Unmanned vehicle control method and device, unmanned vehicle and storage medium

Abstract

The invention provides an unmanned vehicle control method and device, an unmanned vehicle and a storage medium, and relates to the technical field of automatic driving. The method comprises the steps that under the condition that a collision signal transmitted by a collision sensor is received, a braking instruction is sent to an electronic braking system, the unmanned vehicle is controlled to enter a maintenance mode from a driving mode, the braking instruction is used for controlling the unmanned vehicle to execute braking operation, and in the maintenance mode, the unmanned vehicle does not execute a driving control instruction sent by an automatic driving system; determining a collision accident level of the unmanned vehicle based on the collision object type identified by the automatic driving system; the unmanned vehicle is controlled to exit the maintenance mode and enter the driving mode under the condition that a collision relieving signal corresponding to the collision accident level is received, different collision accident levels correspond to different collision relieving signals, and the collision relieving signals are generated after it is determined that the unmanned vehicle has the normal driving condition. According to the method, the processing efficiency and the processing compliance of the unmanned vehicle in the collision event can be improved.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and more specifically, to an unmanned vehicle control method, apparatus, unmanned vehicle, and storage medium in the field of autonomous driving technology. Background Technology

[0002] With the development of automatic control technology and artificial intelligence technology, vehicles (such as driverless cars) are widely used in fields such as express delivery, food delivery and retail.

[0003] Currently, autonomous vehicles are equipped with collision sensors at the front and rear to manage driving safety. When an autonomous vehicle is involved in a collision, it will enter an emergency stop state and wait for maintenance personnel to use a tow truck or push truck to rescue the vehicle. Otherwise, the autonomous vehicle cannot move, resulting in low efficiency in resolving collision incidents.

[0004] Therefore, improving the efficiency of resolving collision incidents involving autonomous vehicles is an urgent problem that needs to be solved. Summary of the Invention

[0005] This application provides an unmanned vehicle control method, device, unmanned vehicle, and storage medium, which can improve the efficiency of resolving unmanned vehicle collision accidents.

[0006] Firstly, a method for controlling an unmanned vehicle is provided. This method is applied to a chassis controller in the unmanned vehicle, which also includes a collision sensor, an autonomous driving system, and an electronic braking system. The collision sensor is connected to the chassis controller, the autonomous driving system is connected to the chassis controller, and the electronic braking system is connected to the chassis controller. The method includes:

[0007] Upon receiving a collision signal transmitted by the collision sensor, a braking command is sent to the electronic braking system, and the unmanned vehicle is controlled to enter a maintenance mode from the driving mode. The braking command is used to control the unmanned vehicle to perform a braking operation. In the maintenance mode, the unmanned vehicle does not execute the driving control commands sent by the autonomous driving system.

[0008] Based on the type of collision object identified by the autonomous driving system, the collision accident level of the unmanned vehicle is determined;

[0009] Upon receiving a collision clearance signal corresponding to the collision incident level, the driverless vehicle is controlled to exit the maintenance mode and enter the driving mode. Different collision incident levels correspond to different collision clearance signals, which are generated after it is determined that the driverless vehicle has normal driving conditions.

[0010] In this embodiment, a method for handling collision events of unmanned vehicles is provided: after detecting a collision signal transmitted by a collision sensor, the unmanned vehicle is controlled to brake and enter a maintenance mode, avoiding the problem of secondary collisions after the collision signal is recovered; in maintenance mode, the autonomous driving system identifies the type of collision object, determines the collision accident level of the unmanned vehicle, and allows the unmanned vehicle to exit maintenance mode and resume normal operation upon receiving a collision release signal matching the collision accident level. This allows the unmanned vehicle to continue operating even after a collision event, without waiting in place, improving the efficiency of handling collision accidents; furthermore, collision accidents can be classified according to the collision object, and matching collision release signals can be set, improving the accuracy of controlling the unmanned vehicle to exit maintenance mode and further ensuring the safety and compliance of handling unmanned vehicle collision accidents.

[0011] In conjunction with the first aspect, in some implementations of the first aspect, controlling the unmanned vehicle to exit the maintenance mode upon receiving a collision release signal corresponding to the collision accident level includes: upon receiving the collision release signal corresponding to the collision accident level, detecting the sensor signal transmitted by the collision sensor; and controlling the unmanned vehicle to exit the maintenance mode when the sensor signal changes from the collision signal to a normal signal.

[0012] In combination with the first aspect and the above-described implementations, in some implementations of the first aspect, the method further includes: controlling the unmanned vehicle to maintain the maintenance mode while the sensor signal maintains the collision signal.

[0013] In this embodiment, after receiving the collision cancellation signal corresponding to the collision accident level, it is necessary to further confirm whether the collision sensor signal has recovered. If it has recovered, the driverless car is controlled to exit the maintenance mode. If it has not recovered, the driverless car is controlled to remain in the maintenance mode. This can avoid the risk of the driverless car accidentally triggering a collision event or a secondary collision if it exits the maintenance mode when the collision sensor is faulty or there is still a collision risk.

[0014] In conjunction with the first aspect and the above implementation methods, in some implementation methods of the first aspect, the step of detecting the sensor signal transmitted by the collision sensor when receiving the collision relief signal corresponding to the collision accident level includes: when the collision accident level is a first accident level, detecting whether a first collision relief signal sent by the autonomous driving system is received, wherein the first collision relief signal is sent by the autonomous driving system to the chassis controller after recognizing that the unmanned vehicle has the normal driving conditions; and detecting the sensor signal transmitted by the collision sensor when receiving the first collision relief signal sent by the autonomous driving system.

[0015] In conjunction with the first aspect and the above implementation methods, in some implementation methods of the first aspect, the step of detecting the sensor signal transmitted by the collision sensor when receiving the collision relief signal corresponding to the collision accident level further includes: when the collision accident level is a second accident level, detecting whether a second collision relief signal sent by a remote driving system is received, wherein the second collision relief signal is sent by the remote driving system to the chassis controller after receiving the user's target confirmation operation, and the accident severity of the second accident level is greater than that of the first accident level; and detecting the sensor signal of the collision sensor when receiving the second collision relief signal sent by the remote driving system.

[0016] In this embodiment, the levels of autonomous vehicle collision events are classified according to the types of collision objects that may occur in the autonomous vehicle operation environment, and different collision release signals are set for different collision accident levels. In the case of a general collision event, the autonomous vehicle itself can determine whether it can continue to operate and issue a collision release signal, thereby improving the efficiency of resolving autonomous vehicle collision events. In the case of a serious collision event, the operators can manually determine whether it can continue to operate and issue a collision release signal, thereby improving the compliance of resolving autonomous vehicle collision events and improving the safety of the autonomous vehicle to continue operating.

[0017] In conjunction with the first aspect and the above implementation methods, in some implementation methods of the first aspect, the method further includes: when the duration for which the sensor signal maintains the collision signal reaches a duration threshold, sending an environmental detection request to the autonomous driving system, the environmental detection request being used to request the autonomous driving system to identify whether there is a collision object within the target range of the unmanned vehicle; if the detection result fed back by the autonomous driving system indicates that there is no collision object, determining that the collision sensor is faulty, and sending a maintenance request to the remote driving system, the maintenance request being used to request the remote driving system to control the unmanned vehicle to return to the maintenance location.

[0018] In this application embodiment, it is also proposed to determine whether the unmanned vehicle needs to return for maintenance by judging the reason why the collision sensor always maintains the collision signal, and to send a maintenance request to the remote driving system in a timely manner, so as to improve the maintenance efficiency of the unmanned vehicle.

[0019] In conjunction with the first aspect and the above implementation methods, in some implementation methods of the first aspect, the method further includes: upon receiving the collision signal transmitted by the collision sensor, controlling the hazard warning light to illuminate; and upon detecting that the unmanned vehicle has exited the maintenance mode, controlling the hazard warning light to turn off.

[0020] In this application embodiment, it is also proposed that after a collision event occurs, a hazard warning light be illuminated to alert surrounding pedestrians or vehicles, so that the autonomous vehicle can be in a relatively safe stationary state.

[0021] In conjunction with the first aspect and the above implementation methods, in some implementation methods of the first aspect, the method further includes: sending a maintenance request to a remote driving system when the collision cancellation signal corresponding to the collision accident level is not received, the maintenance request being used to request the remote driving system to control the unmanned vehicle to return to the maintenance location.

[0022] In this embodiment, even if a collision clearance signal is not received, the chassis controller can promptly send a maintenance request to the remote driving system to request a return to the maintenance location. This avoids waiting for operators to manually discover the fault and go to the site for inspection, saving maintenance waiting time and improving the efficiency of handling collision accidents of unmanned vehicles.

[0023] Secondly, an unmanned vehicle control device is provided, the device being applied to a chassis controller in an unmanned vehicle, the unmanned vehicle also being equipped with a collision sensor, an autonomous driving system, and an electronic braking system, the collision sensor being connected to the chassis controller, the autonomous driving system being connected to the chassis controller, and the electronic braking system being connected to the chassis controller, the device comprising:

[0024] The first control module is used to send a braking command to the electronic braking system when a collision signal is received from the collision sensor, and to control the unmanned vehicle to enter the maintenance mode from the driving mode. The braking command is used to control the unmanned vehicle to perform a braking operation. In the maintenance mode, the unmanned vehicle does not execute the driving control command sent by the autonomous driving system.

[0025] The first determining module is used to determine the collision accident level of the unmanned vehicle based on the type of collision object identified by the autonomous driving system.

[0026] The second control module is used to control the unmanned vehicle to exit the maintenance mode and enter the driving mode when it receives a collision release signal corresponding to the collision accident level. Different collision accident levels correspond to different collision release signals, and the collision release signal is generated after it is determined that the unmanned vehicle has normal driving conditions.

[0027] Thirdly, an unmanned vehicle is provided, including a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, causing the unmanned vehicle to perform the methods in the first aspect or any possible implementation thereof.

[0028] Fourthly, a computer program product is provided, comprising: computer program code, which, when run on a computer, causes the computer to perform the methods described in the first aspect or any possible implementation thereof.

[0029] Fifthly, a computer-readable storage medium is provided that stores computer program code, which, when executed on a computer, causes the computer to perform the methods described in the first aspect or any possible implementation thereof. Attached Figure Description

[0030] Figure 1 This is a schematic diagram of a control system architecture for an unmanned vehicle provided in an embodiment of this application;

[0031] Figure 2 This is a flowchart illustrating an unmanned vehicle control method provided in an embodiment of this application;

[0032] Figure 3 This is a flowchart illustrating another unmanned vehicle control method provided in an embodiment of this application;

[0033] Figure 4 This is a flowchart illustrating another unmanned vehicle control method provided in an embodiment of this application;

[0034] Figure 5 This is a schematic diagram of the structure of the unmanned vehicle control device provided in the embodiments of this application;

[0035] Figure 6 This is a schematic diagram of the structure of the unmanned vehicle provided in the embodiments of this application. Detailed Implementation

[0036] The technical solutions in this application will be clearly and thoroughly described below with reference to the accompanying drawings. In the description of the embodiments of this application, unless otherwise stated, " / " means "or," for example, A / B can mean A or B. "And / or" in the text is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Furthermore, in the description of the embodiments of this application, "multiple" refers to two or more than two.

[0037] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

[0038] First, the control system architecture of the autonomous vehicle will be illustrated by example. Figure 1 This is a schematic diagram of the control system architecture of an unmanned vehicle provided in an embodiment of this application.

[0039] like Figure 1 As shown, the control system of the unmanned vehicle mainly includes an Autonomous Driving Solution (ADS) 101, a Vehicle Control Unit (VCU) 106, a remote driving system 102, a remote control system 103, an electronic braking system 107, a drive system 108, a body domain controller 110, an electric power steering system 109, a front collision sensor 104, and a rear collision sensor 105.

[0040] The autonomous driving system 101 can be used to determine control signals for the driverless vehicle based on road conditions during autonomous driving, such as control signals for vehicle speed, steering, and parking, and send these control signals to the chassis controller. Furthermore, in autonomous driving mode, without human intervention, the chassis controller can automatically plan the driving trajectory and speed based on current road conditions and a pre-planned route, and drive according to the planned trajectory and speed.

[0041] The remote driving system 102 can be used by back-end control personnel (or operators) to send remote control signals to the chassis controller through the back-end control equipment, so that the chassis controller can control the unmanned vehicle according to the remote control signals.

[0042] The remote control system 103 can be used by on-site controllers to send remote control signals, such as acceleration, left turn, and reverse signals, to the chassis controller so that the chassis controller can control the vehicle according to the received remote control information.

[0043] The chassis controller 106 can be used to receive signals sent by the autonomous driving system 101, the remote driving system 102 and the remote control system 103, as well as signals sent by other control modules in the driverless vehicle, and control the driverless vehicle through these signals.

[0044] The electronic braking system 107 can be used to brake the vehicle while it is in motion. The electronic braking system 107 may include two braking systems: IBS and EPB; or, the electronic braking system 107 refers specifically to the IBS braking system.

[0045] The electric power steering system 109 can be used to control the drive motor of the unmanned vehicle to output a specified torque and speed to drive the unmanned vehicle, such as forward and backward movement.

[0046] The vehicle domain controller 110 can be used to control the opening or closing of vehicle lights, doors, etc. on unmanned vehicles.

[0047] Figure 2 This is a flowchart illustrating an unmanned vehicle control method provided in an embodiment of this application. The method is applied to the VCU (Vehicle Control Unit) in an unmanned vehicle and can be controlled by… Figure 1 The autonomous vehicles in the process, or by Figure 1 The VCU executes within it.

[0048] For example, such as Figure 2 As shown, the method 200 includes:

[0049] Step 201: Upon receiving a collision signal transmitted by the collision sensor, a braking command is sent to the electronic braking system, and the unmanned vehicle is controlled to switch from driving mode to maintenance mode.

[0050] During operation, autonomous vehicles may collide with other vehicles, pedestrians, or obstacles (such as road barriers or speed bumps). To detect such collisions, collision sensors are installed at the front and rear of the autonomous vehicle. If no collision occurs, the signal output of the collision sensor can be 0. If a collision occurs, the signal output of the collision sensor changes to 1. The chassis controller can determine whether a collision has occurred based on the signals received from the collision sensors.

[0051] When the chassis controller receives a collision signal from the collision sensor, it indicates that a collision has occurred with the autonomous vehicle. In order to prevent the autonomous vehicle from continuing to drive and causing repeated collisions and damage, the chassis controller first sends a braking command to the electronic braking system (IBS). This braking command is used to control the autonomous vehicle to perform braking operations, so that the autonomous vehicle brakes with maximum braking capacity, reduces the speed of the autonomous vehicle, and thus brings the autonomous vehicle to a safe stop.

[0052] Furthermore, considering that after a collision, the autonomous vehicle will move away from the collided object due to the reaction force, and the collision sensor signal will change from 1 to 0, that is, return to the non-collision state, if the autonomous driving system directly controls the autonomous vehicle to continue operating at this time, it will obviously lead to secondary or multiple collisions, causing secondary damage to the autonomous vehicle. To avoid this secondary collision, in this embodiment, when the chassis controller receives the collision signal transmitted by the collision sensor, it will first send a braking command to the electronic braking system to control the autonomous vehicle to brake. After the autonomous vehicle is in a safe and stationary state, it will control the autonomous vehicle to enter the maintenance mode from the driving mode. In the maintenance mode, the autonomous vehicle will not execute the driving control commands sent by the autonomous driving system. That is to say, when entering the maintenance mode, regardless of whether the collision sensor signal is triggered and then recovers, the autonomous vehicle will be locked in the collision state and kept in a safe and stationary state. In this maintenance mode, the autonomous driving system cannot control the autonomous vehicle to execute the predetermined planned operation route.

[0053] Step 202: Determine the collision accident level of the driverless car based on the type of collision object identified by the autonomous driving system.

[0054] Considering that autonomous vehicles generally operate at low speeds, whether a collision affects their continued operation depends primarily on the object of the collision. If the object is a stationary obstacle along the route, such as a speed bump or road barrier, the impact on the autonomous vehicle may be minimal; however, if the object is another moving vehicle, the impact may be significant. Therefore, by screening the collision objects, collision accidents of autonomous vehicles can be classified, allowing for different follow-up handling methods for different accident levels. In one possible implementation, after the vehicle enters maintenance mode, the chassis controller can send a collision object identification request to the autonomous driving system. This allows the system to identify the collision object type using cameras, LiDAR, etc., and feed this information back to the chassis controller. Based on the collision object type, the chassis controller can determine the collision accident level and, consequently, how to proceed with the follow-up handling at that level.

[0055] Step 203: Upon receiving a collision clearance signal corresponding to the collision accident level, control the unmanned vehicle to exit maintenance mode and enter driving mode.

[0056] If a collision involving an autonomous vehicle does not affect its continued operation, the vehicle can continue operating without waiting for repairs. To improve the efficiency of resolving collision incidents, one possible implementation involves a collision clearance signal generated after confirming that the vehicle is ready for normal driving. Upon receiving the collision clearance signal, the chassis controller can control the vehicle to exit repair mode and enter driving mode, continuing operation according to the planned route under the control of the autonomous driving system.

[0057] Considering that collisions involving autonomous vehicles can have varying levels of damage, resulting in different levels of harm to the vehicle and its surroundings, different collision clearance signals are set for each level. The chassis controller can only control the autonomous vehicle to exit maintenance mode and enter driving mode after receiving a collision clearance signal that matches the collision level. This allows the autonomous vehicle to exit the collision state and continue operation in a compliant and safe manner, improving the efficiency of handling collision accidents while ensuring the safety and compliance of such handling.

[0058] In summary, this application provides a method for handling collision events of unmanned vehicles: by controlling the unmanned vehicle to brake and enter maintenance mode after detecting a collision signal transmitted by a collision sensor, the problem of secondary collisions occurring after the collision signal is recovered is avoided; in maintenance mode, the autonomous driving system identifies the type of collision object, determines the collision accident level of the unmanned vehicle, and allows the unmanned vehicle to exit maintenance mode and resume normal operation upon receiving a collision release signal matching the collision accident level. This allows the unmanned vehicle to continue operating even after a collision event and it is determined that the vehicle can continue to operate without waiting in place, improving the efficiency of handling collision accidents; furthermore, collision accidents can be classified according to the collision object, and matching collision release signals can be set, improving the accuracy of controlling the unmanned vehicle to exit maintenance mode and further ensuring the safety and compliance of handling unmanned vehicle collision accidents.

[0059] After a collision, the collision sensor signal of a typical autonomous vehicle will return to normal. However, if the collision sensor signal remains at the collision level, it indicates that the autonomous vehicle may still have collision problems or that the collision sensor is malfunctioning. In other words, the autonomous vehicle does not meet the conditions for normal operation and needs to be kept in maintenance mode.

[0060] Figure 3 This is a flowchart illustrating another unmanned vehicle control method provided in an embodiment of this application. This method is applied to the VCU (Vehicle Control Unit) in an unmanned vehicle and can be controlled by… Figure 1 The autonomous vehicles in the process, or by Figure 1 The VCU executes within it.

[0061] For example, such as Figure 3 As shown, the method 300 includes:

[0062] Step 301: Upon receiving a collision signal transmitted by the collision sensor, a braking command is sent to the electronic braking system, and the unmanned vehicle is controlled to switch from driving mode to maintenance mode.

[0063] The implementation method of step 301 can refer to step 201, and will not be repeated here in this embodiment.

[0064] In the event of a collision involving an autonomous vehicle, in order to ensure that the autonomous vehicle remains in a safe and stationary state and to avoid the impact of other pedestrians or vehicles on the autonomous vehicle, one possible implementation is that, upon receiving a collision signal transmitted by a collision sensor, the chassis controller can send a lighting request to the body domain controller. Upon receiving the lighting request, the corresponding body domain controller will illuminate the hazard warning lights to alert surrounding vehicles and pedestrians.

[0065] Step 302: Determine the collision accident level of the driverless car based on the type of collision object identified by the autonomous driving system.

[0066] For example, in the operating environment of autonomous vehicles, possible collision objects include: other autonomous vehicles, other vehicles (bicycles, motor vehicles), pedestrians, road barriers, speed bumps, and other stationary obstacles.

[0067] For potential collisions in the autonomous vehicle operating environment, collision incidents are primarily categorized into two levels: Level 1 and Level 2. Level 2 incidents are more severe than Level 1 incidents. Considering that roadblocks, speed bumps, and other stationary obstacles generally do not cause serious damage to autonomous vehicles and do not involve traffic liability or other issues requiring human intervention for judgment, when the autonomous driving system identifies a collision object as a roadblock, speed bump, or other stationary obstacle, the chassis controller can determine the autonomous vehicle's collision incident level as Level 1, i.e., a general incident. However, considering that other autonomous vehicles, other vehicles, and pedestrians may generally cause serious damage to autonomous vehicles and involve traffic liability or other issues requiring human intervention for judgment, when the autonomous driving system identifies a collision object belonging to this category, the chassis controller can determine the autonomous vehicle's collision incident level as Level 2.

[0068] Optionally, in addition to classifying the first accident level and the second accident level for different types of collision objects, a more granular classification can be made to divide the accident into two or more accident levels, and different handling methods can be provided for different accident levels.

[0069] Step 303: Upon receiving a collision release signal corresponding to the collision incident level, detect the sensor signal transmitted by the collision sensor.

[0070] If a collision clearance signal corresponding to the collision incident level is received, it means that the collision incident does not affect the continued operation of the autonomous vehicle. At this time, it is necessary to further judge the sensor signals transmitted by the collision sensor to determine whether the sensor signals have returned to normal, and then determine whether to control the autonomous vehicle to exit the maintenance mode.

[0071] Optionally, if no collision clearance signal corresponding to the collision incident level is received, it indicates that the unmanned vehicle is not in normal driving condition due to the collision event and may need to return for repair. In order to improve repair efficiency, the chassis controller can send a repair request to the remote driving system to request the remote driving system to control the unmanned vehicle to return to the repair location. Upon receiving the repair request, the remote driving system can remind the staff that the unmanned vehicle has a malfunction, and the staff can control the unmanned vehicle to return to the repair location through the remote driving system.

[0072] Optionally, the handling of collision events differs for different accident levels, and the corresponding methods for generating collision release signals also differ. Taking an accident level that includes a first accident level and a second accident level as an example, there are two collision release signals: a first collision release signal for the first accident level and a second collision release signal for the second accident level.

[0073] For the first accident level, step 303 may include steps 303A and 303B.

[0074] Step 303A: If the collision accident level is the first accident level, check whether the first collision cancellation signal sent by the autonomous driving system is received. The first collision cancellation signal is sent by the autonomous driving system to the chassis controller after recognizing that the driverless vehicle has normal driving conditions.

[0075] Step 303B: Upon receiving the first collision relief signal sent by the autonomous driving system, detect the sensor signal transmitted by the collision sensor.

[0076] The first accident level indicates that the collision event of the current driverless car is less harmful to the driverless car and there is no need for traffic accident identification. The corresponding operation judgment logic configured in the autonomous driving system of the driverless car can identify whether the driverless car has normal driving conditions. If the autonomous driving system identifies that the driverless car has normal driving conditions, it sends a first collision cancellation signal to the chassis controller to release the collision state of the driverless car.

[0077] In one possible implementation, when the collision incident is classified as Level 1, the chassis controller detects whether it has received a first collision release signal from the autonomous driving system. If the chassis controller receives the first collision release signal from the autonomous driving system, it further detects the sensor signals transmitted by the collision sensors to determine whether to exit maintenance mode.

[0078] Conversely, if the autonomous driving system detects that the driverless vehicle does not meet the conditions for normal driving, it will not send the first collision cancellation signal to the chassis controller; correspondingly, if the chassis controller does not receive the first collision cancellation signal, it will always keep the driverless vehicle in maintenance mode.

[0079] Regarding the method by which autonomous driving systems identify whether driverless cars have normal driving conditions: it can be determined whether the feedback signals from other control components are normal. If all feedback signals are normal, it means that the driverless car has normal driving conditions and the collision accident did not cause damage to the driverless car itself.

[0080] For the second accident level, step 303 may include steps 303C and 303D.

[0081] Step 303C: If the collision accident level is the second accident level, check whether a second collision cancellation signal sent by the remote driving system is received. The second collision cancellation signal is sent by the remote driving system to the chassis controller after receiving the user's target confirmation operation.

[0082] Step 303D: Upon receiving the second collision cancellation signal sent by the remote driving system, detect the sensor signal of the collision sensor.

[0083] The second accident level indicates that the collision event poses a significant threat to the autonomous vehicle itself, or that there is a need for traffic accident determination. Since traffic accident determination requires human intervention, the chassis controller can send a collision accident determination request to the remote driving system. The corresponding staff or business personnel (target users) can then judge the collision event in the background through the autonomous vehicle's camera. If it is determined that the collision event does not affect the autonomous vehicle's normal driving conditions, the remote driving system will send a second collision cancellation signal to the chassis controller through a target confirmation operation to release the autonomous vehicle from the collision state.

[0084] In one possible implementation, if the collision accident level is the second accident level, the chassis controller detects whether it receives a second collision cancellation signal sent by the remote driving system. If the chassis controller receives the second collision cancellation signal sent by the remote driving system, it further detects the sensor signals transmitted by the collision sensor to determine whether to exit the maintenance mode.

[0085] Conversely, if staff or business personnel determine that the autonomous vehicle does not meet the conditions for normal driving, the corresponding remote driving system will not receive the target confirmation operation, nor will it send a second collision cancellation signal to the chassis controller; correspondingly, if the chassis controller does not receive the second collision cancellation signal, the autonomous vehicle will always be kept in maintenance mode.

[0086] Step 304: When the sensor signal changes from a collision signal to a normal signal, control the unmanned vehicle to exit the maintenance mode and enter the driving mode.

[0087] If the sensor signal changes from a collision signal to a normal signal, it means that the collision sensor of the autonomous vehicle has not undergone collision deformation. At this time, the autonomous vehicle can be controlled to exit the maintenance mode and enter the driving mode, and can continue to operate normally according to the control instructions of the autonomous driving system.

[0088] When the autonomous vehicle is in maintenance mode, the hazard warning lights remain illuminated. After the chassis controller exits maintenance mode, it can send a request to the body domain controller to turn off the hazard warning lights. Upon receiving the request, the corresponding chassis controller will control the hazard warning lights to turn off or shut them off.

[0089] Step 305: While the sensor signal remains a collision signal, control the unmanned vehicle to maintain maintenance mode.

[0090] If the sensor signal still indicates a collision, it means the autonomous vehicle's collision sensor may have deformed due to a collision, or there is still a collision problem. Directly controlling the autonomous vehicle to exit maintenance mode could lead to a secondary collision risk or subsequent incorrect collision identification. In this case, the chassis controller keeps the autonomous vehicle in maintenance mode, awaiting a return trip for further maintenance.

[0091] Optionally, if the collision sensor signal remains unchanged after the chassis controller receives a collision release signal, it may indicate a collision sensor malfunction or that the autonomous vehicle is still in contact with an obstacle. To clarify the subsequent processing method, one possible implementation is to send an environmental detection request to the autonomous driving system when the chassis controller detects that the duration of the collision signal remains unchanged reaches a time threshold. This request asks the autonomous driving system to identify whether a collision object exists within the target range of the autonomous vehicle, thus identifying the reason why the collision sensor continues to maintain the collision signal.

[0092] If the detection results from the autonomous driving system indicate that there is no collision object within the target range of the driverless vehicle, it means that the collision signal was not triggered by the collision object, but rather by a malfunction of the collision sensor itself. In the case of a malfunctioning collision sensor, the driverless vehicle cannot continue operating. To enable the driverless vehicle to return for repairs, the chassis controller sends a repair request to the remote driving system. This request instructs the remote driving system to control the driverless vehicle to return to the repair location. Upon receiving the repair request, personnel can use the remote driving system or remote control system in repair mode to control the vehicle to return for repairs, thereby improving the efficiency of collision accident handling and preventing situations where the driverless vehicle remains stationary, unable to return for repairs, and unable to continue operating.

[0093] In this embodiment, after receiving the collision cancellation signal corresponding to the collision accident level, it is necessary to further confirm whether the collision sensor signal has been restored. If it is restored, the driverless car is controlled to exit the maintenance mode. If it is not restored, the driverless car needs to be controlled to remain in the maintenance mode. This can avoid the risk of the driverless car accidentally triggering a collision event or a secondary collision if it exits the maintenance mode when the collision sensor is faulty or there is still a collision risk.

[0094] Furthermore, this embodiment also classifies autonomous vehicle collision events into levels based on the types of collision objects that may occur in the autonomous vehicle operation environment, and sets different collision release signals for different collision accident levels. This allows the autonomous vehicle itself to determine whether it can continue operating and issue a collision release signal in the case of a general collision event, thereby improving the efficiency of resolving autonomous vehicle collision events. In the case of a serious collision event, the operator manually determines whether it can continue operating and issues a collision release signal, thereby improving the compliance of resolving autonomous vehicle collision events and enhancing the safety of the autonomous vehicle's continued operation.

[0095] Furthermore, the study proposes determining whether an autonomous vehicle (RV) needs to be returned for maintenance by analyzing why the collision sensors maintain a collision signal, and promptly sending maintenance requests to the remote driving system to improve RV maintenance efficiency. It also suggests illuminating hazard warning lights after a collision to alert nearby pedestrians or vehicles, allowing the RV to remain in a relatively safe, stationary state.

[0096] In addition, if no collision clearance signal is received, the chassis controller can also send a maintenance request to the remote driving system in a timely manner to request to return to the maintenance location. This avoids waiting for operators to discover the fault and go to the site for inspection, saves maintenance waiting time, and improves the efficiency of handling collision accidents of autonomous vehicles.

[0097] Figure 4 This is a flowchart illustrating another unmanned vehicle control method provided in an embodiment of this application. The method includes:

[0098] Step 401: The chassis controller detects and triggers a collision signal.

[0099] When the chassis controller detects that the status signal of the front collision sensor is 1, and / or the status signal of the rear collision sensor is 1, it determines that a collision signal has been detected and triggered.

[0100] Step 402: The chassis controller sends the vehicle collision status to the bus and controls the hazard warning lights to illuminate.

[0101] If a collision signal is triggered (front collision sensor status = 1 and / or rear collision sensor status = 1), the chassis controller switches the vehicle operating status to collision status and sends a collision alarm signal and collision sensor signal status to the bus.

[0102] Step 403: Detect whether the actual speed of the driverless car is 0 km / h.

[0103] Step 404: The chassis controller controls the IBS of the unmanned vehicle to perform emergency braking and pulls up the EPB.

[0104] When an autonomous vehicle collides, if the current actual vehicle speed is not equal to 0 km / h, the chassis controller will trigger emergency braking control, control the IBS to execute the maximum braking force (100% braking force), the EPS to maintain the current steering angle, and pull up the EPB to make the vehicle speed equal to 0 km / h. The vehicle driving mode will switch to maintenance mode, and the hazard warning lights will be illuminated to remind surrounding vehicles and pedestrians.

[0105] Step 405: Detect whether the actual speed of the unmanned vehicle is 0 and whether the EPB is activated.

[0106] Step 406: The chassis controller controls the unmanned vehicle to enter maintenance mode.

[0107] If the driverless car switches from driving mode to maintenance mode, the autonomous driving system cannot control the vehicle to execute the predetermined route. The vehicle can only be controlled through a remote driving system or remote control system. In maintenance mode, the vehicle's performance will be limited, that is, the vehicle is kept in a safe stationary state.

[0108] Step 407: The autonomous driving system autonomously determines, or the operators confirm the status of the driverless vehicle through the backend or on-site, whether the driverless vehicle should continue driving.

[0109] In maintenance mode, the autonomous driving system uses sensors such as LiDAR, millimeter-wave radar, or cameras to perceive the surroundings, identify and filter the types of collision targets (collision object types), and send them to the bus. The chassis controller can determine the collision level (collision accident level) based on the type of collision target and execute the corresponding collision handling strategy.

[0110] If the autonomous vehicle collides with a pedestrian / motor vehicle / bicycle, the chassis controller determines the collision accident level as important (second accident level), requiring personnel to handle the accident and deactivate the vehicle's collision status. If the autonomous vehicle collides with a curb or other low-lying object (roadblock / speed bump, etc.) that does not constitute a traffic accident, the chassis controller determines the collision level as normal (first accident level), and the vehicle's collision status can be deactivated by a switch signal issued by the autonomous driving system, improving the efficiency of collision accident handling.

[0111] Step 408: The autonomous driving system or the operator issues a command signal to deactivate the vehicle collision status.

[0112] Step 409: The chassis controller checks whether the collision sensor signal status has recovered.

[0113] When the chassis control detects that the status signal of the front collision sensor is 0 and the status signal of the rear collision sensor is 0, it determines that the collision sensor signal status has recovered.

[0114] Step 410: The chassis controller controls the unmanned vehicle to exit the maintenance mode, turn off the hazard warning lights, and enter the driving mode.

[0115] If the chassis controller receives a collision clearance signal (issued by the autonomous driving system or by staff) and the status signal of the collision sensor has been reset, it can control the unmanned vehicle to exit maintenance mode and enter driving mode. In driving mode, the autonomous driving system can control the vehicle to continue operating according to the planned route.

[0116] Step 411: The chassis controller controls the unmanned vehicle to maintain maintenance mode.

[0117] If the chassis controller receives a collision clearance signal but the collision sensor status signal is not reset, the chassis controller will keep the autonomous vehicle in maintenance mode. Alternatively, if the chassis controller does not receive a collision clearance signal, it will also keep the autonomous vehicle in maintenance mode.

[0118] Figure 5 This is a schematic diagram of the unmanned vehicle control device provided in an embodiment of this application. The device is applied to the chassis controller of an unmanned vehicle. The unmanned vehicle is also equipped with a collision sensor, an autonomous driving system, and an electronic braking system. The collision sensor is connected to the chassis controller, the autonomous driving system is connected to the chassis controller, and the electronic braking system is connected to the chassis controller.

[0119] For example, such as Figure 5 As shown, the device 500 includes:

[0120] The first control module 501 is used to send a braking command to the electronic braking system when it receives a collision signal transmitted by the collision sensor, and to control the unmanned vehicle to enter the maintenance mode from the driving mode. The braking command is used to control the unmanned vehicle to perform a braking operation. In the maintenance mode, the unmanned vehicle does not execute the driving control command sent by the autonomous driving system.

[0121] The first determining module 502 is used to determine the collision accident level of the unmanned vehicle based on the collision object type identified by the autonomous driving system.

[0122] The second control module 503 is used to control the unmanned vehicle to exit the maintenance mode and enter the driving mode when it receives a collision release signal corresponding to the collision accident level. Different collision accident levels correspond to different collision release signals, and the collision release signal is generated after determining that the unmanned vehicle has normal driving conditions.

[0123] In one possible implementation, the second control module 503 is further configured to: detect the sensor signal transmitted by the collision sensor when receiving the collision release signal corresponding to the collision accident level; and control the unmanned vehicle to exit the maintenance mode when the sensor signal changes from the collision signal to a normal signal.

[0124] In one possible implementation, the device further includes a third control module for controlling the unmanned vehicle to maintain the maintenance mode while the sensor signal maintains the collision signal.

[0125] In one possible implementation, the second control module 503 is further configured to: detect whether a first collision relief signal is received from the autonomous driving system when the collision accident level is a first accident level, wherein the first collision relief signal is sent by the autonomous driving system to the chassis controller after recognizing that the unmanned vehicle has the normal driving conditions; and detect the sensor signal transmitted by the collision sensor when the first collision relief signal is received from the autonomous driving system.

[0126] In one possible implementation, the second control module 503 is further configured to: detect whether a second collision clearance signal is received from the remote driving system when the collision accident level is the second accident level, wherein the second collision clearance signal is sent by the remote driving system to the chassis controller after receiving the user's target confirmation operation, and the severity of the second accident level is greater than that of the first accident level; and detect the sensor signal of the collision sensor when the second collision clearance signal is received from the remote driving system.

[0127] In one possible implementation, the device further includes: a first sending module, configured to send an environmental detection request to the autonomous driving system when the duration for which the sensor signal holds the collision signal reaches a duration threshold, the environmental detection request being used to request the autonomous driving system to identify whether a collision object exists within the target range of the unmanned vehicle; and a second determining module, configured to determine that the collision sensor is faulty if the detection result fed back by the autonomous driving system indicates that the collision object does not exist, and to send a maintenance request to a remote driving system, the maintenance request being used to request the remote driving system to control the unmanned vehicle to return to a maintenance location.

[0128] In one possible implementation, the device further includes: a fourth control module, configured to control the hazard warning lights to illuminate upon receiving the collision signal transmitted by the collision sensor; and a fifth control module, configured to control the hazard warning lights to turn off upon detecting that the unmanned vehicle has exited the maintenance mode.

[0129] In one possible implementation, the device further includes a second sending module, configured to send a maintenance request to a remote driving system if the collision clearance signal corresponding to the collision accident level is not received, the maintenance request being used to request the remote driving system to control the unmanned vehicle to return to the maintenance location.

[0130] It should be noted that the aforementioned device 500 is embodied in the form of a functional module. The term "module" here can be implemented in software and / or hardware, without specific limitations.

[0131] For example, a "module" can be a software program, a hardware circuit, or a combination of both that implements the above functions. The hardware circuit may include an application-specific integrated circuit (ASIC), electronic circuitry, a processor (e.g., a shared processor, a proprietary processor, or a group processor) and memory for executing one or more software or firmware programs, integrated logic circuitry, and / or other suitable components that support the described functions.

[0132] Therefore, the modules of the various examples described in the embodiments of this application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0133] Figure 6This is a schematic diagram of the structure of the unmanned vehicle provided in the embodiments of this application.

[0134] For example, such as Figure 6 As shown, the unmanned vehicle 600 includes a memory 601 and a processor 602. The memory 601 stores executable program code 603, and the processor 602 is used to call and execute the executable program code 603 to perform an unmanned vehicle control method.

[0135] This application can divide the vehicle into functional modules based on the above method example. For example, each module can correspond to a separate function module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0136] When each functional module is divided according to its corresponding function, the unmanned vehicle may include: a first determining module, a first control module, and a second control module, etc. It should be noted that all relevant content of each step involved in the above method embodiments can be referenced from the functional descriptions of the corresponding functional modules, and will not be repeated here.

[0137] The vehicle provided in this application is used to execute the aforementioned unmanned vehicle control method, and thus can achieve the same effect as the aforementioned implementation method.

[0138] When using integrated units, the vehicle may include a processing module and a storage module. The processing module is used to control and manage the vehicle's actions. The storage module supports the vehicle in executing program code and data.

[0139] The processing module may be a processor or a controller, which can implement or execute various exemplary logic blocks, modules, and circuits as disclosed in this application. The processor may also be a combination of functions that implement computing capabilities, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc., and the storage module may be a memory.

[0140] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the methods described in the foregoing embodiments. The computer-readable storage medium may include, but is not limited to, any type of disk, including floppy disks, optical disks, DVDs (Digital Video Discs), CD-ROMs (Compact Disc Read-Only Memory), microdrives, magneto-optical disks, ROMs (Read-Only Memory), RAMs (Random Access Memory), EPROMs (Erasable Programmable Read-Only Memory), EEPROMs (Electrically Erasable Programmable Read Only Memory), DRAMs (Dynamic Random Access Memory), VRAMs (Video Random Access Memory), flash memory devices, magnetic cards or optical cards, nanosystems (including molecular memory ICs), or any type of medium or device suitable for storing instructions and / or data.

[0141] This application also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned related steps to implement an unmanned vehicle control method as described in the above embodiments.

[0142] In addition, the vehicle provided in the embodiments of this application may specifically be a chip, component or module. The vehicle may include a connected processor and a memory. The memory is used to store instructions. When the vehicle is running, the processor can call and execute the instructions to make the chip execute an unmanned vehicle control method in the above embodiments.

[0143] The vehicle, computer-readable storage medium, computer program product or chip provided in this application are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects of the corresponding methods provided above, and will not be repeated here.

[0144] Through the above description of the embodiments, those skilled in the art will understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0145] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0146] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for controlling an unmanned vehicle, characterized in that, The method is applied to the chassis controller of an autonomous vehicle, which is also equipped with a collision sensor, an autonomous driving system, and an electronic braking system. The collision sensor is connected to the chassis controller, the autonomous driving system is connected to the chassis controller, and the electronic braking system is connected to the chassis controller. The method includes: Upon receiving a collision signal transmitted by the collision sensor, a braking command is sent to the electronic braking system, and the unmanned vehicle is controlled to enter a maintenance mode from the driving mode. The braking command is used to control the unmanned vehicle to perform a braking operation. In the maintenance mode, the unmanned vehicle does not execute the driving control commands sent by the autonomous driving system. Based on the type of collision object identified by the autonomous driving system, the collision accident level of the unmanned vehicle is determined; Upon receiving a collision clearance signal corresponding to the collision incident level, the driverless vehicle is controlled to exit the maintenance mode and enter the driving mode. Different collision incident levels correspond to different collision clearance signals, which are generated after it is determined that the driverless vehicle has normal driving conditions.

2. The method according to claim 1, characterized in that, Upon receiving a collision clearance signal corresponding to the collision incident level, controlling the unmanned vehicle to exit the maintenance mode includes: Upon receiving the collision release signal corresponding to the collision incident level, the sensor signal transmitted by the collision sensor is detected; When the sensor signal changes from the collision signal to a normal signal, the driverless vehicle is controlled to exit the maintenance mode.

3. The method according to claim 2, characterized in that, The method further includes: While the sensor signal remains the collision signal, the unmanned vehicle is controlled to maintain the maintenance mode.

4. The method according to claim 2, characterized in that, The step of detecting the sensor signal transmitted by the collision sensor upon receiving the collision release signal corresponding to the collision incident level includes: In the case that the collision accident level is the first accident level, it is detected whether a first collision relief signal sent by the autonomous driving system is received. The first collision relief signal is sent by the autonomous driving system to the chassis controller after recognizing that the unmanned vehicle has the normal driving conditions. Upon receiving the first collision relief signal sent by the autonomous driving system, the sensor signal transmitted by the collision sensor is detected.

5. The method according to claim 4, characterized in that, The step of detecting the sensor signal transmitted by the collision sensor upon receiving the collision release signal corresponding to the collision incident level further includes: In the case that the collision accident level is the second accident level, it is detected whether a second collision cancellation signal sent by the remote driving system is received. The second collision cancellation signal is sent by the remote driving system to the chassis controller after receiving the user's target confirmation operation. The accident severity of the second accident level is greater than that of the first accident level. Upon receiving the second collision clearance signal sent by the remote driving system, the sensor signal of the collision sensor is detected.

6. The method according to claim 3, characterized in that, The method further includes: If the duration for which the sensor signal holds the collision signal reaches a duration threshold, an environmental detection request is sent to the autonomous driving system. The environmental detection request is used to request the autonomous driving system to identify whether there is a collision object within the target range of the driverless vehicle. If the detection result fed back by the autonomous driving system indicates that there is no collision object, it is determined that the collision sensor is faulty, and a maintenance request is sent to the remote driving system. The maintenance request is used to request the remote driving system to control the unmanned vehicle to return to the maintenance location.

7. The method according to any one of claims 1 to 6, characterized in that, The method further includes: Upon receiving the collision signal transmitted by the collision sensor, the hazard warning lights are illuminated. If the driverless vehicle is detected to have exited the maintenance mode, the hazard warning lights will be turned off.

8. The method according to any one of claims 1 to 6, characterized in that, The method further includes: If the collision clearance signal corresponding to the collision incident level is not received, a maintenance request is sent to the remote driving system, which requests the remote driving system to control the unmanned vehicle to return to the maintenance location.

9. An unmanned vehicle control device, characterized in that, The device is used in the chassis controller of an unmanned vehicle. The unmanned vehicle is also equipped with a collision sensor, an autonomous driving system, and an electronic braking system. The collision sensor is connected to the chassis controller, the autonomous driving system is connected to the chassis controller, and the electronic braking system is connected to the chassis controller. The device includes: The first control module is used to send a braking command to the electronic braking system when a collision signal is received from the collision sensor, and to control the unmanned vehicle to enter the maintenance mode from the driving mode. The braking command is used to control the unmanned vehicle to perform a braking operation. In the maintenance mode, the unmanned vehicle does not execute the driving control command sent by the autonomous driving system. The first determining module is used to determine the collision accident level of the unmanned vehicle based on the type of collision object identified by the autonomous driving system. The second control module is used to control the unmanned vehicle to exit the maintenance mode and enter the driving mode when it receives a collision release signal corresponding to the collision accident level. Different collision accident levels correspond to different collision release signals, and the collision release signal is generated after it is determined that the unmanned vehicle has normal driving conditions.

10. An unmanned vehicle, characterized in that, The unmanned vehicles include: Memory, used to store executable program code; A processor is configured to call and run the executable program code from the memory, causing the unmanned vehicle to perform the method as described in any one of claims 1 to 8.

Images