generated, and in response to the lane change instruction, a first collision time between the target vehicle and the obstacle vehicle is calculated to determine whether the target vehicle can perform an automatic lane change operation based on the first collision time.

[0038] In step S220, if the first collision time is less than a preset first threshold, it indicates that there is a risk of collision between the target vehicle and the obstacle vehicle during the automatic lane change operation, and therefore the automatic lane change operation is terminated. Conversely, if the first collision time is greater than or equal to the first threshold, it indicates that there is no risk of collision between the target vehicle and the obstacle vehicle during the automatic lane change operation, and therefore the automatic lane change operation can continue.

[0039] In step S230, if the first collision time is less than the first threshold and the target vehicle is detected to have entered a manual lane change state, a second collision time between the target vehicle and the obstacle vehicle is calculated.

[0040] In step S240 , the first threshold is adjusted according to the second collision time, and a decision is made on a subsequent automatic lane change operation of the target vehicle based on the adjusted first threshold.

[0041] In this embodiment, dynamic adjustment of the lane change decision threshold effectively resolves the conflict between manual and automated lane change decisions. If the system determines the lane change risk is high and the driver still insists on manually changing lanes, the system threshold is optimized based on collision time data from the actual lane change process, ensuring that subsequent automated lane change decisions are more consistent with actual driving habits. This threshold adjustment mechanism, based on feedback from actual driving behavior, maintains the rigor of system safety assessments while enhancing the adaptability of human-machine collaboration, thereby improving the intelligence and adaptability of lane change control while ensuring driving safety.

[0042] In a possible embodiment, the obstacle vehicle may further include a vehicle located in the lane that the target vehicle intends to change and in front of the target vehicle.

[0043] As a possible embodiment, when the obstructing vehicle is a vehicle located in the lane that the target vehicle wants to change and in front of the target vehicle, the above solution is also applicable.

[0044] In one embodiment, the first threshold is adjusted according to the second collision time, including: setting the second threshold, the second threshold being the minimum collision time allowed between the target vehicle and the obstacle vehicle when the target vehicle performs an automatic lane change operation, and the second threshold being less than the first threshold; and under the condition that the second collision time is greater than or equal to the second threshold, lowering the first threshold according to the second collision time, so that the lowered first threshold is greater than or equal to the second collision time.

[0045] Among them, the obstacle vehicle can be a vehicle located in the lane that the target vehicle wants to change and behind or in front of the target vehicle; the first threshold is the collision time threshold initially set by the system, which can be changed in combination with the driver's habits; the second threshold is the minimum collision time that must be met during automatic lane change, that is, the bottom line value for the system to comply with regulations and safety, and will not change according to the driver's habits.

[0046] In this embodiment, the compression adjustment of the first threshold is constrained by setting the minimum collision time that must be met in automatic lane changing. This not only retains the safety judgment standard of the system's automatic lane changing, but also optimizes the decision parameters based on the driver's actual behavior, thereby improving the adaptability of the vehicle's lane change decision.

[0047] In a possible embodiment, the second threshold is set by setting the second threshold according to a preset second critical collision time, wherein the second critical collision time is set according to a collision time corresponding to a collision risk warning of the obstructing vehicle.

[0048] The obstructing vehicle is located in the lane that the target vehicle is changing to and behind the target vehicle. The specific value of the second critical collision time can be adjusted according to the specific requirements of the warning system and is usually specified by the vehicle manufacturer or relevant safety standards. For example, it is set to 1.5 seconds.

[0049] In one embodiment, the second threshold is set by calculating a first critical collision time based on a preset rear vehicle braking deceleration threshold, where the first critical collision time is the minimum collision time allowed between the target vehicle and the obstacle vehicle when the target vehicle performs an automatic lane change operation, provided that the braking deceleration of the obstacle vehicle is less than the rear vehicle braking deceleration threshold; and determining the larger value between the first critical collision time and the preset second critical collision time as the second threshold.

[0050] The obstructing vehicle is located in the lane that the target vehicle wants to change and is behind the target vehicle. The first critical collision time is the minimum collision time allowed under the premise that the braking deceleration of the obstructing vehicle is less than the braking deceleration threshold of the rear vehicle. For example, the braking deceleration threshold of the rear vehicle is 2m / s. 2 (meters per second squared), the first critical collision time is when the braking deceleration of the obstacle vehicle is less than 2m / s 2 The minimum collision time allowed under the premise.

[0051] In this embodiment, considering that lane changes should minimize unreasonable risks to the safety of vehicle occupants and other road users, that is, lane changes must not cause collisions with other vehicles or road users on the intended road, nor must they cause the obstructing vehicle to generate significant braking deceleration, that is, the lane change process should be predictable and controllable by other road users. Therefore, a second threshold is set by combining a first critical collision time calculated based on the braking deceleration threshold of the following vehicle and a second critical collision time set based on the collision time corresponding to the collision risk warning issued by the obstructing vehicle, and the larger value of the two is taken as the second threshold. In this way, the second threshold is determined by using dual safety standards, which not only takes into account the slight braking situation of the obstructing vehicle, but also incorporates the safety requirements of the obstructing vehicle collision warning system, thereby establishing a more accurate and reliable safety margin in the automatic lane change decision.

[0052] In addition, the calculation of the first critical collision time according to the preset braking deceleration threshold of the rear vehicle can be implemented based on existing methods, which will not be described in detail in this application.

[0053] In a possible embodiment, the second threshold is set by setting the second threshold according to a preset fourth critical collision time, wherein the fourth critical collision time is set according to a collision time corresponding to a collision risk warning of the target vehicle.

[0054] As a possible embodiment, in this scenario, the obstructing vehicle is located in the lane that the target vehicle is changing to and in front of the target vehicle. The specific value of the fourth critical collision time can be adjusted according to the specific requirements of the warning system, which is usually specified by the vehicle manufacturer or relevant safety standards. For example, it is set to 1.5 seconds.

[0055] In a possible embodiment, the second threshold value is set by: calculating a third critical collision time based on a preset target vehicle braking deceleration threshold value, the third critical collision time being the minimum collision time allowed between the target vehicle and the obstacle vehicle when the target vehicle performs an automatic lane change operation, provided that the braking deceleration of the target vehicle is less than the target vehicle braking deceleration threshold value; and determining the larger value between the third critical collision time and a preset fourth critical collision time as the second threshold value.

[0056] The obstacle vehicle in this scenario is the vehicle in the lane that the target vehicle wants to change and in front of the target vehicle. The third critical collision time is the minimum collision time allowed under the premise that the braking deceleration of the target vehicle is less than the braking deceleration threshold of the target vehicle. For example, the braking deceleration threshold of the target vehicle is 2m / s. 2 (meters per second squared), the third critical collision time is when the target vehicle's braking deceleration is less than 2m / s 2 The minimum collision time allowed under the premise.

[0057] In this way, considering that lane changes should try to avoid bringing unreasonable risks to the safety of vehicle occupants and other road users, and should not cause the target vehicle to generate a large braking deceleration, the second threshold is set in combination with the third critical collision time calculated according to the target vehicle's braking deceleration threshold and the fourth critical collision time set according to the collision time corresponding to the target vehicle when the collision risk warning is issued, and the larger value of the two is taken as the second threshold. In this way, the second threshold is determined by the dual safety standards, which not only takes into account the slight braking situation of the target vehicle, but also combines the safety requirements of the target vehicle's collision warning system, thereby establishing a more accurate and reliable safety boundary in the automatic lane change decision.

[0058] In a possible embodiment, if the obstructing vehicle is a vehicle located in the lane that the target vehicle intends to change and is behind the target vehicle, the method of setting the second threshold value further includes: calculating the sum of the second critical collision time and a preset collision time margin to obtain the second threshold value; or, determining the larger value of the first critical collision time and the preset second critical collision time as the initial second threshold value, and calculating the sum of the initial second threshold value and the preset collision time margin to obtain the final second threshold value.

[0059] In a possible embodiment, if the obstructing vehicle is a vehicle located in the lane that the target vehicle intends to change and in front of the target vehicle, the method of setting the second threshold value also includes: calculating the sum of the fourth critical collision time and the preset collision time margin to obtain the second threshold value; or, determining the larger value of the third critical collision time and the preset fourth critical collision time as the initial second threshold value, and calculating the sum of the initial second threshold value and the preset collision time margin to obtain the final second threshold value.

[0060] In this way, by setting the collision time margin, the reliability of lane change decisions can be further guaranteed.

[0061] In a possible embodiment, considering that the vehicle's FCW (Forward Collision Warning) has a first-level warning and a second-level warning, and the severity of the second-level warning is higher than that of the first-level warning, the first threshold is set according to the TTC value of the first-level warning, and the second critical collision time or the fourth critical collision time is set according to the TTC value of the second-level warning.

[0062] For example, the TTC value of the first-level warning is about 2.7 seconds to 4 seconds, and the TTC value of the second-level warning is about 1.2 seconds to 1.5 seconds. The first threshold is set to 4 seconds, and the second critical collision time or the fourth critical collision time is set to 1.5 seconds.

[0063] In this way, when the target vehicle changes lanes, the FCW of the rear vehicle or the target vehicle can be prevented from generating a level 2 or higher alarm.

[0064] In one embodiment, after calculating the first collision time between the target vehicle and the obstacle vehicle, the method further includes: obtaining the driver's driving experience level; determining the target threshold corresponding to the driver based on a mapping relationship table between the driving experience level and a preset threshold value, wherein the threshold mapping relationship table includes a correspondence between each driving experience level and a different first threshold value; comparing the first collision time with the target threshold value to make a decision on the automatic lane change operation of the target vehicle.

[0065] The driving experience level is inversely proportional to the first threshold. If the driving experience level is higher, the first threshold is smaller. The threshold mapping relationship table can be formulated based on experimental data or expert experience.

[0066] In this embodiment, taking into account the different levels of proficiency of drivers, when the target vehicle does not perform an automatic lane change operation, whether they choose to change lanes manually and their judgment on the timing of manual lane changes also show great differences. Therefore, differentiated first thresholds are adopted for drivers with different driving experience levels. Generally, experienced drivers have stronger risk prediction and emergency handling capabilities and can adopt a lower first threshold. A higher first threshold can be adopted for inexperienced drivers. In this way, the problem of overly conservative or risky lane change decisions caused by the use of fixed thresholds is effectively solved according to personalized decision parameters, thereby improving the adaptability of the vehicle's automatic lane change.

[0067] Exemplarily, the driving experience level can be determined in the following manner: obtaining the driver's historical driving data, which includes cumulative mileage, lane change success rate and emergency braking frequency; scoring the historical driving data using a preset scoring algorithm; and determining the driver's driving experience level based on the score and a preset level mapping relationship table, wherein the level mapping relationship table includes the correspondence between each driving experience level and different scores, and the level mapping relationship table can be formulated based on experimental data or expert experience.

[0068] For example, driving experience levels can be divided into three levels: beginner, intermediate, and advanced. Each level corresponds to a different first threshold. The first threshold for beginner drivers is 5 seconds, for intermediate drivers it is 4 seconds, and for advanced drivers it is 3 seconds.

[0069] In a possible embodiment, the first thresholds corresponding to different driving experience levels are set according to the TTC value range of the first level warning.

[0070] For example, the TTC value of the first-level warning is around 2.7 seconds to 4 seconds. The first threshold corresponding to the lowest driving experience level is 4 seconds, the first threshold corresponding to the highest driving experience level is 2.7 seconds, and the first threshold corresponding to other levels is any value between 2.7 seconds and 4 seconds.

[0071] In one embodiment, after monitoring the target vehicle entering the manual lane change state, it also includes: recording the longitudinal speed change information of the target vehicle during the lane change process, so as to control the target vehicle to perform the automatic lane change operation according to the longitudinal speed change information when deciding to perform the automatic lane change operation of the target vehicle.

[0072] The longitudinal speed change information is longitudinal speed change information after the target vehicle starts to move laterally during the lane change process. The longitudinal speed change information may be a speed change curve after the target vehicle starts to move laterally during the lane change process.

[0073] In this embodiment, by recording the longitudinal speed change information during the manual lane change process, actual driving behavior data reference is provided for subsequent automatic lane change operations. When the system decides that the target vehicle is allowed to perform automatic lane change operations based on the adjusted first threshold, the vehicle speed can be controlled based on the recorded longitudinal speed change information. This not only ensures safety during the lane change process, but also makes the speed change of the automatic lane change more in line with the driver's habitual operations.

[0074] Continuing with the example that the first threshold corresponding to the highest driving experience level is 2.7 seconds and the first threshold corresponding to the lowest driving experience level is 4 seconds: If the driver is at the highest driving experience level, then in the first few gesture lane changes, when the first collision time between the target vehicle and the obstacle vehicle is ≥2.7 seconds, the system controls the vehicle to change lanes normally. When the first collision time is <2.7 seconds, the system terminates the lane change operation. If the driver overrides the steering wheel to change lanes according to the actual road conditions, the second collision time between the target vehicle and the obstacle vehicle is recorded at this time, as well as the longitudinal speed change information of the target vehicle after the lateral movement. Under the premise that the second collision time is greater than or equal to the second threshold, the system will stop the lane change operation. , the first threshold of 2.7 seconds is compressed and adjusted according to the second collision time; if the driver is at the lowest driving experience level, then in the first few gesture lane changes, when the first collision time between the target vehicle and the obstacle vehicle is ≥4 seconds, the system controls the vehicle to change lanes normally. When the first collision time is less than 4 seconds, the system aborts the lane change operation. If the driver decides to override the steering wheel and perform an override lane change based on actual road conditions, the second collision time between the target vehicle and the obstacle vehicle is recorded at this time, as well as the longitudinal speed change information of the target vehicle after the lateral movement. Under the premise that the second collision time is greater than or equal to the second threshold, the first threshold of 4 seconds is compressed and adjusted according to the second collision time.

[0075] In one embodiment, after calculating the second collision time between the target vehicle and the obstacle vehicle, the method further includes: recording multiple second collision times and recording longitudinal speed change information of the target vehicle during lane change at each second collision time; constructing an automatic lane change decision model based on the multiple second collision times and the multiple longitudinal speed change information; and controlling the target vehicle to perform an automatic lane change operation based on the automatic lane change decision model.

[0076] Among them, the automatic lane change decision model is composed of multiple second collision times and multiple longitudinal speed change information. The target vehicle is controlled to perform automatic lane change operation according to the automatic lane change decision model. That is, when the driver requests the target vehicle to perform automatic lane change operation through lane change gesture, as long as the current collision time is one of the multiple second collision times, the target vehicle can be controlled to perform automatic lane change operation based on the corresponding longitudinal speed change information.

[0077] In this embodiment, by recording the collision time and speed change data when the driver manually changes lanes, an automatic lane change decision model based on actual driving behavior is constructed. This can effectively solve the decision-making difference problem between manual lane changes and system automatic lane changes, and improve the intelligence and adaptability of lane change decisions while ensuring safety.

[0078] In one possible embodiment, the automatic lane change decision model can be constructed using a machine learning method, taking multiple second collision times and multiple longitudinal speed change information as input features, and training a classification model through supervised learning to output a decision result on whether to execute automatic lane change.

[0079] In one embodiment, a method for generating a lane change instruction includes: if a lane change gesture of the driver is detected, identifying the current lane change scenario of the target vehicle, wherein the lane change gesture includes a right lane change gesture and a left lane change gesture, and the lane change scenario includes a right overtaking lane change scenario; if the lane change gesture is a left lane change gesture, generating a first lane change instruction to change to the left; if the lane change gesture is a right lane change gesture, generating a second lane change instruction to change to the right; if the lane change gesture is a right lane change gesture and the lane change scenario is a right overtaking lane change scenario, generating a third lane change instruction to change to the left.

[0080] Among them, the recognition of lane change scenarios can be achieved based on existing methods, which will not be described in detail here.

[0081] In this embodiment, taking into account the regulations prohibiting overtaking on the right, while maintaining the convenience of gesture control, scene recognition is used to avoid the potential safety hazards caused by directly executing the direction lane change represented by the driver's gesture in the right-hand overtaking scenario, thereby improving the rationality and safety of lane change decisions.

[0082] In one possible embodiment, the camera identifies the driver's lane change gestures in two ways to determine the driver's lane change intention: when the driver's eyes are facing the road ahead, he or she extends his or her hand in front of his or her chest with the palm facing forward, indicating that the driver intends to change lanes, and the system realizes that the driver may be about to send a lane change request; when the driver turns his or her head to look at a specific camera (such as the camera on the left front A-pillar) for a time period greater than or equal to a preset time threshold (such as 0.5 seconds), the system recognizes that the driver intends to communicate with the system and then identifies the driver's next physical instruction. If the driver looks at the camera and then poses with his or her palm facing forward, or poses while looking at the camera, the system also believes that the driver is preparing to send a lane change request.

[0083] As a possible embodiment, before the recognition step, it is first defined in the deep learning model that the driver's gesture of extending his hand with his palm facing forward and his eyes looking at the camera with his palm facing forward indicates that the driver is about to issue a lane change request. The system captures the driver's gesture image through a high-resolution camera and defines the driver's gesture swing. A left swing means the vehicle changes lanes to the left, and a right swing means the vehicle changes lanes to the right. Through repeated gesture experiments by the driver, the deep learning model in the MDC (Mobile Data Center) platform continuously learns, preprocesses the image, extracts features and executes decisions. The MDC sends the decision to the EPS (Electric Power Steering) for execution.

[0084] Exemplarily, the steps for the system to recognize gestures and make automatic lane change decisions when the driver is paying attention to the road ahead include: when the camera recognizes that the driver's eyes are facing the road ahead, it determines that the driver is concentrating on driving; when the driver raises his hand with his palm facing forward and lasts for more than 0.5 seconds, the camera captures the driver's gesture image, obtains real-time video stream, and sends the data to MDC so that MDC can pre-process the image, including adjusting image size, grid division, grayscale, denoising, etc.; the deep learning model in the MDC platform performs gesture recognition and feature extraction on the image, including detection of key points, such as gesture shape and trajectory. At this time, the camera can fully capture five fingers. Or palm; after comparing the extracted features with the predefined gesture template, the MDC platform recognizes that the driver is giving instructions to the vehicle at this moment; the driver then waves his hand to the left or right, and the MDC platform preprocesses the data and extracts features, identifies the trajectory and pointing area of ​​the driver's gesture, and determines the driver's lane change gesture; then calculates the first collision time between the vehicle and the obstacle vehicle, and determines the first threshold value based on the driver's driving experience level, and decides whether to perform automatic lane change operation based on the first collision time and the first threshold value; MDC passes the decision result to the execution layer, and implements lane change control of the vehicle through wire control braking and wire control steering.

[0085] Exemplarily, the steps for the system to recognize gestures and continue automatic lane change decisions when the driver is paying attention to the cockpit camera include: when the camera recognizes that the driver's eyes are facing the road ahead, the system assumes that the driver is concentrating on driving; when the driver's eyes are looking at the camera and his head is slightly turned at the same time, the camera captures images of the driver's eyes and head, the MDC preprocesses and extracts features of the facial and head changes in the image, and the system enters the next step of waiting for the driver to output a command; the driver then waves his hand to the left or right, and the MDC platform preprocesses and extracts features of the data, recognizes the trajectory and pointed area of ​​the driver's gesture, and determines the driver's lane change gesture; then the first collision time between the vehicle and the obstacle vehicle is calculated, and a first threshold is determined based on the driver's driving experience level, so as to decide whether to perform the automatic lane change operation based on the first collision time and the first threshold; the MDC passes the decision result to the execution layer, and implements lane change control of the vehicle through wire control braking and wire control steering.

[0086] See Figure 3 , Figure 3 FIG. 1 is a flow chart of another vehicle lane change control method shown in an exemplary embodiment of the present application. Figure 3 As shown, the detailed steps of another vehicle lane change control method are as follows:

[0087] 1. During driving, the camera constantly identifies the driver's eye gaze and head posture, defining the driver's gaze direction as three scenarios: the road ahead, a specific camera, and other directions. The automatic lane change function is activated based on the different gaze directions.

[0088] 2. When the driver keeps his eyes on the road ahead and extends his hand forward for at least 0.5 seconds while driving, the automatic lane change function is activated and waits for the driver's next instruction;

[0089] 3. When the driver extends his or her left or right hand, holds it forward for more than 0.5 seconds (the palm can be straight or bent), and gestures to the right, MDC recognizes this as a request to change lanes to the right.

[0090] 4. When the driver extends his or her left or right hand, holds it forward for more than 0.5 seconds (the palm can be straight or bent), and gestures to the left, MDC recognizes this as a request to change lanes to the left.

[0091] 5. When the driver looks at a specific camera for more than 0.5 seconds while driving, the automatic lane change function is activated and waits for the driver's next instruction;

[0092] 6. Similar to steps 3 and 4, the driver extends his or her left or right hand, holds it forward for at least 0.5 seconds (the palm can be straight or bent), and then gestures to the right or left. The MDC recognizes this as a request to change lanes to the right or left.

[0093] 7. The MDC sends a right turn command or a left turn command to the EPS, which enables the EPS to execute the vehicle's lane change to the right or left.

[0094] 8. If the driver's eyes are looking in a direction other than the road ahead and the camera, even if the driver makes a lane change gesture, it is considered that the driver is not requesting a lane change and the automatic lane change function will not be activated.

[0095] In addition, in the embodiment of the present application, the vehicle lane change control method is not only applicable to the solution of executing the vehicle automatic lane change operation based on the lane change gesture request, but also can be applied to the solution of executing the vehicle automatic lane change operation based on voice instructions, key input or other forms of human-computer interaction means.

[0096] The above-mentioned vehicle lane change control method calculates the first collision time between the target vehicle and the obstacle vehicle by responding to the lane change instruction. The lane change instruction is generated according to the lane change gesture of the driver in the target vehicle in the automatic driving mode, and is used to control the target vehicle to perform an automatic lane change operation. The obstacle vehicle includes a vehicle located in the target vehicle's pre-change lane and behind the target vehicle. If the first collision time is less than a preset first threshold, the automatic lane change operation is terminated. If the first collision time is less than the first threshold and the target vehicle is detected to enter a manual lane change state, the second collision time between the target vehicle and the obstacle vehicle is calculated, and the first threshold is adjusted according to the second collision time. The system makes adjustments to the target vehicle's subsequent automatic lane-changing operations based on the adjusted first threshold value, and dynamically adjusts the lane-changing decision parameters according to the actual safety situation when the driver manually changes lanes, so that the lane-changing decision changes according to the driver himself, that is, the lane-changing decision process of the system is optimized according to the driver's habits. The safety considerations in the system's lane-changing decision also constrain the driver's manual lane-changing operation, so that the system's decision is in line with the driver's driving habits to the greatest extent possible while ensuring driving safety, narrowing the decision-making gap between man and machine, and achieving the effect of man-machine-environment integration, thereby realizing more intelligent human-machine interaction and adaptive control of vehicle lane changes, and improving user experience.

[0097] Therefore, the entire lane-changing operation process is simple and easy to understand. The driver only needs to operate through lane-changing gestures, and the system can automatically optimize the lane-changing decision-making process based on the driver's lane-changing habits.

[0098] See Figure 4 , Figure 4 This is a block diagram of a vehicle lane change control system shown in an exemplary embodiment of the present application. The system can be applied to Figure 1 The implementation environment shown is shown. It should be understood that the system can also be applied to other exemplary implementation environments, and this embodiment does not limit the implementation environment to which the system is applicable.

[0099] like Figure 4 As shown, in an exemplary embodiment, the vehicle lane change control system 400 includes at least a calculation module 410, a lane change control module 420 and a monitoring module 430, which are described in detail as follows:

[0100] a calculation module 410 for calculating a first collision time between the target vehicle and an obstacle vehicle in response to a lane change instruction, wherein the lane change instruction is generated based on a lane change gesture of a driver in the target vehicle in the automatic driving mode and is used to control the target vehicle to perform an automatic lane change operation, and the obstacle vehicle includes a vehicle located in a lane to be changed by the target vehicle and behind the target vehicle;

[0101] a lane change control module 420 configured to terminate the automatic lane change operation if the first collision time is less than a preset first threshold;

[0102] The monitoring module 430 is configured to calculate a second collision time between the target vehicle and the obstacle vehicle if the first collision time is less than the first threshold and the target vehicle is detected to have entered a manual lane change state;

[0103] The lane change control module 420 is further configured to adjust the first threshold according to the second collision time, and make a decision on a subsequent automatic lane change operation of the target vehicle based on the adjusted first threshold.

[0104] It should be noted that the vehicle lane change control system provided in the above embodiment and the vehicle lane change control method provided in the above embodiment belong to the same concept, and the contents of the operations performed by each module have been described in detail in the method embodiment and will not be repeated here.

[0105] See Figure 5 , Figure 5 This is a structural diagram of a vehicle-mounted device provided in one embodiment of the present application. Figure 5 The following is a schematic diagram showing the structure of a computer system suitable for implementing the vehicle-mounted device of the embodiment of the present application. Figure 5 The computer system 500 of the vehicle-mounted device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0106] like Figure 5As shown, the computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 502 or the program loaded from the storage part 508 into the random access memory (RAM) 503, such as executing the method in the above embodiment. Various programs and data required for system operation are also stored in the RAM 503. The CPU 501, ROM 502 and RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0107] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, and the like; an output section 507 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and a speaker; a storage section 508 including a hard disk; and a communication section 509 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as needed. Removable media 511, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 510 as needed, so that computer programs read therefrom can be installed into the storage section 508 as needed.

[0108] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 509, and / or installed from a removable medium 511. When the computer program is executed by the central processing unit (CPU) 501, the various functions defined in the system of the present application are executed.

[0109] This application also provides a computer-readable storage medium having a computer program stored thereon. When executed by a computer processor, the computer program causes the computer to perform the vehicle lane change control method described above. The computer-readable storage medium may be included in the vehicle-mounted terminal described in the above embodiments, or may exist independently and not be deployed in the vehicle-mounted terminal.

[0110] It should be noted that the computer-readable medium shown in the embodiments of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable computer program. This propagated data signal can take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. A computer program embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0111] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Anyone skilled in the art may modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concepts disclosed in this application shall be covered by the claims of this application.

Claims

1. A vehicle lane change control method, characterized in that: The method comprises: Calculating a first collision time between a target vehicle and an obstacle vehicle in response to a lane change instruction, wherein the lane change instruction is generated based on a lane change gesture of a driver in the target vehicle in an automatic driving mode and is used to control the target vehicle to perform an automatic lane change operation, and the obstacle vehicle includes a vehicle located in a lane to be changed by the target vehicle and behind the target vehicle; If the first collision time is less than a preset first threshold, terminating the automatic lane change operation; If the first collision time is less than the first threshold and the target vehicle is detected to have entered a manual lane change state, calculating a second collision time between the target vehicle and the obstacle vehicle; The first threshold is adjusted according to the second collision time, and a decision is made on a subsequent automatic lane change operation of the target vehicle based on the adjusted first threshold.

2. The vehicle lane change control method according to claim 1, characterized in that: The adjusting the first threshold according to the second collision time includes: Setting a second threshold, where the second threshold is the minimum collision time allowed between the target vehicle and the obstacle vehicle when the target vehicle performs the automatic lane change operation, and the second threshold is smaller than the first threshold; Under the condition that the second collision time is greater than or equal to the second threshold, the first threshold is reduced according to the second collision time, so that the reduced first threshold is greater than or equal to the second collision time.

3. The vehicle lane change control method according to claim 2, characterized in that: The second threshold value is set as follows: Calculating a first critical collision time based on a preset rear vehicle braking deceleration threshold, the first critical collision time being the minimum allowed collision time between the target vehicle and the obstacle vehicle when the target vehicle performs an automatic lane change operation, provided that the braking deceleration of the obstacle vehicle is less than the rear vehicle braking deceleration threshold; The larger value between the first critical collision time and a preset second critical collision time is determined as the second threshold value, wherein the second critical collision time is set according to the collision time corresponding to the collision risk warning of the obstacle vehicle.

4. The vehicle lane change control method according to claim 1, characterized in that: After the target vehicle is detected to have entered a manual lane change state, the method further includes: The longitudinal speed change information of the target vehicle during the lane changing process is recorded, so as to control the target vehicle to perform the automatic lane changing operation according to the longitudinal speed change information when deciding to perform the automatic lane changing operation of the target vehicle.

5. The vehicle lane change control method according to claim 1, characterized in that: After calculating the second collision time between the target vehicle and the obstacle vehicle, the method further includes: recording a plurality of second collision times, and recording longitudinal speed change information of the target vehicle during lane change at each second collision time; constructing an automatic lane change decision model based on the plurality of second collision times and the plurality of longitudinal speed change information; The target vehicle is controlled to perform an automatic lane change operation according to the automatic lane change decision model.

6. The vehicle lane change control method according to claim 1, characterized in that: After calculating the first collision time between the target vehicle and the obstacle vehicle, the method further includes: Obtaining the driver's driving experience level; Determining a target threshold corresponding to the driver according to a mapping relationship table between the driving experience level and a preset threshold value, wherein the threshold mapping relationship table includes a correspondence between each driving experience level and a different first threshold value; The first collision time is compared with the target threshold value, and a decision is made on an automatic lane change operation of the target vehicle.

7. The vehicle lane change control method according to any one of claims 1 to 6, characterized in that: The method for generating the lane change instruction includes: If the lane change gesture of the driver is detected, identifying the current lane change scenario of the target vehicle, wherein the lane change gesture includes a right lane change gesture and a left lane change gesture, and the lane change scenario includes a right overtaking lane change scenario; If the lane change gesture is the left lane change gesture, generating a first lane change instruction to change lane to the left; If the lane change gesture is the right lane change gesture, generating a second lane change instruction to change lanes to the right; If the lane change gesture is the right lane change gesture and the lane change scenario is the right overtaking lane change scenario, a third lane change instruction to change to the left is generated.

8. A vehicle lane change control system, characterized in that: The system comprises: a calculation module, configured to calculate a first collision time between a target vehicle and an obstacle vehicle in response to a lane change instruction, wherein the lane change instruction is generated based on a lane change gesture of a driver in the target vehicle in an automatic driving mode and is configured to control the target vehicle to perform an automatic lane change operation, wherein the obstacle vehicle comprises a vehicle located in a lane to be changed by the target vehicle and behind the target vehicle; a lane change control module, configured to terminate the automatic lane change operation if the first collision time is less than a preset first threshold; a monitoring module, configured to calculate a second collision time between the target vehicle and the obstacle vehicle if the first collision time is less than the first threshold and the target vehicle is detected to have entered a manual lane change state; The lane change control module is further configured to adjust the first threshold according to the second collision time, and make a decision on a subsequent automatic lane change operation of the target vehicle based on the adjusted first threshold.

9. A vehicle-mounted device, characterized in that: include: processor; A storage device for storing a program, which, when executed by the processor, enables the vehicle-mounted device to implement the vehicle lane change control method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the computer program is executed by a processor of a computer, the computer is caused to execute the vehicle lane change control method according to any one of claims 1 to 7.

Images