Vehicle control method, vehicle and storage medium

Abstract

The invention relates to a vehicle control method, a vehicle and a storage medium, and the method comprises the steps: in response to determining that an auxiliary driving system of the vehicle is abnormal, controlling the auxiliary driving system to enter a cooperative takeover mode; and in response to determining that the auxiliary driving system enters the cooperative takeover mode, if the vehicle has the collision risk, actively controlling the vehicle to act by utilizing a target control system of the vehicle so as to avoid collision. Thus, when the vehicle auxiliary driving system is abnormal, the auxiliary driving system is controlled to enter the cooperative take-over mode instead of quitting immediately, in the cooperative take-over mode and under the condition that collision risks exist, even if a driver does not take over the vehicle in time, the target control system can be used for actively intervening the vehicle, then the accident occurrence probability is reduced, and the driving safety is improved. And the life safety of drivers and passengers is ensured.

Description

Technical Field

[0001] This disclosure relates to the field of vehicles, and more specifically, to a vehicle control method, a vehicle, and a storage medium. Background Technology

[0002] With the increasing intelligence of vehicles, Advanced Driver Assistance Systems (ADAS) are becoming more and more common. However, in practical applications, unintentional intervention by the driver or uncertain changes in the external environment can trigger unexpected disengagement or performance degradation of ADAS. If the driver fails to respond in time, it may lead to safety risks.

[0003] Currently, most ADAS systems issue warnings to drivers when they malfunction, but fail to provide effective intervention in emergency situations and cannot effectively prevent potential collisions. Summary of the Invention

[0004] The purpose of this disclosure is to provide a vehicle control method, a vehicle, and a storage medium to avoid collisions and improve vehicle safety.

[0005] To achieve the above objectives, a first aspect of this disclosure provides a vehicle control method, comprising: In response to determining that the vehicle's driver assistance system is malfunctioning, the driver assistance system is controlled to enter a cooperative takeover mode; In response to determining that the driver assistance system has entered cooperative takeover mode, if there is a risk of collision with the vehicle, the vehicle's target control system is used to actively control the vehicle's actions to avoid a collision.

[0006] Optionally, if the vehicle is at risk of collision, the vehicle's target control system is used to actively control the vehicle's actions, including: When the vehicle is at risk of collision, if the driver fails to perform driving maneuvers that would effectively avoid a collision, the target control system will be used to control the vehicle's actions.

[0007] Optionally, when the vehicle is at risk of collision, if the driver fails to perform a driving operation that can effectively avoid the collision, the target control system is used to control the vehicle's actions, including: If the driver fails to perform a driving operation that can effectively avoid a collision when the remaining collision reference time is less than a first remaining time threshold, the target control system will be used to control the vehicle's movement.

[0008] Optionally, if the driver fails to perform a driving operation that effectively avoids a collision, the target control system controls the vehicle's actions, including at least one of the following: If the driver does not take over the vehicle, the target control system provides all the corrective torque to achieve lateral collision avoidance. If the collision avoidance direction indicated by the driving operation is consistent with the theoretical collision avoidance direction, but the steering angle indicated by the driving operation is less than the theoretical collision avoidance steering angle, and the collision reference remaining time is less than the second remaining time threshold, then the auxiliary correction torque provided by the target control system, together with the steering torque provided by the driver, is used to achieve lateral collision avoidance, wherein the second remaining time threshold is less than the first remaining time threshold. If the collision avoidance direction indicated by the driving operation is inconsistent with the theoretical collision avoidance direction, a prompt message is generated to remind the user that the driving operation is incorrect, and the target control system is used to achieve lateral collision avoidance when the steering wheel torque is reduced.

[0009] Optionally, the method further includes: In response to determining that the vehicle has deviated from its course, the remaining collision reference time is determined based on the vehicle status information and the position of the activated reference line, wherein the activated reference line is located on the side of the obstacle facing the vehicle and is at a preset distance from the obstacle.

[0010] Optionally, the preset distance is determined based on the vehicle width and / or the road width; the wider the vehicle width, the greater the preset distance; the wider the road width, the greater the preset distance.

[0011] Optionally, the method of controlling vehicle movement using a target control system includes: Based on the target correction angle, determine the correction torque to be provided by the target control system; Based on the corrective torque, the target control system controls the vehicle to achieve lateral collision avoidance.

[0012] Optionally, the method further includes: In response to determining that the vehicle turns to the target correction angle, if there is a risk of collision if the vehicle travels along the current trajectory, the vehicle is controlled not to exceed the maximum allowable deviation boundary, and the lateral speed of the vehicle is reduced to a vehicle speed threshold, wherein the maximum allowable deviation boundary is closer to the obstacle than the active reference line.

[0013] Optionally, the method further includes: In response to determining that the lateral speed of the vehicle has decreased to the vehicle speed threshold, and based on the rear collision risk of the vehicle, the vehicle is controlled to perform regression control to guide the vehicle to move back towards the original lane direction.

[0014] Optionally, controlling the vehicle to perform regression control based on the rear collision risk includes at least one of the following: If it is determined that there is a collision risk behind the vehicle, the vehicle is controlled to move to the first return position; If it is determined that there is no risk of collision behind the vehicle and the driver has taken control of the vehicle, then the vehicle is moved to the second return position. If it is determined that there is no risk of collision behind the vehicle and the driver has not taken over the vehicle, then the vehicle is controlled to move to the third return position; Wherein, the lateral offset between the first regression position and the current position of the vehicle is less than the lateral offset between the second regression position and the current position of the vehicle; the lateral offset between the second regression position and the current position of the vehicle is less than the lateral offset between the third regression position and the current position of the vehicle.

[0015] Optionally, the method further includes: The driver is determined to take over the vehicle if any of the following conditions are met: The steering wheel hand torque is greater than the first torque threshold and the steering wheel direction is consistent with the steering lever; The brake pedal is pressed and the pressing time is longer than the first preset duration; The accelerator pedal is pressed deeper than the depth threshold and the steering wheel torque is greater than the second torque threshold.

[0016] Optionally, the method further includes: The vehicle's driver assistance system is deemed malfunctioning if any of the following conditions are met: The lane width is less than the width threshold; The lane curvature is greater than the curvature threshold; The lane markings ahead are missing; The brake pedal was pressed; The driver remained hands-free and did not take control of the vehicle. The steering wheel hand torque is greater than the third torque threshold.

[0017] Optionally, the target control system is an electric power steering system.

[0018] A second aspect of this disclosure provides a vehicle control device, comprising: The first control module is used to control the driver assistance system to enter a cooperative takeover mode in response to determining that the vehicle's driver assistance system is abnormal. The second control module is used to respond to the determination that the driver assistance system has entered the cooperative takeover mode. If there is a risk of collision with the vehicle, the module actively controls the vehicle's actions using the vehicle's target control system to avoid a collision.

[0019] A third aspect of this disclosure provides a vehicle, comprising: processor; Memory used to store processor-executable instructions; The processor is configured to execute the executable instructions in the memory to implement the steps of the vehicle control method provided in the first aspect of this disclosure.

[0020] The fourth aspect of this disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the vehicle control method provided in the first aspect of this disclosure.

[0021] The fifth aspect of this disclosure provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the vehicle control method provided in the first aspect of this disclosure.

[0022] In the above technical solution, when the vehicle's driver assistance system malfunctions, the driver assistance system is controlled to enter a cooperative takeover mode instead of immediately exiting. In the cooperative takeover mode, even if the driver fails to take over the vehicle in time when there is a risk of collision, the target control system can actively intervene in the vehicle, thereby reducing the probability of an accident and ensuring the safety of the occupants.

[0023] Other features and advantages of this disclosure will be described in detail in the following detailed description section. Attached Figure Description

[0024] The accompanying drawings are provided to further illustrate the present disclosure and form part of the specification. They are used together with the following detailed description to explain the present disclosure, but do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart of a vehicle control method provided in an exemplary embodiment of this disclosure.

[0025] Figure 2 This is a schematic diagram of a straight road scenario provided by an exemplary embodiment of this disclosure.

[0026] Figure 3 This is a schematic diagram of a curve scenario provided by an exemplary embodiment of this disclosure.

[0027] Figure 4 This is a flowchart of a vehicle control method provided in an exemplary embodiment of this disclosure.

[0028] Figure 5 This is a flowchart of a vehicle control method provided in an exemplary embodiment of this disclosure.

[0029] Figure 6 This is a schematic diagram of vehicle return control provided in an exemplary embodiment of this disclosure.

[0030] Figure 7 This is a block diagram of a vehicle control device provided in an exemplary embodiment of the present disclosure. Detailed Implementation

[0031] The specific embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit this disclosure.

[0032] Figure 1 This is a flowchart of a vehicle control method provided in an exemplary embodiment of this disclosure. Figure 1 As shown, the method may include steps S101 and S102.

[0033] In step S101, in response to determining that the vehicle's driver assistance system is malfunctioning, the driver assistance system is controlled to enter a cooperative takeover mode.

[0034] In one embodiment, when it is determined that the conditions for the Advanced Driver Assistance System (ADAS) to perform an unexpected exit or degrade operation are met, an ADAS anomaly can be identified, and the ADAS can be controlled to enter a cooperative takeover mode. In cooperative takeover mode, the ADAS does not immediately exit; before the driver takes full control, the ADAS continues to perceive the environment, predict risks, and assess the effectiveness of the driver's actions in real time. This allows for a smoother and safer return of control to the driver.

[0035] Unexpected exit refers to the sudden and complete shutdown of ADAS, handing vehicle control back to the driver. Unexpected exit of ADAS may be triggered by unintentional intervention by the driver or uncertain changes in the external environment. Degradation refers to ADAS not being completely turned off, but one or more functions (such as lane centering and adaptive cruise control) becoming ineffective or weakened due to performance limitations.

[0036] In step S102, in response to determining that the driver assistance system has entered the cooperative takeover mode, if there is a risk of collision with the vehicle, the vehicle's target control system is used to actively control the vehicle's actions to avoid a collision.

[0037] In one embodiment, surrounding obstacles can be identified using sensors such as cameras, millimeter-wave radar, and lidar to acquire environmental perception data such as obstacle positions, distances between vehicles and obstacles, and relative speeds, in order to calculate the remaining collision time. If the remaining collision time is lower than a preset threshold, a collision risk can be determined. Obstacles may include guardrails, bollards, water-filled barriers, lane markings, curbs, etc. The accuracy of environmental perception can be ensured through cross-verification of information from multiple sensors.

[0038] In one embodiment, the target control system can be an actuator with lateral control capabilities. For example, the target control system may include a brake-by-wire system and / or an electric power steering system. By actively intervening in lateral control using the target control system (such as implementing obstacle avoidance steering or stability braking), collisions can be avoided.

[0039] In the above technical solution, when the vehicle's driver assistance system malfunctions, the driver assistance system is controlled to enter a cooperative takeover mode instead of immediately exiting. In the cooperative takeover mode, even if the driver fails to take over the vehicle in time when there is a risk of collision, the target control system can actively intervene in the vehicle, thereby reducing the probability of an accident and ensuring the safety of the occupants.

[0040] In one possible implementation, in step S101, if there is a risk of collision with the vehicle, the vehicle's target control system is used to actively control the vehicle's actions, including: When there is a risk of collision, if the driver fails to take driving actions that can effectively avoid the collision, the target control system will be used to control the vehicle's actions.

[0041] In one embodiment, signals such as steering wheel angle and speed, hand torque, steering lever direction, brake / accelerator pedal opening and its rate of change can be monitored in real time, and these signals can be filtered to accurately determine whether the driver is performing a driving operation that can effectively avoid a collision.

[0042] If the driver fails to take over the vehicle, or if the driver's actions after taking over are insufficient to avoid a collision (i.e., improper operation), it can be determined that the driver did not perform driving operations that would have effectively avoided a collision.

[0043] In one embodiment, trajectory prediction can be performed based on vehicle status, and a "safe collision avoidance trajectory" can be calculated in real time as a reference benchmark. The trajectory corresponding to the driving operation is compared with the safe trajectory to quickly quantify whether the operation can effectively avoid a collision.

[0044] The above technical solution can proactively avoid collision risks when the driver fails to respond to them in a timely or effective manner, reducing the probability of accidents caused by human delays or improper operation, and ensuring driving safety.

[0045] In one possible implementation, if the driver does not perform a driving operation that can effectively avoid a collision when the collision reference remaining time is less than a first remaining time threshold, the target control system can be used to control the vehicle's actions.

[0046] For example, the existence of a collision risk can be determined by comparing the collision reference remaining time with a first remaining time threshold. The first remaining time threshold can be preset based on actual needs, for example, it can be set to 0.5s. The collision reference remaining time between the vehicle and the obstacle can be calculated. If the collision reference remaining time is less than the first remaining time threshold, it can be determined that a hazard is approaching. At this time, if it is determined that the driver has not performed a driving operation that could effectively avoid a collision (including no operation and improper operation), the target control system can be immediately triggered to perform active avoidance intervention.

[0047] In the above technical solution, by introducing a dual decision-making mechanism of the first remaining time threshold and the judgment of the driver's operation effectiveness, it can be ensured that the target control system intervenes at critical moments when danger is imminent and human response is insufficient. This avoids unnecessary interference to the driver due to premature intervention and ensures reliable safety redundancy at the last moment.

[0048] In one possible implementation, the remaining collision reference time can be determined in the following way: In response to determining that the vehicle has deviated from its course, the remaining collision reference time is determined based on the vehicle status information and the position of the activated reference line.

[0049] The activation reference line is located on the side of the obstacle facing the vehicle and is at a preset distance from the obstacle.

[0050] For example, related technologies can be used to detect vehicle deviation. If the vehicle deviates from its lane or predetermined path, the remaining collision reference time can be calculated based on the vehicle's real-time status (such as speed and yaw rate) and a preset "activation reference line". This activation reference line is set on the side of the obstacle closest to the vehicle and maintains a fixed safe distance from the obstacle to provide early warning of potential side collision risks.

[0051] exist Figure 2 In a straight road scenario, the left side of the lane features continuous traffic cones, while the right side is a normal lane marking. In cooperative takeover mode, if ADAS detects that the outer left edge of the vehicle will cross the active reference line (Lactive) in 0.3 seconds, it can actively control the vehicle's movement using the electric power steering system to steer the vehicle to the right to prevent a collision with the left-side traffic cones. Here, Dactive represents a preset distance.

[0052] exist Figure 3 In a curve scenario, with a highway guardrail on the right and the left lane lines suddenly disappearing, the ADAS, in cooperative takeover mode, can actively control the vehicle's movement using the electric power steering system if it detects that the outer edge of the vehicle's right side crosses the active reference line (Lactive) after 0.3 seconds. This corrects the vehicle's deviation to the left to prevent a collision with the right-side guardrail. Here, Dactive represents a preset distance.

[0053] In this way, by setting a virtual boundary (activation reference line) relative to the obstacle, the triggering time of the vehicle's active collision avoidance action can be advanced, thereby improving the response margin of the target control system. This effectively addresses the risk of side scrapes / collisions caused by the vehicle deviating from its lane, enhancing predictive protection capabilities in complex scenarios.

[0054] In one possible implementation, the preset distance is determined based on the vehicle width and / or the road width. Specifically, the wider the vehicle and the wider the road, the greater the preset distance.

[0055] In other words, the preset distance is a dynamic value that can be determined based on a combination of the vehicle's width and the current road width. For example, the preset distance can be determined using a preset correspondence. This correspondence can be between the vehicle's width, the road width, and the preset distance; it can also be between the vehicle's width and the preset distance, or between the road width and the preset distance—there are no restrictions here.

[0056] By dynamically adjusting the preset distance using the vehicle's width, a safety margin matching the vehicle's dimensions can be obtained, avoiding insufficient protection for wide-body vehicles due to fixed distance settings. This also accommodates the passability needs of different vehicle types, ensuring driving safety. Similarly, dynamically adjusting the preset distance using the road width can adapt to varying road conditions, ensuring driving safety while avoiding unnecessary interventions due to overly conservative triggering on wide roads.

[0057] Figure 4 This is a flowchart of a vehicle control method provided in an exemplary embodiment of this disclosure. Figure 4 As shown, the method may include steps S401 to S408.

[0058] In step S401, in response to determining that the driver assistance system has entered cooperative takeover mode, it is determined whether there is a collision risk to the vehicle. If not, step S402 is executed; if so, step S403 is executed.

[0059] For example, a vehicle may be determined to be at risk of collision if the remaining time for a collision reference is less than a first remaining time threshold.

[0060] In step S402, it is further determined whether there is a risk of collision with the vehicle.

[0061] In step S403, it is determined whether the driver has taken over the vehicle. If not, proceed to step S404; if yes, proceed to step S405.

[0062] For example, by monitoring steering wheel torque, brake / accelerator pedal signals, etc. in real time, it can be determined whether the driver has taken over the vehicle. If it is determined that the driver has not taken over, it can be determined that the driver has no intention of actively controlling the vehicle, and step S404 can be executed, in which the target control system fully intervenes in the vehicle to ensure driving safety. If it is determined that the driver has taken over, it can be determined that the driver has an intention of actively controlling the vehicle, and step S405 can be executed to further evaluate the effectiveness of the driver's driving operation.

[0063] In step S404, the target control system provides all the corrective torque to achieve lateral collision avoidance.

[0064] For example, ADAS can determine the theoretical collision avoidance steering angle based on environmental perception information and send an intervention request to the target control system, which can be generated based on the theoretical collision avoidance steering angle. Upon receiving the intervention request, the target control system uses it to generate specific corrective torque commands and drives the corresponding actuators (such as the steering motor) to achieve lateral collision avoidance assistance for the vehicle. In this way, it can provide safety for the vehicle in emergency situations, preventing accidents caused by complete driver absence.

[0065] In step S405, it is determined whether the collision avoidance direction indicated by the driving operation is consistent with the theoretical collision avoidance direction. If not, proceed to step S406; if yes, proceed to step S408.

[0066] In one embodiment, the driving operations performed by the driver can be analyzed to obtain the collision avoidance direction and steering angle indicated by the driving operations (i.e., the collision avoidance direction and steering angle intended by the driver). The theoretical collision avoidance direction can also be determined automatically by the vehicle's system based on environmental perception information.

[0067] The effectiveness of driving operations can be assessed first from the perspective of direction, avoiding conflicts between the target control system assistance and the driver's intentions, and ensuring cooperative safety. If the collision avoidance direction indicated by the driving operation is inconsistent with the theoretical collision avoidance direction, step S406 can be executed to prompt the user. If the collision avoidance direction indicated by the driving operation is consistent with the theoretical collision avoidance direction, step S408 can be executed to further assess the driving situation and ensure the accuracy of control.

[0068] In step S406, a prompt message is generated to alert the user that there is an error in the driving operation.

[0069] For example, a prompt message such as "Driving operation error" can be displayed on the in-vehicle screen, broadcast through the speaker, or the driver can be alerted to the driving operation error by controlling the steering wheel vibration. This allows the driver to be promptly reminded to correct the error, giving them priority in addressing the problem.

[0070] In step S407, when the steering wheel torque decreases, the target control system is used to achieve lateral collision avoidance.

[0071] After indicating an error in driving operation, if a decrease in steering wheel torque is detected, it can be determined that the driver has given up resistance or accepted intervention. At this point, the target control system takes over the vehicle and provides steering assistance. The generation of prompts enables a smooth and safe transition of human-machine control. By recognizing the driver's willingness to comply before intervention, the risk of vehicle instability caused by a conflict between the target control system and the driver's intentions can be effectively avoided, ensuring driving safety.

[0072] For example, steps S404 to S409 can be used to implement the process of using the target control system to achieve lateral collision avoidance in step S407.

[0073] In step S408, it is determined whether the steering angle indicated by the driving operation is less than the theoretical collision avoidance steering angle, and whether the collision reference remaining time is less than the second remaining time threshold. If not, step S402 is repeated; if yes, step S409 is executed.

[0074] The second remaining time threshold is less than the first remaining time threshold. The second remaining time threshold can be preset based on actual needs, for example, it can be set to 0.2 seconds. If the collision reference remaining time is less than the second remaining time threshold, it can be determined that the danger is extremely imminent, and the intervention of the target control system is imperative. If the steering angle indicated by the driving operation is less than the theoretical collision avoidance steering angle, it can be determined that the driver's driving operation cannot independently avoid the collision. By judging the remaining collision reference time and the steering angle indicated by the driving operation, the necessity and urgency of the target control system to intervene can be clearly defined, providing an accurate decision basis for the execution of coordinated control.

[0075] In step S409, the target control system provides an auxiliary corrective torque, which, together with the steering torque provided by the driver, achieves lateral collision avoidance.

[0076] For example, driver input can be analyzed to determine the steering torque and steering angle indicated by the input, and to identify the difference between these values ​​and the theoretical / target values. The target control system can then generate and apply an auxiliary corrective torque to compensate for this difference. This auxiliary corrective torque can be superimposed on the driver-provided steering torque vector to jointly drive the steering mechanism, thereby achieving collision avoidance.

[0077] In this way, the target control system can provide precise understanding assistance at the last moment, rather than taking over completely, to achieve human-machine collaboration. This not only makes up for the driver's possible lack of strength or reaction in extreme emergency situations and ensures the bottom line of safety, but also respects and preserves the driver's sense of leadership and control.

[0078] Figure 4Steps S405 to S408 are used to determine whether the driver's actions can avoid a collision. Figure 4 The provided technical solution constructs multi-level safety redundancy. When ADAS malfunctions, it can make decisions based on collision risk and driver operation status, and implement graded lateral intervention. While ensuring vehicle safety, it respects the driver's intention to the greatest extent, so as to achieve an effective balance between safety and driving experience.

[0079] Figure 5 This is a flowchart of a vehicle control method provided in an exemplary embodiment of this disclosure. Figure 5 As shown, the method may include steps S501 to S508.

[0080] In step S501, the correction torque to be provided by the target control system is determined based on the target correction angle.

[0081] In step S502, based on the correction torque, the target control system is used to control the vehicle to achieve lateral collision avoidance.

[0082] For example, the target correction angle can be determined by ADAS based on relevant algorithms. This target correction angle can be consistent with the theoretical collision avoidance steering angle mentioned earlier, or it can be an angle obtained by optimizing the theoretical collision avoidance steering angle. The target control system can convert the target correction angle requirement into a specific correction torque command based on a preset vehicle dynamics model. This torque command is then sent to the corresponding actuator to drive the tires to generate a corresponding lateral force, thereby enabling the vehicle to achieve lateral collision avoidance.

[0083] In step S503, in response to determining that the vehicle has turned to the target correction angle, it is determined whether there is a risk of collision if the vehicle continues to travel along the current trajectory. If not, step S504 is executed; if yes, step S505 is executed.

[0084] For example, the first stage of correction can be achieved based on steps S501 and S502. If the vehicle turns to the target correction angle, the first stage of correction can be considered complete. At this point, to ensure vehicle safety, it can be determined whether a second stage of correction is needed by assessing whether there is a collision risk if the vehicle continues along its current trajectory. For example, related technologies can be used to plan the driving trajectory, which will not be elaborated here. The collision risk is determined by predicting the interaction between the vehicle's trajectory and obstacles.

[0085] In this way, by continuously assessing collision risks, a basis for decision-making can be provided for initiating secondary intervention (i.e., the second stage of correction) when necessary, thereby ensuring driving safety.

[0086] In step S504, it is determined that the collision avoidance has ended.

[0087] In step S505, the vehicle is controlled to not exceed the maximum allowable deviation boundary, and the lateral speed of the vehicle is reduced to the vehicle speed threshold.

[0088] The maximum permissible deviation boundary is closer to the obstacle than the active reference line. The active reference line can be understood as a "warning line" used to trigger warnings and the first stage of correction; its relatively forward position allows the target control system sufficient decision-making and response time. The maximum permissible deviation boundary, on the other hand, can be understood as the final physical tolerance; being closer to the obstacle, it provides a final guarantee to prevent the vehicle from deviating excessively into adjacent lanes or dangerous areas, thus avoiding a collision or reducing its severity. This maximum boundary can also be determined based on the vehicle width and road width.

[0089] For example, the vehicle speed threshold can be preset based on actual needs; for instance, it can be set to 0. Reducing the vehicle's lateral speed to the speed threshold reduces the vehicle's lateral kinetic energy toward the obstacle. Controlling the vehicle to prevent it from exceeding the maximum permissible deviation boundary ensures vehicle safety by establishing a final physical safety baseline. Based on step S505, a second stage of correction can be implemented, achieving final safety protection.

[0090] In step S506, in response to determining that the vehicle's lateral speed has decreased to a vehicle speed threshold, the vehicle is controlled to perform regression control based on the risk of rear-end collision, so as to guide the vehicle to move back to the original lane direction.

[0091] For example, if a vehicle's lateral speed decreases to a speed threshold, it can be determined that the vehicle is in a relatively safe state. After performing the second stage of correction, i.e., when the vehicle's lateral movement is significant, the system can automatically guide the vehicle back to its original position, taking into account the risk of rear-end collisions, to prevent secondary accidents and restore normal traffic flow as quickly as possible, while ensuring the vehicle's own safety.

[0092] In one possible implementation, in step S506, based on the risk of a rear-end collision, the vehicle is controlled to perform regression control, including at least one of the following: If a collision risk is determined to be behind the vehicle, the vehicle is controlled to move to the first return position; If it is determined that there is no risk of collision behind the vehicle and the driver has taken control of the vehicle, then control the vehicle to move to the second return position. If it is determined that there is no risk of collision behind the vehicle and the driver has not taken over the vehicle, then control the vehicle to move to the third return position; Among them, the lateral offset between the first regression position and the vehicle's current position is less than the lateral offset between the second regression position and the vehicle's current position; the lateral offset between the second regression position and the vehicle's current position is less than the lateral offset between the third regression position and the vehicle's current position.

[0093] like Figure 6 As shown, the first regression position L1end has the smallest lateral offset from the current vehicle position, the third regression position L3end has the largest lateral offset from the current vehicle position, and the second regression position L2end has a relatively moderate lateral offset from the current vehicle position, falling between the two.

[0094] When there is a risk of collision from behind, choose the trajectory with the least lateral offset. Minimal lateral offset means the shortest lateral movement distance and the slowest speed. This allows for quick vehicle stabilization, minimizing uncertainty within the lane and providing more reaction time for vehicles behind.

[0095] When there is no risk behind and the driver has taken over, a trajectory with moderate lateral deviation is selected. In this way, by maintaining a certain degree of automatic control, the vehicle is kept within a relatively safe driving range, thus providing a safety net; at the same time, sufficient space is left for the driver to exercise driving control, achieving a balance between safety assurance and respect for the driver's autonomy.

[0096] When there is no risk behind and the driver is not in control, choosing the trajectory with the largest lateral deviation can move the vehicle to a greater extent away from the currently potentially dangerous driving lane, allowing it to enter a safer area and isolate the risk.

[0097] In one possible implementation, after performing step S506, it can be detected whether the vehicle body is parallel to obstacles such as curbs, so as to prevent the vehicle from deviating to the other side after correction.

[0098] In one possible implementation, the vehicle control method provided in this disclosure may further include: The driver is deemed to have taken over the vehicle if any of the following conditions are met: The steering wheel hand torque is greater than the first torque threshold and the steering wheel direction is consistent with the steering lever; The brake pedal is pressed and the pressing time is longer than the first preset duration; The accelerator pedal is pressed deeper than the depth threshold and the steering wheel torque is greater than the second torque threshold.

[0099] For example, both the first and second torque thresholds can be preset based on actual needs, such as 2 Nm. The first preset duration can also be preset based on actual needs, such as 2 seconds. For example, if the steering wheel torque is continuously greater than 2 Nm and the turning direction is consistent with the steering lever direction, or the brake pedal is continuously depressed for more than 2 seconds, or the accelerator pedal depth exceeds the depth threshold while accompanied by effective steering wheel torque input, it can be determined that the driver intends to take over the vehicle. In this way, by setting multi-dimensional judgment conditions, the accuracy and robustness of driver takeover intention recognition can be improved, avoiding misjudgments caused by accidental fluctuations of a single signal (such as unintentional touch of the steering wheel).

[0100] In one possible implementation, the vehicle control method provided in this disclosure may further include: The vehicle's driver assistance system is deemed malfunctioning if any of the following conditions are met: The lane width is less than the width threshold; The lane curvature is greater than the curvature threshold; The lane markings ahead are missing; The brake pedal was pressed; The driver continued to ditch the vehicle and did not take control. The steering wheel hand torque is greater than the third torque threshold.

[0101] For example, the width threshold can be preset based on actual needs (such as based on ADAS safety control boundary settings). If the lane width is less than the width threshold, it indicates that the lane is too narrow. Lanes that are too narrow usually exceed the ADAS safety control boundary, and continuing to maintain assisted driving poses a collision risk. Therefore, an ADAS malfunction can be identified, and vehicle safety can be ensured by actively downgrading or disengaging.

[0102] For example, the curvature threshold can be preset based on actual needs (such as setting based on the performance limits of ADAS). A lane curvature greater than the curvature threshold indicates that the vehicle is on a sharp curve, which requires high lateral control precision and exceeds the performance limits of ADAS. Therefore, an ADAS malfunction can be identified, and vehicle safety can be ensured by actively downgrading or disengaging the system.

[0103] For example, the presence or absence of a brake pedal can be determined based on the brake pedal opening. A depressed brake pedal indicates the driver's intention to take over the vehicle. A third torque threshold can be preset based on actual needs, for example, it could be set to 2 Nm. Similarly, if the steering wheel torque exceeds the third torque threshold, the driver's intention to take over the vehicle can also be determined. When the driver's intention to take over is determined, an ADAS malfunction can be identified. By controlling the ADAS to actively degrade or disengage, control can be returned to the driver, avoiding potential conflicts caused by simultaneous operation of the braking system by the driver and the ADAS, thus improving vehicle safety.

[0104] In addition, vehicles rely on lane lines for positioning and guidance. The lack of this crucial perception information, the lane lines ahead, prevents ADAS from navigating safely. Therefore, an ADAS malfunction can be identified, and vehicle safety can be ensured by actively downgrading or disengaging the system.

[0105] If a driver continuously takes hands off the vehicle without taking control, it can be determined that the driver may have a long-term lack of concentration, indicating an ADAS malfunction. By actively downgrading or disabling the ADAS, the driver can be forced to take control again to prevent accidents caused by over-reliance on ADAS.

[0106] In this way, by setting multi-dimensional and controllable ADAS anomaly judgment conditions, driving safety and user experience can be effectively improved.

[0107] The following is combined with Figure 2 , 3 A more specific example of the vehicle control process is given.

[0108] exist Figure 2 In a straight-line scenario, the left side of the lane features continuous cones, while the right side is a normal lane marking. When the NOA (Navigation Assist) function is activated and the vehicle is driving normally, the lateral function disengages due to the narrow lane. The driver continues to fail to take over steering, and the vehicle deviates to the left. The ADAS determines that an unexpected disengagement has occurred. Furthermore, the ADAS detects that the outer left edge of the vehicle will cross the active reference line (Lactive) in 0.3 seconds. At this point, by executing the first and second stages of correction described earlier, the vehicle can be corrected to the right to prevent a collision with the left-side cones.

[0109] exist Figure 3 In a curve scenario, the left lane line suddenly disappears from the right side of the highway guardrail. At this point, the ICC (Intelligent Cruise Control) function downgrades to ACC (Adaptive Cruise Control). The vehicle's lateral control becomes insufficient, causing it to veer outwards, posing a risk of collision with the highway guardrail. The ADAS (Advanced Driver Assistance System) determines that the function has unexpectedly disengaged. Simultaneously, it detects that the driver has continued to take over without tackling the vehicle, and that the outer right edge of the vehicle crosses the active reference line (Lactive) after 0.3 seconds. At this point, by executing the first and second stages of correction described earlier, the vehicle can be corrected to the left to prevent a collision with the right-side guardrail.

[0110] The technical solution provided in this disclosure enhances the safety redundancy of the advanced driver assistance system (ADAS) in case of unexpected exit or degradation. When the conditions for unexpected exit or degradation by the ADAS are met, the ADAS is controlled to enter a cooperative takeover mode. The ADAS in cooperative takeover mode ensures vehicle safety. When the vehicle deviates from its lane and is about to approach obstacles such as curbs, water barriers, or guardrails, the target control system promptly corrects the deviation. This compensates for the driver's takeover delay, reduces collision risk through real-time correction, and achieves full-scenario failure safety protection, thereby constructing a multi-dimensional driving safety assurance system.

[0111] Based on the same concept, embodiments of this disclosure also provide a vehicle control device. Figure 7 This is a block diagram of a vehicle control device 700 provided in an exemplary embodiment of this disclosure. Figure 7 As shown, the vehicle control device 700 may include: The first control module 701 is used to control the driver assistance system to enter a cooperative takeover mode in response to determining that the vehicle's driver assistance system is abnormal. The second control module 702 is used to respond to the determination that the driver assistance system has entered the cooperative takeover mode. If there is a risk of collision with the vehicle, the module actively controls the vehicle's actions using the vehicle's target control system to avoid a collision.

[0112] In the above technical solution, when the vehicle's driver assistance system malfunctions, the driver assistance system is controlled to enter a cooperative takeover mode instead of immediately exiting. In the cooperative takeover mode, even if the driver fails to take over the vehicle in time when there is a risk of collision, the target control system can actively intervene in the vehicle, thereby reducing the probability of an accident and ensuring the safety of the occupants.

[0113] Optionally, the second control module 702 is used to control the vehicle's actions using the target control system if the driver fails to perform driving operations that can effectively avoid a collision when there is a risk of collision with the vehicle.

[0114] Optionally, the second control module 702 is used to control the vehicle's movement using the target control system if the driver does not perform a driving operation that can effectively avoid a collision when the collision reference remaining time is less than a first remaining time threshold.

[0115] Optionally, the second control module 702 includes: The first control submodule is used to provide all the corrective torque using the target control system to achieve lateral collision avoidance if the driver does not take over the vehicle. The second control submodule is used to achieve lateral collision avoidance by using the auxiliary correction torque provided by the target control system, together with the steering torque provided by the driver, if the collision avoidance direction indicated by the driving operation is consistent with the theoretical collision avoidance direction but the steering angle indicated by the driving operation is less than the theoretical collision avoidance steering angle, and the collision reference remaining time is less than the second remaining time threshold. The third control submodule is used to generate a prompt message to indicate that the driving operation is incorrect if the collision avoidance direction indicated by the driving operation is inconsistent with the theoretical collision avoidance direction, and to achieve lateral collision avoidance using the target control system when the steering wheel torque is reduced.

[0116] Optionally, the device 700 also includes: The first determining module is used to determine the remaining collision reference time in response to determining that the vehicle has deviated from its course, based on the vehicle status information and the position of the activated reference line, wherein the activated reference line is located on the side of the obstacle facing the vehicle and is at a preset distance from the obstacle.

[0117] Optionally, the preset distance is determined based on the vehicle width and / or the road width; the wider the vehicle width, the greater the preset distance; the wider the road width, the greater the preset distance.

[0118] Optionally, the second control module 702 includes: The fourth control submodule is used to determine the correction torque to be provided by the target control system based on the target correction angle. The fifth control submodule is used to control the vehicle to achieve lateral collision avoidance based on the corrective torque and the target control system.

[0119] Optionally, the device 700 also includes: The third control module is used to respond to determining that the vehicle turns to the target correction angle. If there is a risk of collision if the vehicle travels along the current trajectory, the module controls the vehicle to not exceed the maximum allowable deviation boundary and reduces the lateral speed of the vehicle to a vehicle speed threshold. The maximum allowable deviation boundary is closer to the obstacle than the active reference line.

[0120] Optionally, the device 700 also includes: The fourth control module is used to respond to determining that the lateral speed of the vehicle has decreased to the vehicle speed threshold, and to control the vehicle to perform regression control based on the rear collision risk of the vehicle, so as to guide the vehicle to move back to the original lane direction.

[0121] Optionally, the fourth control module is used for: If it is determined that there is no risk of collision behind the vehicle and the driver has taken control of the vehicle, then the vehicle is moved to the second return position. If it is determined that there is no risk of collision behind the vehicle and the driver has not taken over the vehicle, then the vehicle is controlled to move to the third return position; Wherein, the lateral offset between the first regression position and the current position of the vehicle is less than the lateral offset between the second regression position and the current position of the vehicle; the lateral offset between the second regression position and the current position of the vehicle is less than the lateral offset between the third regression position and the current position of the vehicle.

[0122] Optionally, the device 700 also includes: The second determining module is configured to determine that the driver takes over the vehicle if any of the following conditions are met: The steering wheel hand torque is greater than the first torque threshold and the steering wheel direction is consistent with the steering lever; The brake pedal is pressed and the pressing time is longer than the first preset duration; The accelerator pedal is pressed deeper than the depth threshold and the steering wheel torque is greater than the second torque threshold.

[0123] Optionally, the device 700 also includes: The third determination module is used to determine that the vehicle's driver assistance system is malfunctioning if any of the following conditions are met: The lane width is less than the width threshold; The lane curvature is greater than the curvature threshold; The lane markings ahead are missing; The brake pedal was pressed; The driver remained hands-free and did not take control of the vehicle. The steering wheel hand torque is greater than the third torque threshold.

[0124] Optionally, the target control system is an electric power steering system.

[0125] Based on the same concept, this disclosure also provides a controller, which includes: processor; Memory used to store processor-executable instructions; The processor is configured to execute the steps of the above vehicle control method.

[0126] Based on the same concept, embodiments of this disclosure also provide a vehicle including the controller described above.

[0127] Based on the same concept, embodiments of this disclosure also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described vehicle control method.

[0128] Based on the same concept, this disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-described vehicle control method.

[0129] The preferred embodiments of this disclosure have been described in detail above with reference to the accompanying drawings. However, this disclosure is not limited to the specific details of the above embodiments. Within the scope of the technical concept of this disclosure, various simple modifications can be made to the technical solutions of this disclosure, and these simple modifications all fall within the protection scope of this disclosure.

[0130] It should also be noted that the various specific technical features described in the above embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, this disclosure will not describe the various possible combinations separately.

[0131] Furthermore, various different embodiments of this disclosure can be combined in any way, as long as they do not violate the spirit of this disclosure, they should also be regarded as the content disclosed in this disclosure.

Claims

1. A vehicle control method, characterized in that, include; In response to determining that the vehicle's driver assistance system is malfunctioning, the driver assistance system is controlled to enter a cooperative takeover mode; In response to determining that the driver assistance system has entered cooperative takeover mode, if there is a risk of collision with the vehicle, the vehicle's target control system is used to actively control the vehicle's actions to avoid a collision.

2. The method according to claim 1, characterized in that, If the vehicle is at risk of collision, the vehicle's target control system is used to actively control the vehicle's actions, including: When the vehicle is at risk of collision, if the driver fails to perform driving maneuvers that would effectively avoid a collision, the target control system will be used to control the vehicle's actions.

3. The method according to claim 2, characterized in that, When the vehicle is at risk of collision, if the driver fails to perform driving maneuvers that could effectively avoid a collision, the target control system is used to control the vehicle's actions, including: If the driver fails to perform a driving operation that can effectively avoid a collision when the remaining collision reference time is less than a first remaining time threshold, the target control system will be used to control the vehicle's movement.

4. The method according to claim 2 or 3, characterized in that, If the driver fails to perform a driving maneuver that effectively avoids a collision, the target control system controls the vehicle's actions, including at least one of the following: If the driver does not take over the vehicle, the target control system provides all the corrective torque to achieve lateral collision avoidance. If the collision avoidance direction indicated by the driving operation is consistent with the theoretical collision avoidance direction, but the steering angle indicated by the driving operation is less than the theoretical collision avoidance steering angle, and the collision reference remaining time is less than the second remaining time threshold, then the auxiliary correction torque provided by the target control system, together with the steering torque provided by the driver, is used to achieve lateral collision avoidance, wherein the second remaining time threshold is less than the first remaining time threshold. If the collision avoidance direction indicated by the driving operation is inconsistent with the theoretical collision avoidance direction, a prompt message is generated to remind the user that the driving operation is incorrect, and the target control system is used to achieve lateral collision avoidance when the steering wheel torque is reduced.

5. The method according to claim 4, characterized in that, The method further includes: In response to determining that the vehicle has deviated from its course, the remaining collision reference time is determined based on the vehicle status information and the position of the activated reference line, wherein the activated reference line is located on the side of the obstacle facing the vehicle and is at a preset distance from the obstacle.

6. The method according to claim 5, characterized in that, The preset distance is determined based on the vehicle width and / or the road width; the wider the vehicle width, the greater the preset distance; the wider the road width, the greater the preset distance.

7. The method according to claim 1, characterized in that, The method of controlling vehicle actions using a target control system includes: Based on the target correction angle, determine the correction torque to be provided by the target control system; Based on the corrective torque, the target control system controls the vehicle to achieve lateral collision avoidance.

8. The method according to claim 7, characterized in that, The method further includes: In response to determining that the vehicle turns to the target correction angle, if there is a risk of collision if the vehicle travels along the current trajectory, the vehicle is controlled not to exceed the maximum allowable deviation boundary, and the lateral speed of the vehicle is reduced to a vehicle speed threshold, wherein the maximum allowable deviation boundary is closer to the obstacle than the active reference line.

9. The method according to claim 8, characterized in that, The method further includes: In response to determining that the lateral speed of the vehicle has decreased to the vehicle speed threshold, and based on the rear collision risk of the vehicle, the vehicle is controlled to perform regression control to guide the vehicle to move back towards the original lane direction.

10. The method according to claim 9, characterized in that, The step of controlling the vehicle to perform regression control based on the rear collision risk includes at least one of the following: If it is determined that there is a collision risk behind the vehicle, the vehicle is controlled to move to the first return position; If it is determined that there is no risk of collision behind the vehicle and the driver has taken control of the vehicle, then the vehicle is moved to the second return position. If it is determined that there is no risk of collision behind the vehicle and the driver has not taken over the vehicle, then the vehicle is controlled to move to the third return position; Wherein, the lateral offset between the first regression position and the current position of the vehicle is less than the lateral offset between the second regression position and the current position of the vehicle; The lateral offset between the second regression position and the current position of the vehicle is less than the lateral offset between the third regression position and the current position of the vehicle.

11. The method according to claim 4 or 10, characterized in that, The method further includes: The driver is determined to take over the vehicle if any of the following conditions are met: The steering wheel hand torque is greater than the first torque threshold and the steering wheel direction is consistent with the steering lever; The brake pedal is pressed and the pressing time is longer than the first preset duration; The accelerator pedal is pressed deeper than the depth threshold and the steering wheel torque is greater than the second torque threshold.

12. The method according to claim 1, characterized in that, The method further includes: The vehicle's driver assistance system is deemed malfunctioning if any of the following conditions are met: The lane width is less than the width threshold; The lane curvature is greater than the curvature threshold; The lane markings ahead are missing; The brake pedal was pressed; The driver remained hands-free and did not take control of the vehicle. The steering wheel hand torque is greater than the third torque threshold.

13. The method according to claim 1, characterized in that, The target control system is an electric power steering system.

14. A vehicle, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured to execute the executable instructions in the memory to implement the steps of the vehicle control method according to any one of claims 1-13.

15. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the vehicle control method according to any one of claims 1-13.

Images