Control method and apparatus

Abstract

The present application provides a control method and apparatus. The method comprises: when a vehicle is in an autonomous driving state, acquiring surrounding environment information; and sending a vehicle control instruction on the basis of the environment information. The vehicle control instruction comprises passing instruction information and safe stopping instruction information. The passing instruction information indicates a target pose of a vehicle during travel when an autonomous driving function is in an effective output state; and the safe stopping instruction information indicates a target pose of the vehicle during stopping when the autonomous driving function is not in the effective output state. Embodiments of the present application can be applied to a new energy vehicle or an intelligent driving vehicle, and when the autonomous driving function is not in the effective output state (for example, an autonomous driving domain controller crashes and a fault occurs in a communication line for transmitting the output of an autonomous driving controller), the vehicle can still be in a controlled state without manual intervention, so that the safety risk caused by out-of-control of the vehicle is avoided, and the driving safety of the vehicle can be improved.

Description

Control method and device

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of China on April 1, 2024, with application number 202410389857.0 and invention name “Control Method and Device”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of intelligent driving, and more specifically, to a control method and device. Background Art

[0003] With technological advancements, autonomous driving features are becoming increasingly common. As the level of autonomous driving increases, the requirements for functional safety are also increasing. For example, high-level autonomous driving often requires the vehicle to be able to cope with safety risks caused by anomalies or failures of various systems and components in autonomous driving scenarios, thereby ensuring vehicle safety without driver or user intervention. The implementation of redundant components can improve functional safety performance to a certain extent. However, on the one hand, blindly adding redundant components will lead to increased costs and vehicle weight; on the other hand, the implementation of redundant components cannot effectively prevent common cause failures.

[0004] Therefore, how to improve the functional safety performance of autonomous driving has become an urgent problem to be solved. Summary of the Invention

[0005] The present application provides a control method and device, which enables the vehicle to remain in a controlled state without human intervention when the autonomous driving function is not in a valid output state (for example, the autonomous driving domain controller is down, or the communication line transmitting the output of the autonomous driving controller is faulty), thereby avoiding safety risks caused by vehicle loss of control and improving vehicle driving safety.

[0006] On the first aspect, a control method is provided, which can be executed by a control device of an autonomous driving system (such as an autonomous driving domain controller) or a component used for the control device (such as a chip, a chip system, a processing unit or a processing circuit), or can also be executed by a system or vehicle equipped with the control device, which is not limited in this application.

[0007] The method includes: when the vehicle is in an automatic driving state, obtaining environmental information about the vehicle's surroundings; sending vehicle control instructions based on the environmental information, the vehicle control instructions including passage instruction information and safe parking instruction information, wherein the passage instruction information indicates: when the automatic driving function is in an effective output state, the target position of the vehicle during driving; the safe parking instruction information indicates: when the automatic driving function is not in an effective output state, the target position of the vehicle during parking.

[0008] In actual scenarios, for communication networks and control devices in autonomous driving systems, blindly adding redundant components will lead to increased costs and vehicle weight. Even if redundant components are installed, common cause failures caused by failures of products from the same manufacturer, type, or batch, ambient temperature, humidity, and dust in the environment are difficult to completely eliminate. For other systems (such as braking systems, steering systems, etc.) or control devices downstream of the autonomous driving system, when the control device in the autonomous driving system (such as the autonomous driving domain controller) goes down or the communication network that transmits vehicle control commands fails, it will be unable to receive / detect control information from upstream, causing the vehicle in the autonomous driving state to lose control. That is, when the autonomous driving function is not in an effective output state, the vehicle will lose control.

[0009] In this application, because the vehicle control instructions include both pass instruction information and safe parking instruction information, when the autonomous driving function is in an effective output state, the downstream system or control device can use the pass instruction information to control the vehicle's operation; and if a subsequent failure causes the autonomous driving function to be unable to be in an effective output state, the downstream system or control device can control the vehicle to stop according to the previously obtained safe parking instruction information. The safe parking instruction information can provide a safety net for the vehicle when the autonomous driving function is not in an effective output state, preventing the vehicle from being out of control in such situations, avoiding the safety risks caused by the vehicle being out of control, and improving the vehicle's driving safety.

[0010] In conjunction with the first aspect, in certain implementations of the first aspect, the vehicle control command may include a first vehicle control command corresponding to a first detection cycle, and the second detection cycle is after the first detection cycle. When the autonomous driving function is in a valid output state during the first detection cycle, the vehicle operates according to the target posture indicated by the passage instruction information in the first vehicle control command; when the autonomous driving function is not in a valid output state during the second detection cycle, the vehicle operates according to the target posture indicated by the safe parking instruction information in the first vehicle control command.

[0011] In this application, when the automatic driving function is not in a valid output state in the second detection cycle, the system or control device downstream of the automatic driving system can control the vehicle to stop according to the safe parking instruction information in the vehicle control command detected in the first detection cycle, thereby avoiding the safety risks caused by vehicle loss of control.

[0012] In conjunction with the first aspect, in certain implementations of the first aspect, the vehicle is in an autonomous driving state at a first moment, and the vehicle may be in a first lane at the first moment. The vehicle control command corresponds to the first moment, and the target position of the vehicle during parking may include the target position of the vehicle during parking in the first lane.

[0013] In this application, when a sudden fault causes the autonomous driving function to be unable to be in an effective output state, the system or control device downstream of the autonomous driving function can control braking in the current lane until it stops according to the safe parking instruction information obtained before the fault occurs. This can prevent the vehicle from driving into other lanes due to the fault, and can achieve the effect of "giving up speed but not giving up lanes", thereby ensuring the safety of the vehicle.

[0014] In conjunction with the first aspect, in certain implementations of the first aspect, the safe parking instruction information indicates: the target position of the vehicle during parking when the autonomous driving function is not in an effective output state, and may include: a first target driving distance and a first target steering angle of the vehicle at at least one moment when the autonomous driving function is not in an effective output state. The at least one moment includes a second moment, and the second moment is later than the first moment. The first target driving distance at the second moment may include: the distance along the lane direction of the first lane between the target position of the vehicle at the second moment and the position of the vehicle at the first moment when the autonomous driving function is not in an effective output state. The first target steering angle at the second moment may indicate: the target steering angle of the vehicle at the second moment when the autonomous driving function is not in an effective output state.

[0015] In real-world scenarios, there can be a variety of lane types. When parking in a curved lane, in addition to braking, the vehicle also needs to be steered. In this application, the safe parking instruction information can include a first target driving distance and a first target steering angle at at least one moment, thereby indicating the target position of the vehicle during parking. This allows the safe parking instruction information to be applicable to various lane types.

[0016] In combination with the first aspect, in some implementations of the first aspect, the first target steering angle includes at least one of a target steering wheel angle, a target yaw angle, and a target heading angle.

[0017] Since the target yaw angle and target heading angle may need to be further converted into a target steering wheel angle to control vehicle steering, the use of the target steering wheel angle in this application helps reduce the computing power requirements of control devices such as the brake controller and the steering controller.

[0018] Since a vehicle involves multiple different systems such as a braking system and a steering system, in this application, by adopting a target yaw angle or a target heading angle, and indicating a target posture, it is beneficial for different systems to convert them into corresponding control parameters according to their respective needs.

[0019] In conjunction with the first aspect, in certain implementations of the first aspect, the first target steering angle includes a target yaw angle or a target heading angle, and the safe parking instruction information may further include a target posture of the vehicle at at least one moment in time. The target steering wheel angle of the vehicle at a second moment in time is determined based on the target posture at the second moment in time, the first steering angle at the second moment in time, and the real-time posture of the vehicle.

[0020] In conjunction with the first aspect, in certain implementations of the first aspect, the safe parking instruction information may include a first target stopping distance. The first target stopping distance may include: the distance between the vehicle's position at a first moment and the vehicle's target parking position within the first lane when the autonomous driving function is not in an effective output state. The method may further include: determining the first target stopping distance based on environmental information.

[0021] In real-world scenarios, there may be obstacles or dead-end roads ahead of the vehicle. In this application, determining the first target stopping distance based on environmental information helps the vehicle park within the parking distance allowed by the surrounding environment, reducing the risk of collision with obstacles during parking.

[0022] In combination with the first aspect, in certain implementations of the first aspect, the method may further include: determining, based on the first target stopping distance and the braking capability of the vehicle, an initial parking speed limit allowed for the vehicle to park within the first stopping distance; and when the vehicle speed at the first moment is greater than or equal to the initial parking speed limit, controlling the vehicle to decelerate.

[0023] In this application, by comparing the vehicle's speed with the initial parking speed limit allowed for stopping within the first target stopping distance, the vehicle can be decelerated in advance when the vehicle speed is high. This approach ensures that even in the event of a sudden failure such as a sudden crash of the autonomous driving domain controller, the vehicle can still be parked within the first target stopping distance, ensuring vehicle safety.

[0024] In combination with the first aspect, in certain implementations of the first aspect, the autonomous driving function is not in a valid output state, including at least one of the following: the autonomous driving domain controller is in a down state, the communication network used to transmit the output of the autonomous driving function is in a faulty state, or the autonomous driving controller sends a first request message, and the first request message is used to request control of the vehicle to stop.

[0025] In a second aspect, a control method is provided. This method can be executed by a control device outside of an autonomous driving system, such as a braking system control device, a steering system control device, or a vehicle control unit. Alternatively, the method can be executed by a component (such as a chip or chip system) or unit of the aforementioned control device, or by a computing platform or vehicle equipped with the control device, which is not limited in this application.

[0026] The method includes: obtaining a vehicle control instruction, the vehicle control instruction including passage instruction information and safe parking instruction information, wherein the passage instruction information indicates: when the automatic driving function is in a valid output state, the target position of the vehicle during driving; the safe parking instruction information indicates: when the automatic driving function is not in a valid output state, the target position of the vehicle during parking; and controlling the operation of the vehicle according to the vehicle control instruction.

[0027] In conjunction with the second aspect, in certain implementations of the second aspect, the vehicle control instruction may include a first vehicle control instruction corresponding to a first detection cycle, and the second detection cycle is after the first detection cycle. During the second detection cycle, the autonomous driving function is not in a valid output state, which may include: not detecting the vehicle control instruction corresponding to the second detection cycle in the second detection cycle, or detecting first request information in the second cycle, the first request information being used to request control of the vehicle to stop. Controlling vehicle operation according to the vehicle control instruction may include: when the autonomous driving function is not in a valid output state in the second detection cycle, controlling the vehicle to stop according to safe parking instruction information in the first vehicle control instruction.

[0028] In combination with the second aspect, in certain implementations of the second aspect, the vehicle is in an automatic driving state at a first moment, the vehicle may be in a first lane at the first moment, the vehicle control instruction corresponds to the first moment, and the target posture of the vehicle during parking may include the target posture of the vehicle during parking in the first lane.

[0029] In conjunction with the second aspect, in certain implementations of the second aspect, the safe parking instruction information indicates: the target position of the vehicle during parking when the autonomous driving function is not in an effective output state, which may include: the first target driving distance of the vehicle at at least one moment and the first target steering angle at at least one moment when the autonomous driving function is not in an effective output state. The at least one moment includes a second moment, and the second moment is later than the first moment. The first target driving distance at the second moment may include: the distance along the lane direction of the first lane between the target position of the vehicle at the second moment and the position of the vehicle at the first moment when the autonomous driving function is not in an effective output state. The first target steering angle at the second moment may indicate: the target steering angle of the vehicle at the second moment when the autonomous driving function is not in an effective output state.

[0030] In combination with the second aspect, in some implementations of the second aspect, the first target steering angle includes at least one of a target steering wheel angle, a target yaw angle, and a target heading angle.

[0031] In conjunction with the second aspect, in certain implementations of the second aspect, the first target steering angle includes a target yaw angle or a target heading angle, and the safe parking instruction information also includes a target posture of the vehicle at at least one moment. The method may further include determining a target steering wheel angle of the vehicle at the second moment based on the target posture at the second moment, the first target steering angle at the second moment, and the real-time posture of the vehicle.

[0032] In combination with the second aspect, in certain implementations of the second aspect, the method may further include: when the automatic driving function is not in a valid output state, determining the target driving distance and the first target deceleration of the vehicle between the first control node and the second control node based on the first vehicle speed of the vehicle at the first control node, the second control node being later than the first control node.

[0033] In real-world scenarios, failures such as autonomous driving domain controller downtime and communication network failures that prevent autonomous driving functions from operating effectively are sporadic. In most autonomous driving scenarios, since these failures are not involved, the safe stop instruction information may simply serve as a safety net for the vehicle, rather than controlling the vehicle's parking. When the number of target poses involved in the safe stop instruction information is large, it will consume significant communication resources, but in most scenarios, these target poses are not used to control vehicle operation.

[0034] In this application, when the automatic driving function is not in an effective output state, the target braking deceleration and target driving distance before the next control node are determined based on the vehicle speed at the current control node, so that the safe parking instruction information only indicates part of the posture to realize the downstream control device's braking control during the parking process, which is beneficial to reducing the occupation of communication resources by the safe parking instruction information.

[0035] In conjunction with the second aspect, in certain implementations of the second aspect, the second control node is between the first control node and the second moment. The method may further include: determining a first target steering angle of the vehicle at the second control node based on the first target driving distance at the second moment, the first target steering angle at the second moment, the position of the vehicle at the first control node, and the target driving distance of the vehicle between the first control node and the second control node.

[0036] In the present application, when the automatic driving function is not in an effective output state, the target steering angle of the vehicle at the next control node can be determined based on the target posture indicated by the safe parking instruction information and the position of the vehicle at the current node, so that the safe parking instruction information only indicates part of the target posture to enable the downstream control device to control the steering during the parking process, which is beneficial to reducing the occupation of communication resources by the safe parking instruction information.

[0037] In combination with the second aspect, in certain implementations of the second aspect, the position of the vehicle at the first control node is determined based on vehicle speed and posture change information of the vehicle between the first moment and the first control node.

[0038] In combination with the second aspect, in certain implementations of the second aspect, the method may further include: determining a first steering limit based on a first vehicle speed at a first control node, the first steering limit including a limit on a target steering angle allowed for stable driving of the vehicle at the first speed; when the first target steering angle at the second control node is less than the first steering limit, determining the first target steering angle as the target steering angle of the second control node, and controlling the steering of the vehicle; or, when the first target steering angle at the second control node is greater than or equal to the first steering limit, determining the first steering limit as the target steering angle of the second control node, and controlling the steering of the vehicle.

[0039] In this application, constraining the target steering angle of the next control node according to the vehicle speed at the current control node can reduce the risk of vehicle instability during the steering process.

[0040] In combination with the second aspect, in certain implementations of the second aspect, the method may further include: determining a first deceleration limit based on the maximum target steering angle of the vehicle between the first control node and the second control node, the first deceleration limit may include a limit on the target braking deceleration allowed for the vehicle to travel stably at the maximum target steering angle; when the first target deceleration is less than the first deceleration limit, using the first target deceleration as the target braking deceleration between the first control node and the second control node, and controlling vehicle braking; or, when the first target deceleration is greater than or equal to the first deceleration limit, using the first deceleration limit as the target braking deceleration between the first control node and the second control node, and controlling vehicle braking.

[0041] In this application, the target braking deceleration within the time period is constrained based on the target steering angle of the vehicle at the current control node and the next control node, which can reduce the risk of instability caused by braking with a large deceleration during the steering process.

[0042] In combination with the second aspect, in certain implementations of the second aspect, the autonomous driving function is not in a valid output state, including at least one of the following: the autonomous driving domain controller is in a down state, the communication network used to transmit the output of the autonomous driving function is in a faulty state, or the autonomous driving controller sends a first request message, and the first request message is used to request control of the vehicle to stop.

[0043] In a third aspect, a control device is provided. The control device may include an acquisition unit and a processing unit. The acquisition unit may be configured to acquire environmental information surrounding the vehicle when the vehicle is in an autonomous driving state. The processing unit may be configured to issue vehicle control commands based on the environmental information. The vehicle control commands may include passage instructions and safe parking instructions.

[0044] In conjunction with the third aspect, in certain implementations of the third aspect, the safe parking instruction information may include a first target parking distance. The processing unit may also be configured to: determine the first target parking distance based on the environmental information.

[0045] In combination with the third aspect, in certain implementations of the third aspect, the processing unit may further be configured to: determine, based on the first target stopping distance and the braking capability of the vehicle, an initial parking speed limit allowed for the vehicle to be parked within the first stopping distance; and control the vehicle to decelerate when the vehicle speed at the first moment is greater than or equal to the initial parking speed limit.

[0046] In a fourth aspect, a control device is provided. The control device may include an acquisition unit and a processing unit. The acquisition unit may be configured to acquire vehicle control instructions, including passage instruction information and safe parking instruction information. The processing unit may be configured to control vehicle operation according to the vehicle control instructions.

[0047] In conjunction with the fourth aspect, in certain implementations of the fourth aspect, the vehicle control command may include a first vehicle control command corresponding to the first detection period, and the second detection period is after the first detection period. The processing unit may be configured to, when the autonomous driving function is not in a valid output state in the second detection period, control the vehicle to stop according to the safe parking instruction information in the first vehicle control command.

[0048] In combination with the fourth aspect, in certain implementations of the fourth aspect, the processing unit may also be used to: when the automatic driving function is not in a valid output state, determine the target driving distance and the first target deceleration of the vehicle between the first control node and the second control node based on the first vehicle speed of the vehicle at the first control node, the second control node being later than the first control node.

[0049] In conjunction with the fourth aspect, in certain implementations of the fourth aspect, the second control node is between the first control node and the second moment. The processing unit may be further configured to determine a first target steering angle for the vehicle at the second control node based on the first target driving distance at the second moment, the first target steering angle at the second moment, the position of the vehicle at the first control node, and the target driving distance between the first and second control nodes.

[0050] In combination with the fourth aspect, in certain implementations of the fourth aspect, the processing unit may also be used to determine the position of the vehicle at the first control node based on the vehicle speed and posture change information between the vehicle at the first moment and the first control node.

[0051] In combination with the fourth aspect, in certain implementations of the fourth aspect, the processing unit can also be used to: determine a first steering limit based on the first speed of the vehicle at the first control node, the first steering limit including the limit of the target steering angle allowed for the vehicle to travel stably at the first speed; when the first target steering angle at the second control node is less than the first steering limit, determine the first target steering angle as the target steering angle of the second control node, and control the steering of the vehicle; or, when the first target steering angle of the second control node is greater than or equal to the first steering limit, determine the first steering limit as the target steering angle of the second control node, and control the steering of the vehicle.

[0052] In combination with the fourth aspect, in certain implementations of the fourth aspect, the processing unit may also be used to: determine a first deceleration limit based on the maximum target steering angle of the vehicle between the first control node and the second control node, where the first deceleration limit may include a limit on the target braking deceleration allowed for stable driving of the vehicle at the maximum target steering angle; when the first target deceleration is less than the first deceleration limit, use the first target deceleration as the target braking deceleration between the first control node and the second control node, and control vehicle braking; or, when the first target deceleration is greater than or equal to the first deceleration limit, use the first deceleration limit as the target braking deceleration between the first control node and the second control node, and control vehicle braking.

[0053] In a fifth aspect, a control device is provided, which includes: a memory for storing a computer program; and a processor for executing the computer program stored in the memory, so that the device executes the method in the above-mentioned first aspect and any possible implementation thereof.

[0054] In a sixth aspect, a control device is provided, which includes: a memory for storing a computer program; and a processor for executing the computer program stored in the memory, so that the device executes the method in the above-mentioned second aspect and any possible implementation thereof.

[0055] In a seventh aspect, a system is provided, comprising a first control device and a second control device. The first control device may include the device of the third aspect or the fifth aspect, and any possible implementation thereof. The second control device may include the device of the fourth aspect or the sixth aspect, and any possible implementation thereof.

[0056] In an eighth aspect, a method is provided, which includes: when a vehicle is in an automatic driving state, a first control device obtains environmental information around the vehicle; the first control device sends a vehicle control instruction based on the environmental information, wherein the passage indication information indicates: when the automatic driving function is in an effective output state, the target position of the vehicle during driving; the safe parking indication information indicates: when the automatic driving function is not in an effective output state, the target position of the vehicle during parking; a second control device obtains the vehicle control instruction; and the second control device controls the vehicle operation according to the vehicle control instruction.

[0057] In conjunction with the eighth aspect, in certain implementations of the eighth aspect, the vehicle control command may include a first vehicle control command corresponding to a first detection period, and the second detection period is after the first detection period. The second control device controlling the operation of the vehicle according to the vehicle control command may include: when the automatic driving function is in a valid output state in the first detection period, the second control device controlling the operation of the vehicle according to the passage instruction information in the first vehicle control command; when the automatic driving function is not in a valid output state in the second detection period, the second control device controlling the vehicle to stop according to the safe parking instruction information in the first vehicle control command.

[0058] Exemplarily, in the second detection cycle, the automatic driving function is not in a valid output state, which may include: no vehicle control instruction corresponding to the second detection cycle is detected in the second detection cycle, or, first request information is detected in the second cycle, and the first request information is used to request control of the vehicle to stop.

[0059] In combination with the eighth aspect, in certain implementations of the eighth aspect, the vehicle is in an automatic driving state at a first moment, the vehicle may be in a first lane at the first moment, the vehicle control instruction corresponds to the first moment, and the target posture of the vehicle during parking may include the target posture of the vehicle during parking in the first lane.

[0060] In conjunction with the eighth aspect, in certain implementations of the eighth aspect, the safe parking instruction information indicates: the target position of the vehicle during parking when the autonomous driving function is not in a valid output state, which may include: the first target driving distance of the vehicle at at least one moment and the first target steering angle at at least one moment when the autonomous driving function is not in a valid output state. The at least one moment includes a second moment, and the second moment is later than the first moment. The first target driving distance at the second moment may include: the distance along the lane direction of the first lane between the target position of the vehicle at the second moment and the position of the vehicle at the first moment when the autonomous driving function is not in a valid output state. The first target steering angle at the second moment may indicate: the target steering angle of the vehicle at the second moment when the autonomous driving function is not in a valid output state.

[0061] In combination with the eighth aspect, in certain implementations of the eighth aspect, the first target steering angle includes at least one of a target steering wheel angle, a target yaw angle, and a target heading angle.

[0062] In conjunction with the eighth aspect, in certain implementations of the eighth aspect, the first target steering angle includes a target yaw angle or a target heading angle, and the safe parking instruction information further includes a target posture of the vehicle at at least one moment. The method may further include: a second control device determining a target steering wheel angle of the vehicle at the second moment based on the target posture at the second moment, the first target steering angle at the second moment, and the real-time posture of the vehicle.

[0063] In conjunction with the eighth aspect, in certain implementations of the eighth aspect, the safe parking instruction information may include a first target parking distance. The first target parking distance may include: the distance between the vehicle's position at a first moment and the vehicle's target parking position within the first lane when the autonomous driving function is not in an effective output state. The method may further include: the first control device determining the first target parking distance based on environmental information.

[0064] In combination with the eighth aspect, in certain implementations of the eighth aspect, the method may further include: a first control device determines an initial parking speed limit allowed for the vehicle to park within the first stopping distance based on the first target stopping distance and the braking capacity of the vehicle; when the vehicle speed at the first moment is greater than or equal to the initial parking speed limit, controlling the vehicle to decelerate.

[0065] In combination with the eighth aspect, in certain implementations of the eighth aspect, the method may further include: when the automatic driving function is not in a valid output state, the second control device determines the target driving distance and the first target deceleration of the vehicle between the first control node and the second control node based on the first vehicle speed of the vehicle at the first control node, and the second control node is later than the first control node.

[0066] In conjunction with the eighth aspect, in certain implementations of the eighth aspect, the second control node is between the first control node and the second moment. The method may further include: the second control device determining the first target steering angle of the vehicle at the second control node based on the first target driving distance at the second moment, the first target steering angle at the second moment, the position of the vehicle at the first control node, and the target driving distance of the vehicle between the first control node and the second control node.

[0067] In combination with the eighth aspect, in certain implementations of the eighth aspect, the method may further include: a second control device determines a first steering limit based on a first vehicle speed at a first control node, the first steering limit including a limit on a target steering angle allowed for stable driving of the vehicle at the first speed; when the first target steering angle at the second control node is less than the first steering limit, the first target steering angle is determined as the target steering angle of the second control node, and the vehicle steering is controlled; or, when the first target steering angle at the second control node is greater than or equal to the first steering limit, the first steering limit is determined as the target steering angle of the second control node, and the vehicle steering is controlled.

[0068] In combination with the eighth aspect, in certain implementations of the eighth aspect, the method may further include: a second control device determines a first deceleration limit based on the maximum target steering angle of the vehicle between the first control node and the second control node, and the first deceleration limit may include a limit on the target braking deceleration allowed for the vehicle to travel stably at the maximum target steering angle; when the first target deceleration is less than the first deceleration limit, the first target deceleration is used as the target braking deceleration between the first control node and the second control node, and the vehicle braking is controlled; or, when the first target deceleration is greater than or equal to the first deceleration limit, the first deceleration limit is used as the target braking deceleration between the first control node and the second control node, and the vehicle braking is controlled.

[0069] In combination with the eighth aspect, in certain implementations of the eighth aspect, the method may further include: the autonomous driving function is not in a valid output state, including at least one of the following: the autonomous driving domain controller is in a down state, the communication network used to transmit the output of the autonomous driving function is in a faulty state, or the autonomous driving controller sends a first request message, and the first request message is used to request control of the vehicle to stop.

[0070] In the ninth aspect, a computer program product is provided, which includes: computer program code, which, when the computer program code is run on a computer, enables the computer to execute the method in the first aspect, the second aspect or the eighth aspect and any possible implementation thereof.

[0071] In the tenth aspect, a computer-readable storage medium is provided, wherein the computer-readable medium stores a computer program. When the computer program runs on a computer, the computer executes the method in the first aspect, the second aspect or the eighth aspect and any possible implementation thereof.

[0072] In the eleventh aspect, a chip is provided, which includes a circuit for executing the method in the above-mentioned first aspect, second aspect or eighth aspect and any possible implementation manner thereof.

[0073] In the twelfth aspect, a vehicle is provided, which includes the device of the third aspect, fourth aspect, fifth aspect or sixth aspect and any possible implementation thereof, or includes a system of the seventh aspect and any possible implementation thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] FIG1 is a functional block diagram of an intelligent driving device 100 provided in an embodiment of the present application;

[0075] FIG2 is a schematic diagram of a system architecture provided in an embodiment of the present application;

[0076] FIG3 is a schematic diagram of a control method provided in an embodiment of the present application;

[0077] FIG4 is a schematic diagram of another control method provided in an embodiment of the present application;

[0078] FIG5 is a schematic diagram of a vehicle driving scenario provided by an embodiment of the present application;

[0079] FIG6 is a schematic diagram of target driving distances and target steering wheel angles at various moments in a safe parking scenario provided by an embodiment of the present application;

[0080] FIG7 is a schematic diagram of another system architecture provided in an embodiment of the present application;

[0081] FIG8 is a schematic diagram of another system architecture provided in an embodiment of the present application;

[0082] FIG9 is a schematic diagram of another system architecture provided in an embodiment of the present application;

[0083] FIG10 is a schematic block diagram of a device provided in an embodiment of the present application;

[0084] FIG11 is a schematic block diagram of another device provided in an embodiment of the present application;

[0085] FIG12 is a schematic block diagram of another device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0086] The technical solution in this application will be described below with reference to the accompanying drawings.

[0087] Figure 1 is a functional block diagram of an intelligent driving device 100 provided in an embodiment of the present application. The intelligent driving device 100 may include a perception system 120 and a computing platform 150, wherein the perception system 120 may include one or more sensors for sensing environmental information about the surroundings of the intelligent driving device 100. For example, the perception system 120 may include a positioning system, which may be a global positioning system (GPS), a Beidou system, or other positioning systems. The perception system 120 may also include an inertial measurement unit (IMU), one or more of a laser radar, a millimeter-wave radar, an ultrasonic radar, and a camera device.

[0088] Some or all functions of the intelligent driving device 100 can be controlled by the computing platform 150. The computing platform 150 may include one or more processors, such as processors 151 to 15n (n is a positive integer). A processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction reading and execution capabilities, such as a central processing unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), or a digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. The logical relationships of the hardware circuits are fixed or reconfigurable. For example, the processor is a hardware circuit implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as a field programmable gate array (FPGA). In a reconfigurable hardware circuit, the process of the processor loading a configuration file to implement the hardware circuit configuration can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), a tensor processing unit (TPU), a deep learning processing unit (DPU), etc. In addition, the computing platform 150 can also include a memory for storing instructions, and some or all of the processors 151 to 15n can call the instructions in the memory to implement corresponding functions.

[0089] With the development of intelligent driving technology, vehicles are gradually evolving from purely manual driving modes to autonomous driving modes. Current and future vehicles may include one or more autonomous driving levels L0-L5. The above autonomous driving levels (L0-L5) are based on the grading standards of the Society of Automotive Engineers (SAE). Among them, L0 is no automation; L1 is driving assistance; L2 is partial automation; L3 is conditional automation; L4 is high automation; and L5 is full automation. The tasks of monitoring road conditions and responding to L1 to L3 can be completed by the driver and the system together, and the driver is required to take over dynamic driving tasks. L4 and L5 allow the driver to completely transform into the role of a passenger. For example, through the computing platform 150 (or some processors in the computing platform 150) and the perception system 120, the intelligent driving device 100 can achieve the corresponding level of autonomous driving functions.

[0090] To meet the demands of autonomous driving, vehicle system complexity continues to increase, leading to an increasing risk of system failures and random hardware failures. To address these risks, it's crucial to focus on the post-failure behavior of each vehicle system and hardware to avoid unacceptable risks resulting from functional safety failures, a key component of functional safety.

[0091] Vehicles capable of achieving high-level autonomous driving (e.g., L3 and above) often need to be able to cope with safety risks caused by abnormalities in various systems / components while in autonomous driving mode, thereby ensuring vehicle driving safety without driver or user intervention. For example, assuming that the perception system 120 and the computing platform 150 are used to implement the autonomous driving function, during the use of the autonomous driving function, the intelligent driving device 100 needs to be able to cope with safety risks caused by failures in the perception system 120 and / or the computing platform 150.

[0092] For example, based on the failure mode, the failure / failure mode of each system and component can be divided into software failure and hardware failure. By setting up redundant components in the system, unexpected risks caused by single point failure can be avoided.

[0093] However, in real-world scenarios, adding redundant components is difficult to completely eliminate common cause failures. For example, assume the control device in an autonomous driving system includes processing unit #1 and processing unit #2. Processing unit #2 can serve as a redundant component for processing unit #1, assuming it can perform some or all of its functions in the event of a failure. Because processing unit #1 and processing unit #2 are located in the same control device, they are subject to the same physical environment, including ambient temperature, humidity, and dust. Common cause failures caused by this physical environment are difficult to effectively prevent. For another example, assume a vehicle is equipped with communication network #1 and communication network #2. During normal operation, communication network #1 can be used to enable communication between the control device in the autonomous driving system and the control devices in other systems (e.g., the braking system or steering system). Communication network #2 can serve as a redundant component for communication network #1. In real-world scenarios, communication network #1 and communication network #2 may utilize the same wiring harness, connectors, and other components from the same batch or type. Therefore, common cause failures caused by these wiring harnesses and connectors are difficult to completely eliminate. Furthermore, blindly adding redundant components will negatively impact the cost and weight of the vehicle.

[0094] In view of this, the embodiments of the present application provide a control method and a control device, which enable the vehicle to remain in a controlled state without human intervention when the autonomous driving function is not in a valid output state (for example, the autonomous driving domain controller is down, or the communication line transmitting the output of the autonomous driving controller is faulty), thereby avoiding safety risks caused by vehicle loss of control and improving vehicle driving safety.

[0095] For example, FIG2 is a schematic diagram of a system architecture provided by an embodiment of the present application. As shown in FIG2 , a system 200 may include multiple control devices, such as a control device 210 , a control device 220 , and a control device 230 .

[0096] The control device 210 can plan the vehicle's driving path based on data collected by perception sensors (e.g., cameras, millimeter-wave radar, lidar, or inertial measurement units) and control the vehicle to travel along the planned path. The control device 210 may include a main processing unit 211. For example, the main processing unit 211 can be used to determine the distance between the vehicle and surrounding obstacles based on the data collected by the perception sensors. For another example, the main processing unit 211 can be used to plan the vehicle's driving path.

[0097] In some possible implementations, redundant components may be provided in one or more control devices involved in the system architecture 200. For example, the control device 210 may further include a redundant processing unit 212. The redundant processing unit 212 may be configured to perform some or all of the functions of the main processing unit 211 in the event of a failure of the main processing unit 211.

[0098] In one embodiment, control device 210 can be understood as a control device in an autonomous driving system. For example, control device 210 may include an autonomous driving domain controller. Main processing unit 211 may include a main processing circuit, a main processor, or a main computing unit in the autonomous driving domain controller; correspondingly, redundant processing unit 212 may include a redundant processing circuit, a redundant processor, or a redundant computing unit in the autonomous driving domain controller.

[0099] For example, control devices 220 and 230 may be control devices in systems other than the autonomous driving system (e.g., a braking system, a steering system, etc.). Control device 220 may include a main processing unit 221, and control device 230 may include a main processing unit 231. For example, main processing units 221 and 231 may be used to control the actuation of actuators in the corresponding systems.

[0100] In some possible implementations, the control device 220 may further include a redundant processing unit 222, and / or the control device 230 may further include a redundant processing unit 232. The redundant processing units 222 and 232 may be respectively configured to implement part or all of the functions of the main processing units 221 and 231 when the main processing units 221 and 231 fail.

[0101] In one embodiment, the control device 220 can be used to control the actuation of actuators in the braking system. For example, taking a hydraulic braking system as an example, when the main processing unit 221 operates normally, it can control the actuation of the motor and control valve in the braking system to adjust the pressure of the brake fluid in the hydraulic pipeline. When the main processing unit 221 fails, the redundant processing unit 222 can control the actuation of actuators such as motors and control valves, and can realize part or all of the functions of the main processing unit 221. For another example, the control device 220 may include a brake controller, and the brake controller may control the actuation of an electronic brake system (EBS). In this scenario, the main processing unit 221 may include a main processing unit, a main processing circuit, etc. in the brake controller; the redundant processing unit 222 may include a redundant processing unit, a redundant processing circuit, etc. in the brake controller.

[0102] In another embodiment, the control device 230 can be used to control the actuation of the actuator (such as a steering motor, etc.) in the steering system. For example, taking electric power steering (EPS) as an example, the control device 230 may include a steering controller. The main processing unit 231 may include a main processing unit, a main processing circuit, etc. in the steering controller; the redundant processing unit 232 may include a redundant processing unit, a redundant processing circuit, etc. in the steering controller. For example, when the main control unit 231 operates normally, the actuator actuation in the EPS can be controlled according to the request or instruction of the autonomous driving domain controller to achieve vehicle steering. When the main control unit 231 fails, the redundant control unit 232 can be used to control the actuator actuation in the steering system, and can achieve part or all of the functions of the main control unit 231.

[0103] In some possible implementations, the system architecture 200 may further include more or fewer control devices. For example, the system 200 may further include a power system control device. For another example, the system 200 may further include a vehicle control unit (VCU).

[0104] For example, as shown in FIG2 , system 200 may further include a communication network 241. Communication network 241 may be used to enable communication between different control devices. For example, communication network 241 may include a communication line between control devices 210 and 220, and may also include a communication line between control devices 210 and 230. For another example, a communication line may be provided between control devices 220 and 230. In some possible implementations, different communication lines may share some wiring harnesses.

[0105] In one embodiment, as shown in FIG2 , the system 200 may further include a communication network 242. The communication network 242 may be used to implement part or all of the functions of the communication network 241 when the communication network 241 fails. The communication network 241 may also be referred to as the primary communication network 241, and the communication network 242 may also be referred to as the redundant communication network 242. For example, when the communication line between the control devices 210 and 220 in the communication network 241 fails, the communication between the two control devices may be implemented by the communication line between the control devices 210 and 220 in the communication network 242. For another example, when in an automatic driving state, the control device 210 may send a vehicle control command, and the control device 220 and / or the control device 230 may control the corresponding system and the execution device according to the vehicle control command.

[0106] For example, Figure 3 is a schematic diagram of a control method provided in an embodiment of the present application. The following is an exemplary description of the control device of the autonomous driving system (such as the control device 210) as the execution subject of the method 300. In some possible implementations, the execution subject of the method 300 may be a component of the control device 210 (such as a chip, a processor, or a processing circuit), or the execution subject may be a system or vehicle equipped with the control device 210, which is not limited in this embodiment of the present application. The method 300 may include steps S310 and S320.

[0107] S310, when the vehicle is in an automatic driving state, obtaining environmental information around the vehicle.

[0108] In one embodiment, the path and target position of the vehicle during driving in an automatic driving state can be planned based on the surrounding environment information.

[0109] In another embodiment, based on the surrounding environment information, a target parking position allowed for the vehicle to park in the current lane can be determined; and the distance between the target parking position and the current position of the vehicle along the lane direction can be determined.

[0110] S320: Send a vehicle control instruction based on the environmental information.

[0111] Accordingly, control devices of other systems (such as a braking system and a steering system), such as the control device 220 , the control device 230 , and the VCU, can obtain the vehicle control instruction.

[0112] Exemplarily, the vehicle control command includes passage instruction information and safe parking instruction information. The passage instruction information may indicate the target position of the vehicle during driving when the autonomous driving function is in an effective output state. The safe parking instruction information may indicate the target position of the vehicle during parking when the autonomous driving function is not in an effective output state.

[0113] In one embodiment, the control device 210 may send a message to another control device based on a communication protocol. The vehicle control instructions may be carried in the message. For example, a frame of the message sent by the control device 210 may include passage instruction information and safe parking instruction information.

[0114] In some possible implementations, control device 210 may periodically send vehicle control commands. Other control devices in system 200 (e.g., control devices 220, 230, and the VCU) may detect whether they have received the corresponding periodic vehicle control commands. Based on whether the vehicle control commands are detected, it can be determined whether the autonomous driving function is in a valid output state.

[0115] For example, when a vehicle control command is detected, it can be considered that the automatic driving function is in a valid output state.

[0116] In one embodiment, if no vehicle control command is detected, the autonomous driving function may be deemed to be in an inactive output state. For example, if control device 220 suddenly crashes and is unable to send a vehicle control command, control devices 220 and 230 will be unable to detect the vehicle control command at the corresponding time. For another example, if the communication line between control device 210 and control device 220 fails in the communication network, even if control device 210 periodically sends a vehicle control command, control device 220 may not be able to detect the corresponding vehicle control command.

[0117] In another embodiment, to reduce misjudgments, if no vehicle control command is detected for p consecutive cycles (e.g., 3 or 5 cycles), the autonomous driving function may be considered to be in an invalid output state. Where p is a positive integer. In actual scenarios, the value of p can be set according to specific needs.

[0118] In another embodiment, when the communication line between the control device 210 and the control device 220 fails, the control device 210 may send a first request message to other control devices (such as the control device 230 or the VCU) to request control of the vehicle to stop.

[0119] In some possible implementations, the vehicle control command may include a first vehicle control command corresponding to a first detection cycle. When the autonomous driving function is in a valid output state during the first detection cycle, the vehicle operates according to the passage instruction information in the first vehicle control command. When the autonomous driving function is not in a valid output state during a second detection cycle, the vehicle operates according to the safe parking instruction information in the first vehicle control command. The second detection cycle occurs after the first detection cycle.

[0120] For example, assuming that control device 210 is an autonomous driving domain controller and control device 220 is a brake controller, and the autonomous driving domain controller periodically sends vehicle control commands, it should send vehicle control commands #1 to #5 at the times corresponding to cycles #1 to #5, respectively. If the brake controller detects vehicle control command #1 during cycle #1, it can control the brake system based on the traffic indication information in vehicle control command #1. If it detects vehicle control command #2 during cycle #2, it can control the brake system based on the traffic indication information in vehicle control command #2.

[0121] In one embodiment, if the brake controller fails to detect a vehicle control command during cycle #3 due to a crash of the autonomous driving domain controller or a communication network failure, the autonomous driving function may be deemed inactive and the vehicle may be stopped according to the safe stop instruction in vehicle control command #2. In this scenario, cycle #2 may correspond to the first detection cycle, and cycle #3 may correspond to the second detection cycle.

[0122] In another embodiment, the autonomous driving function is considered inactive only when the vehicle control command is not detected for multiple consecutive detection cycles (e.g., two). For example, if the brake controller fails to detect the vehicle control command in cycles #3 and #4, the autonomous driving function may be considered inactive and the vehicle may be stopped according to the safe stop instruction information in vehicle control command #2. In this scenario, cycle #2 may correspond to the first detection cycle, and cycle #4 may correspond to the second detection cycle.

[0123] In some possible implementations, the vehicle is in an automatic driving state at a first moment, and the vehicle is in a first lane at the first moment. The vehicle control instruction may correspond to the first moment, and the target posture indicated by the safe parking instruction information contained in the vehicle control instruction may include the target posture of the vehicle during the parking process in the first lane. For example, assume that when the control device 210 generates vehicle control instruction #2 or sends vehicle control instruction #2, the vehicle is in lane #1. In this case, the safe parking instruction information contained in vehicle control instruction #2 may indicate the target posture of the vehicle during the parking process in lane #1. When the vehicle is controlled to stop according to the safe parking instruction information in vehicle control instruction #2, the vehicle will brake in lane #1 until it stops.

[0124] In an embodiment of the present application, when the automatic driving function is not in an effective output state, by controlling the vehicle to brake in the first lane until it stops, the vehicle can be prevented from driving into other lanes due to loss of control. The vehicle can achieve the effect of "giving up speed but not giving up lanes" when the automatic driving function is not in an effective output state, thereby ensuring the safety of the vehicle.

[0125] In some possible implementations, the safe parking indication information may include: a first target driving distance and a first target steering angle of the vehicle at at least one moment when the autonomous driving function is not in a valid output state. The at least one moment includes a second moment, and the second moment is later than the first moment. The first target driving distance at the second moment may include: the distance along the lane direction of the first lane between the target position of the vehicle at the second moment and the position of the vehicle at the first moment when the autonomous driving function is not in a valid output state. The first target steering angle at the second moment may include: the target steering angle of the vehicle at the second moment when the autonomous driving function is not in a valid output state. In other words, the safe parking indication information can indicate the target posture of the vehicle during the parking process by including the first target driving distance and the first target steering angle at at least one moment.

[0126] In one embodiment, the safe stop instruction information contained in the message sent by control device 210 may not include the specific time information of the at least one moment, and may simply include multiple first driving distances and corresponding multiple first steering angles. For example, the multiple first driving distances and multiple first steering angles may be carried in a sequence. After receiving the vehicle control instruction, control devices 220 and 230 may determine the times corresponding to the multiple first driving distances and first steering angles based on a preset period and the order of the data in the sequence. This approach helps reduce the communication resources occupied by vehicle control instructions.

[0127] For example, the first target steering angle may include at least one of a target steering wheel angle, a target yaw angle, and a target heading angle. In other words, the first target steering angle of the vehicle at a corresponding moment may be embodied as at least one of the target steering wheel angle, the target yaw angle, and the target heading angle.

[0128] In one embodiment, the first target steering angle may include a target yaw angle or a target heading angle. The safe parking instruction information may also include: a target position of the vehicle at at least one moment in time when the autonomous driving function is not in an effective output state. When the autonomous driving function is not in an effective output state, the target steering wheel angle of the vehicle at a second moment in time may be determined based on the target position of the vehicle at that second moment in time, the first target steering angle at that second moment in time, and the vehicle's real-time position.

[0129] Since a vehicle involves various systems such as a braking system and a steering system, in the embodiment of the present application, by adopting a target yaw angle or a target heading angle, and indicating a target posture, it is beneficial for different systems to convert them into corresponding control parameters according to their respective needs.

[0130] In yet another embodiment, the first target steering angle may include a target steering wheel angle.

[0131] Since the target yaw angle and target heading angle may need to be further converted into a target steering wheel angle to control vehicle steering, in the embodiment of the present application, the use of the target steering wheel angle helps reduce the computing power requirements of control devices such as the brake controller and the steering controller.

[0132] In some possible implementations, the safe parking instruction information may include a first target stopping distance. This first target stopping distance may include the distance along the first lane between the vehicle's position at a first moment and the vehicle's target stopping position in the first lane when the autonomous driving function is not in an active output state. This first target stopping distance is determined based on information about the vehicle's surrounding environment. For example, if there is an obstacle 80 meters ahead in the current lane, the target stopping position for parking in that lane should be set in front of the obstacle, and the first target driving distance should be less than or equal to 80 meters to avoid collision with the obstacle during parking.

[0133] In some possible implementations, the method may further include: determining, based on the first target stopping distance and the braking capability of the vehicle, an initial parking speed limit allowed for the vehicle to stop within the first target stopping distance; and controlling the vehicle to decelerate when the vehicle speed at the first moment is greater than or equal to the initial parking speed limit.

[0134] In one embodiment, assume that the vehicle's braking capacity is -8 meters per square second (m / s²), and due to factors such as obstacles, the distance between the target parking position in the current lane and the vehicle's current position along the lane is 75 meters. In this scenario, the initial parking speed limit allowed to achieve parking within this distance is approximately 125 kilometers per hour (km / h). When the vehicle's speed exceeds this speed limit, the autonomous driving domain controller can control the vehicle to decelerate.

[0135] In this embodiment of the present application, by comparing the vehicle's speed with the initial parking speed limit allowed for stopping within the first target stopping distance, the vehicle can be decelerated in advance when the vehicle speed is high. This approach ensures that even in the event of a sudden failure such as a sudden crash of the autonomous driving domain controller, the vehicle can still be parked within the first target stopping distance, ensuring vehicle safety.

[0136] For example, FIG4 is a schematic diagram of another control method provided in an embodiment of the present application. The following is an exemplary description using control devices 220 and 230 as the execution subject of method 400. In some possible implementations, the execution subject of the method may be a component of the above-mentioned control device (such as a chip, processor, or processing circuit), or the execution subject may be a system or vehicle equipped with the above-mentioned control device. The method 400 includes steps S410 and S420.

[0137] S410: Obtain vehicle control instructions, which include traffic instruction information and safe parking instruction information.

[0138] For example, for the description of the passage instruction information and the safe parking instruction information, reference may be made to step S320.

[0139] S420: Control the vehicle operation according to the vehicle control instruction.

[0140] In some possible implementations, when in the autonomous driving state, the control device 210 may periodically send vehicle control commands. The control devices 220 and 230 may periodically detect the vehicle control commands. For example, based on whether the vehicle control commands are detected, it may be determined whether the autonomous driving function is in a valid output state.

[0141] For example, the vehicle control command may include a first vehicle control command corresponding to a first detection cycle. The second detection cycle is subsequent to the first detection cycle. When the autonomous driving function is in a valid output state during the first detection cycle, the vehicle may be controlled to travel according to the passage instruction information in the first vehicle control command. When the autonomous driving function is not in a valid output state during the second detection cycle, the vehicle may be controlled to stop according to the safe parking instruction information in the first vehicle control command.

[0142] In some possible implementations, the automatic driving function is not in a valid output state in the second detection cycle, which may include: no vehicle control instruction corresponding to the second detection cycle is detected in the second detection cycle, or, first request information is detected in the second detection cycle, and the first request information is used to request control of the vehicle to stop.

[0143] Regarding whether the automatic driving function is in a valid output state, please refer to the relevant records of method 300.

[0144] In some possible implementations, the safe stop instruction information may include: a first target driving distance and a first target steering angle for the vehicle at at least one time point when the autonomous driving function is not in an effective output state. For a description of the first target driving distance and the first target steering angle, refer to the relevant description of method 300.

[0145] In real-world scenarios, failures such as autonomous driving domain controller downtime and communication network failures that prevent the autonomous driving function from being in an effective output state are sporadic. That is, the vehicle will only be stopped according to the safe stop instruction information when a failure occurs that prevents the autonomous driving function from being in an effective output state. However, in most autonomous driving scenarios, since these failures are not involved, the safe stop instruction information may only serve as a safety net for the vehicle's safety, and the vehicle will not be stopped according to the safe stop instruction information. When the number of target postures involved in the safe stop instruction information is large, the safe stop instruction information will occupy a large amount of communication resources, but in most scenarios, these target postures are not used to control the operation of the vehicle.

[0146] In some possible implementations, in order to reduce the communication resources occupied by the vehicle control instructions, the number of target postures during the parking process indicated by the safe parking instruction information may be less than or equal to a preset value.

[0147] For example, the number of target positions indicated by the safe parking instruction information may not match the number of control nodes involved in controlling the parking of the vehicle by the control devices 220 and 230. For example, the safe parking instruction information only includes the first target driving distance and the first target steering angle at 10 moments during the vehicle parking process. The control devices 220 and 230 may need to control the corresponding actuators at 100 moments (also referred to as control nodes or control moments) to control the parking of the vehicle. In other words, for the control devices 220 and 230, the target position during the parking process indicated by the safe parking instruction information may be too sparse. For the control devices 220 and 230, the target position of the vehicle at each control node can be determined in combination with the operating status of the vehicle.

[0148] For example, the vehicle's position at the first control node can be determined based on the vehicle's speed and posture change information between the first moment and the first control node. The first control node can be any control node. In one embodiment, any of the at least one moment involved in the safe parking instruction information can also be the first control node.

[0149] In some possible implementations, the second control node is later than the first control node. When the autonomous driving function is not in an effective output state, the target driving distance and first target deceleration between the first and second control nodes can be determined based on the vehicle's speed at the first control node. For example, the brake controller can be preset with a curve showing how braking deceleration changes with vehicle speed in a safe parking scenario. Based on the vehicle's current speed, the target deceleration between the current node and the next control node can be determined. For another example, the target deceleration between the current and next control nodes can be determined based on the vehicle's current speed and the vehicle's braking capacity.

[0150] In some possible implementations, the second control node may be located between the first control node and the second moment. The first target steering angle of the vehicle at the second control node is determined based on the first target driving distance at the second moment, the first target steering angle at the second moment, the position of the vehicle at the first control node, and the target driving distance of the vehicle between the first control node and the second control node. For example, because the target posture during parking indicated by the safety instruction information may be too sparse, the control devices 220 and 230 may obtain the target steering angle of the next control node by interpolation based on the target posture indicated by the safety instruction information and the current posture of the vehicle.

[0151] In real-world scenarios, controlling a vehicle to perform a large steering angle at a high speed or braking at a high deceleration at a large steering angle can risk vehicle instability. To ensure safe driving, when determining the target steering angle and target braking deceleration for the next control node, these can be constrained based on the vehicle's operating status.

[0152] In some possible implementations, a first steering limit is determined based on the vehicle speed at a first control node. The first steering limit may include a limit on the steering angle allowed for stable vehicle travel at the speed. When a first target steering angle at a second control node is less than the first steering limit, the first target steering angle may be determined as the target steering angle for the second control node. When the first target steering angle at the second control node is greater than or equal to the first steering limit, the first steering limit may be determined as the target steering angle for the second control node.

[0153] In an embodiment of the present application, constraining the target steering angle of the next control node according to the vehicle speed at the current control node can reduce the risk of vehicle instability during the steering process.

[0154] In some possible implementations, a first deceleration limit is determined based on a maximum target steering angle of the vehicle between a first control node and a second control node. The first deceleration limit may include a limit on the braking deceleration allowed when the vehicle is traveling stably at the maximum target steering angle. When the first target deceleration is less than the first deceleration limit, the first target deceleration may be determined as the target braking deceleration between the first control node and the second control node. When the first target deceleration is greater than or equal to the first deceleration limit, the first deceleration limit may be determined as the target braking deceleration between the first control node and the second control node.

[0155] For ease of understanding, the following exemplifies the methods involved in FIG. 3 and FIG. 4 in conjunction with the scenario shown in FIG. 5 .

[0156] For example, Figure 5 is a schematic diagram of a vehicle driving scenario provided by an embodiment of the present application. As shown in Figure 5, vehicle 500 can serve as an example of intelligent driving device 100. Vehicle 500 can include system 200. For example, vehicle 500 can be equipped with control devices such as an autonomous driving domain controller, a brake controller, and a steering controller. Information exchange between these controllers can be achieved through a communication network.

[0157] Assume that vehicle 500 is in lane #1 at time #0 and in autonomous driving mode, as shown in Figure 5. In autonomous driving mode, the autonomous driving domain controller can plan a driving path based on the surrounding environment data collected by the perception sensors. For example, when the autonomous driving function is in an active output state, the autonomous driving domain controller will control the vehicle to travel along path #1, as shown in Figure 5. The vehicle can subsequently switch from lane #1 to lane #2 along this path. In this scenario, the passage instruction information can indicate the target position of the vehicle while traveling along path #1.

[0158] In one embodiment, when the autonomous driving function is operating normally, for example, when the autonomous driving domain controller and the communication network are operating normally, the autonomous driving domain controller can exchange information with other controllers and can control the vehicle to automatically drive according to path #1.

[0159] In another embodiment, even when the autonomous driving function fails, the function may still be in a valid output state. For example, although some processing units in the autonomous driving domain controller are in a faulty state, the corresponding redundant processing units can still perform the corresponding functions. In this scenario, the autonomous driving function may still be in a valid output state.

[0160] While vehicle 500 is operating using the autonomous driving function, a fault may occur that prevents the function from operating effectively. For example, the autonomous driving domain controller may crash, or a communication network failure may prevent the autonomous driving domain controller from communicating with other controllers. If the vehicle or related control devices do not have a response plan for such a failure scenario, the vehicle may risk losing control.

[0161] In one embodiment, as shown in FIG5 , when a fault occurs at time A that causes the autonomous driving function to be unable to be in a valid output state, the vehicle 500 will travel along path #2 as shown in FIG5 in a loss of control, and may then drive out of the boundary of lane #2 and hit a guardrail, signboard, tree, etc., causing a safety accident.

[0162] To prevent safety accidents caused by the inability of the autonomous driving function to be in an effective output state, in addition to planning the travel path when the autonomous driving function is in an effective output state (for example, path #1), the autonomous driving domain controller can also plan the target position of the vehicle during the parking process when the autonomous driving function is not in an effective output state, so that the vehicle can brake until it stops when such a failure occurs.

[0163] For example, the autonomous driving domain controller can plan the target posture in the parking scenario based on the vehicle's motion state at time #0, so that the vehicle 500 can achieve the braking parking process in lane #1 from time #0 to time #m. For example, in the parking process with the vehicle's motion state at time #0 as the initial state, the corresponding target driving trajectory can be the safe parking path shown in Figure 5, and the autonomous driving domain controller can plan the target posture #0 to the target posture #m located on the safe parking path. Among them, the target posture #0 to the target posture #m can respectively represent the target posture of the vehicle 500 from time #0 to time #m during the parking process, and the target posture #0 to the target posture #m can also be referred to as the target posture in the safe parking scenario. In other words, the safe parking indication information can indicate the target posture #0 to the target posture #m.

[0164] For example, the autonomous driving domain controller can send vehicle control instructions through the internal communication network. In the detection cycle corresponding to time #0, when the brake controller and the steering controller detect the corresponding vehicle control instruction, they can control the vehicle to travel along path #1 according to the traffic instruction information in the vehicle control instruction. Assume that a fault occurs at time A that causes the autonomous driving function to be unable to be in an effective output state. In the detection cycles after this moment (such as the detection cycle corresponding to time #1, the detection cycle corresponding to time #2, etc.), the brake controller and the steering controller cannot detect the corresponding vehicle control instruction. In this scenario, the detection cycle corresponding to time #0 can be used as an example of the first detection cycle, and the corresponding vehicle control instruction is the first vehicle control instruction; the detection cycle corresponding to time #1 can be used as an example of the second detection cycle, and the vehicle control instruction that should be detected in this detection cycle can be used as an example of the vehicle control instruction corresponding to the second detection cycle. In some possible embodiments, such as when the autonomous driving domain controller is down, the autonomous driving domain controller may not send the vehicle control instruction corresponding to the second detection cycle.

[0165] In one embodiment, taking the safe parking instruction information corresponding to time #0 as an example, the vehicle coordinate system at time #0 can be used as a reference, including the vehicle's position and posture in this coordinate system at each time. The vehicle coordinate system corresponding to time #0 can include a coordinate system established based on the orientation of the horizontal and vertical axes of vehicle 500 at time #0. In this scenario, time #0 can be understood as an example of the first time.

[0166] In another embodiment, the target posture of the vehicle during the parking process can be indicated by the target driving distance of the vehicle at different moments in the parking process and the steering angle related to the vehicle's steering. For example, the target driving distance at each moment can be based on the position of the vehicle 500 at moment #0. Moment #0 can be understood as an example of the first moment. For another example, the steering angle related to the steering of the vehicle can include: steering wheel angle, yaw angle, front wheel angle, heading angle, etc. For another example, during the parking process, the target posture of the vehicle 500 at moment #2 can be determined based on the target yaw angle at moment #1; that is, the target yaw angle of the vehicle at moment #1 can indicate its target posture at moment #2. For another example, during the parking process, the target position of the vehicle 500 at moment #2 can be obtained based on the target driving distance at moment #2.

[0167] Exemplarily, the safe parking instruction information may include target driving distances and target steering wheel angles at multiple moments in a safe parking scenario. For example, the target driving distances from moment #0 to moment #m may be recorded as s_0 to s_m, respectively. In some possible implementations, s_m may represent the target driving distance from moment #0 to moment #m in the direction along lane #1. For another example, the target steering wheel angles from moment #0 to moment #m may be recorded as ang_0 to ang_m, respectively. For another example, based on the target steering wheel angle of vehicle 500 at moment #0, the posture change of vehicle 500 between moment #0 and moment #1 may be estimated, and combined with the posture of vehicle 500 at moment #0, the posture of vehicle 500 at moment #1 may be obtained. In other words, by indicating the target steering wheel angle of vehicle 500 at moment #0, the target posture of vehicle 500 at moment #1 may be indicated.

[0168] In one embodiment, using the scenario shown in Figure 5 as an example, Figure 6 illustrates the target driving distances and target steering wheel angles at various times in a safe parking scenario. s_0 through s_m can be understood as examples of the first target driving distances at the corresponding time; ang_0 through ang_m can be understood as examples of the first target steering angles at the corresponding time.

[0169] In some possible implementations, the vehicle does not experience a fault between time #0 and time #1 that would prevent the autonomous driving function from being in a valid output state. At time #1, the autonomous driving domain controller may send a new vehicle control command, and the brake controller may update the target position corresponding to the safe parking scenario based on the vehicle control command. In this scenario, time #1 can be used as an example of the first time, and the detection period corresponding to time #1 can be used as an example of the first detection period. After time #1, if the detected autonomous driving domain controller node is lost, the brake controller may control the vehicle to stop according to the updated target position.

[0170] The following takes the case where the loss of the autonomous driving domain controller node is detected at time #A as an example, and combines Figures 5 and 6 to briefly describe the process of the brake controller controlling the vehicle to stop.

[0171] For example, as shown in Figure 5, at time #0, the autonomous driving function is operating normally, and vehicle 500 is autonomously traveling along path #1. Assuming that at time #A (e.g., time #A is between time #0 and time #1), the brake controller detects the loss of the autonomous driving domain controller node, the brake controller can control vehicle braking based on the target position indicated by the safe parking instruction information. Based on the target position indicated by the safe parking instruction information, the length of the safe parking path can be determined.

[0172] In one embodiment, the vehicle's travel distance during that time period can be estimated based on vehicle speed information and the time interval between time #0 and time #A. Combined with the vehicle's posture changes during that time period, the position of vehicle #A can be estimated, as shown in Figure 6. Based on the vehicle's position at time #A and the safe parking path, the remaining braking distance from the position at time #A to the target parking position can be determined.

[0173] In some possible implementations, the distance between the target positions indicated by the safe stop indication information is large, which does not match the time interval used by the brake controller to control vehicle braking. For example, the time interval between moment #0 and moment #1, and between moment #1 and moment #2 is 200 milliseconds (ms), and the time interval used by the brake controller for planning and controlling vehicle braking may be 10ms or 20ms. In other words, for the control of vehicle braking and steering, the target posture indicated by the safe stop indication information may be too sparse. In this scenario, the brake controller can determine the target braking deceleration of the vehicle before the next control node based on the vehicle speed at the current moment, and can determine the target posture of the next control node based on the vehicle speed at the current moment.

[0174] In one embodiment, assuming that the vehicle 500 has decelerated to the target posture #1 from moment #A to moment #1, it is necessary to further plan the target braking deceleration and target position of the vehicle at the subsequent control nodes (for example, moment #1-1 is the next control node of moment #1, moment #1-2 is the next control node of moment #1-1, and the time interval between adjacent control nodes is 10ms). For example, assuming that moment #1 is the current control node, the target braking deceleration of the vehicle between moment #1 and moment #1-1 can be planned based on the speed of the vehicle 500 at moment #1; the distance traveled by the vehicle in this time period can be planned based on the speed of the vehicle 500 at moment #1, and the target position of the vehicle at moment #1-1 can be determined in combination with the position of the vehicle at moment #1. In this scenario, moment #1 can be used as an example of the first control node, and moment #1-1 can be used as an example of the second control node. For another example, assuming that time #1-1 is the current control node, the target braking deceleration of the vehicle before time #1-2 and the target position of the vehicle at time #1-2 can be planned based on the speed of vehicle 500 at time #1-1. In this scenario, time #1-1 can be used as an example of the first control node, and time #1-2 can be used as an example of the second control node.

[0175] In another embodiment, the target steering wheel angle for the next control moment can be determined based on the target position of the next control node. For example, assuming that time #1-1 is the current control node, the target steering wheel angle for time #1-2 can be determined by interpolation, table lookup, etc. based on the position of vehicle 500 at time #1-1, the target driving distance between time #1-1 and time #1-2, and the target steering wheel angle and target driving distance of vehicle 500 at time #2.

[0176] In real-world scenarios, when driving at high speeds, if a vehicle turns at a large angle, there is a risk of vehicle instability. In some possible implementations, to improve vehicle stability, the target steering wheel angle at the next control moment can be constrained based on vehicle speed.

[0177] In one embodiment, assuming that vehicle 500 is in target posture #1 at time #1, by planning the vehicle's target position at time #1-1, the target steering wheel angle of the vehicle at time #1-1 can be determined as angle #1. Based on the vehicle's speed at time #1, the maximum steering wheel angle allowed at time #1-1 (or the maximum / average steering wheel angle between time #1 and time #1-1) without vehicle instability is angle #2. For example, when angle #1 is less than angle #2, it can be assumed that steering the vehicle at angle #1 does not pose a risk of instability. In this case, the brake controller can send an instruction to the steering controller, instructing the steering controller to steer the vehicle at angle #1 at time #1-1. For another example, when angle #1 is greater than angle #2, it can be assumed that steering the vehicle at angle #1 poses a risk of instability. In this case, the brake controller can send an instruction to the steering controller, instructing the steering controller to steer the vehicle at angle #2 at time #1-1. In this embodiment, angle #2 can be used as an example of a first steering limit.

[0178] In real-world scenarios, when driving at high speeds or turning at large angles, braking with excessive deceleration may cause vehicle instability. In some possible embodiments, to improve vehicle driving stability, the target longitudinal braking deceleration can be limited based on the vehicle's steering angle.

[0179] In one embodiment, assume that vehicle 500 is in target posture #1 at time #1. Given the steering wheel angle at time #1, the maximum allowable braking deceleration without destabilizing the vehicle is deceleration #1. The target braking deceleration between time #1 and time #1-1, determined based on the vehicle's speed at time #1, is deceleration #2. For example, if deceleration #1 is greater than deceleration #2, it can be assumed that braking at deceleration #2 poses no risk of destabilization. In this case, the brake controller may control vehicle braking at deceleration #2 between time #1 and time #1-1. For another example, if deceleration #1 is less than deceleration #2, it can be assumed that braking at deceleration #2 poses a risk of destabilization. In this case, the brake controller may control vehicle braking at deceleration #1 between time #1 and time #1-1. In this embodiment, deceleration #2 serves as an example of a first deceleration limit.

[0180] In another embodiment, the maximum braking deceleration (e.g., deceleration #3) allowed for the vehicle to maintain stability during the period from moment #1 to moment #1-1 can be determined based on the steering angle at moment #1 and the target steering wheel angle planned for moment #1-1. For example, when deceleration #2 is less than deceleration #3, the vehicle is braked at deceleration #2 during this period. For another example, when deceleration #2 is greater than deceleration #3, the vehicle is braked at deceleration #3 during this period. In this embodiment, deceleration #3 can be used as an example of the first deceleration limit.

[0181] For example, FIG7 is a schematic diagram of another system architecture provided by an embodiment of the present application, and the system 700 can be understood as an extension or deformation of the system 200. The system 700 may include an automatic driving controller, a braking controller, and a steering controller.

[0182] The autonomous driving domain controller may include a main computing unit, a redundant computing unit, and an arbitration unit. The autonomous driving domain controller may correspond to the control device 210, the main computing unit may correspond to the main processing unit 211, and the redundant computing unit may correspond to the redundant processing unit 212.

[0183] In some possible implementations, when the main computing unit 211 fails, the redundant computing unit can perform part or all of its functions, enabling the autonomous driving domain controller to send vehicle control instructions containing passage instruction information and safe parking instruction information.

[0184] The brake controller may include a primary brake control unit and a redundant brake control unit. The brake controller may correspond to the control device 220 , the primary brake control unit may correspond to the primary control unit 221 , and the redundant brake control unit may correspond to the redundant control unit 222 .

[0185] The steering controller may include a main steering control unit and a redundant steering control unit. The steering controller may correspond to the control device 230 , the main steering control unit may correspond to the main control unit 231 , and the redundant steering control unit may correspond to the redundant control unit 232 .

[0186] 8 is a schematic diagram of another system architecture provided in an embodiment of the present application. The system architecture 800 can be understood as an extension or variation of the systems 200 and 700.

[0187] As shown in Figure 8 , the autonomous driving domain controller 810 can perform scene perception based on data from various perception sensors, make decisions about the planned path, and control the vehicle to autonomously drive along the planned path. The autonomous driving domain controller 810 can also determine safe parking instructions based on the vehicle's current lane and information about obstacles around the road to ensure that the vehicle can safely park in the current lane according to the parking instructions in the future when the autonomous driving function is not in an effective output state. The autonomous driving domain controller 800 can send passage instructions to control the vehicle to drive along the normal planned path (such as path #1 shown in Figure 5 ); it can also send safe parking instructions to indicate the target posture for potential parking scenarios in the future (such as the target posture corresponding to the safe parking path shown in Figure 5 ).

[0188] In some possible implementations, the safe parking instruction information may include the distance between the vehicle's current position and the target parking position along the current lane. For example, the target parking position may be located in the current lane to achieve the effect of giving way without giving way. In another example, the distance and target parking position may be determined based on surrounding environment information.

[0189] In one embodiment, assuming a vehicle's current speed of 130 km / h and a braking capacity of -8 m / s², the theoretical braking distance required to stop the vehicle at the current speed is approximately 81.5 m. For example, if the distance between the target parking location and the vehicle's current position along the current lane is 75 m, the vehicle would not be able to stop within this distance at its current speed. To ensure safe parking even when the autonomous driving function is not in an active output state, the autonomous driving domain controller can actively control the vehicle to slow down.

[0190] In some possible implementations, the brake controller 820 may include a minimum risk strategy unit 821, as shown in FIG8 . Upon detecting that the autonomous driving domain controller 810 node is lost, the minimum risk strategy unit 821 may control the vehicle's braking until the vehicle stops according to the safe parking instruction information. This approach may also be referred to as enabling the minimum risk strategy.

[0191] In some possible implementations, the minimum safety measurement unit 821 may activate a minimum risk strategy upon receiving an execution request from the autonomous driving domain controller. For example, if a communication failure between the autonomous driving domain controller 810 and the steering controller 830 causes an autonomous driving function failure, the autonomous driving domain controller may send a request to the brake controller 820 to stop the vehicle; in response, the brake controller may activate the minimum risk strategy to stop the vehicle.

[0192] In one embodiment, the minimum risk strategy unit 821 may include a safe parking instruction information acquisition unit, a remaining available trajectory calculation unit, a position estimation unit, a vehicle speed / IMU data acquisition unit, a target position / target deceleration instruction calculation unit, a target steering instruction calculation unit, a steering instruction safety constraint unit, and a braking instruction safety constraint unit, as shown in Figure 8.

[0193] For example, the safe parking instruction information acquisition unit can be used to acquire safe parking instruction information. In another example, the safe parking instruction information acquisition unit can also estimate the length of the safe parking path (or the target total braking distance) indicated by the safe parking instruction information based on the target braking distance and target steering wheel angle corresponding to the target posture included in the safe parking instruction information. In another example, the vehicle speed / IMU data acquisition unit can be used to acquire real-time vehicle speed and data collected by the IMU (such as heading angle). In another example, the position estimation unit can be used to estimate the vehicle's current position based on the real-time vehicle speed and heading angle. In another example, the remaining available trajectory calculation unit can be used to determine the remaining braking distance for the control node based on the vehicle's current position and the length of the safe parking path. In another example, the target position / target deceleration command calculation unit can be used to determine the vehicle's target position at the next control node and the target braking deceleration during the period based on the remaining braking distance and the vehicle's current position. In another example, the target steering command calculation unit can be used to determine the target steering wheel angle for the next control node based on the target posture indicated by the safe parking instruction information and the target position of the next control node. For another example, the steering command safety constraint unit can be used to limit the target steering angle output by the minimum risk strategy unit to the steering controller based on the maximum steering wheel angle allowed for stable driving at the vehicle's current speed, thereby avoiding the risk of vehicle instability caused by excessive steering angles when driving at high speeds. For another example, the braking command safety constraint unit can be used to limit the target deceleration output to the braking command arbitration unit or subsequently to the brake actuator based on the maximum value of the steering wheel angle of the vehicle's current control node and the target steering wheel angle of the next control node, thereby avoiding the risk of vehicle instability caused by excessive braking deceleration when turning at a large angle.

[0194] In some possible implementations, system 800 may include other control devices, such as a vehicle control unit (VCU), which can exchange information with the autonomous driving domain controller 810, brake controller 820, and steering controller 830 via a communication network. For example, the minimum risk strategy unit 821 can also be located in the VCU. In this scenario, the vehicle control unit can exchange information with the brake controller and steering controller to control the vehicle's braking and stopping by activating the minimum risk strategy.

[0195] In some possible implementations, the minimum risk strategy unit can also be set in the steering controller. In this scenario, when the autonomous driving function is not in an effective output state, the steering controller can send a braking command to the brake controller to brake the vehicle until it stops.

[0196] 9 is a schematic diagram of another system architecture provided by an embodiment of the present application. The system architecture 900 can be understood as an extension or variation of the systems 200, 700, and 800.

[0197] As shown in Figure 9, the autonomous driving domain controller 910 can exchange information with the brake controller 920 through the primary communication network and the redundant communication network. For example, the autonomous driving domain controller 910 can encrypt the vehicle control command, and the brake controller 920 can receive the vehicle control command and decrypt it in a corresponding manner.

[0198] In one embodiment, the brake controller 910 may include a minimum risk strategy unit 921, a main road data parsing unit 922, a backup road data parsing unit 923, a driver instruction acquisition unit 924, a link arbitration unit 925, a brake instruction arbitration unit 926, a brake execution arbitration unit 927, an information parsing unit 928 and an instruction encapsulation unit 929, as shown in Figure 9.

[0199] Illustratively, the primary data parsing unit 922 can be used to obtain data transmitted through the primary communication network (also referred to as primary data), and can perform end-to-end (E2E) verification on the obtained data, decrypt data packets, etc. The backup data parsing unit 923 can be used to obtain data transmitted through the redundant communication network (also referred to as backup data), and can perform E2E verification on the obtained data, decrypt data packets, etc. The link arbitration unit 925 can obtain E2E verification results; based on the E2E verification results, it can determine whether there is a fault in the primary communication network or the redundant communication network, and can also obtain corresponding fault information; it can indicate which data from the primary or backup road is used to control vehicle braking.

[0200] In one embodiment, the main road data parsing unit 922 and the backup road data parsing unit 923 decrypt the data packet, for example, they can obtain the target posture involved in the vehicle control instruction, the driving path corresponding to the traffic instruction information, the safe parking path corresponding to the safe parking instruction information, etc.

[0201] For example, minimum risk strategy unit 921 can obtain information such as the target position associated with the vehicle control command, and can be used to determine lateral and longitudinal control commands for the vehicle under the minimum risk strategy. Under the minimum risk strategy, the vehicle will brake until it stops according to the safe stop instruction information. Minimum risk strategy unit 921 may correspond to minimum risk strategy unit 821.

[0202] The driver instruction acquisition unit 924 can be used to acquire the instruction input by the driver so that the vehicle can brake according to the driver's intention.

[0203] For example, the braking system in which the brake controller is located may include a main brake actuator and a standby brake actuator. The standby brake actuator can realize vehicle braking when the main brake actuator fails. The brake controller 920 may include a main brake monitoring unit and a standby brake monitoring unit to monitor the operating status of the main brake actuator and the standby brake actuator respectively; it may also include a main brake control unit and a standby brake control unit to control the operation of the main brake actuator and the standby brake actuator respectively. The brake execution arbitration unit 927 may be used to obtain the brake command determined by the brake command arbitration unit; determine the brake actuator used to execute the brake command based on the operating status of the main brake actuator and the standby brake actuator; when the vehicle brake is controlled by the main brake actuator, the main brake control unit may be instructed to control the operation of the main brake actuator according to the brake command; or, when the vehicle brake is controlled by the standby brake actuator, the standby brake control unit may be instructed to control the operation of the standby brake actuator according to the brake command.

[0204] For example, the information parsing unit 928 and the instruction encapsulation unit 929 can be used to exchange information with other control devices. The information parsing unit 928 can obtain and parse data packets from the communication network. For example, through parsing, it can obtain real-time steering wheel angle information. When using the minimum risk strategy, the brake command arbitration unit 926 can determine the steering wheel angle command, the electric parking brake (EPB) command, the brake light command, the double flash light command, etc. The instruction encapsulation unit 929 can encapsulate the above-mentioned commands, and the brake controller 920 can send them to other control devices via the communication network. For example, the EPS controller, the EPB controller, the body control module (BCM), and other control devices can obtain the corresponding commands and control the steering wheel, EPB, brake lights, etc.

[0205] The method provided in the embodiments of the present application is described in detail above with reference to Figures 3 to 9. The apparatus provided in the embodiments of the present application will be described in detail below with reference to Figures 10 and 11. The description of the apparatus embodiment corresponds to the description of the method embodiment. Therefore, for any details not described in detail, reference can be made to the method embodiment above.

[0206] For example, FIG10 is a schematic block diagram of an apparatus provided in an embodiment of the present application. The apparatus 1000 may correspond to the control apparatus 210, or may be a component (e.g., a chip, a processor, a processing unit, etc.) or unit that implements the control apparatus. The apparatus 1000 may include an acquisition unit 1010 and a processing unit 1020.

[0207] When the apparatus 1000 is used to execute the method 300 of FIG. 3 , the acquiring unit 1010 may be used to execute step S310 , and the processing unit 1020 may be used to execute step S320 .

[0208] Specifically, the acquisition unit 1010 can be used to acquire environmental information about the vehicle's surroundings when the vehicle is in an automatic driving state. The processing unit 1020 can be used to send a vehicle control instruction based on the environmental information, the vehicle control instruction including passage instruction information and safe parking instruction information.

[0209] Exemplarily, the control device 1000 may be an autonomous driving domain controller, or a chip or processor in the autonomous driving domain controller, or a computing platform or vehicle equipped with the autonomous driving domain controller.

[0210] In some possible implementations, the safe parking instruction information may include a first target parking distance, and the processing unit 1020 may be further configured to determine the first target parking distance according to environmental information.

[0211] In some possible implementations, the processing unit 1020 may also be configured to: determine, based on the first target stopping distance and the vehicle's braking capability, an initial parking speed limit allowed for the vehicle to park within the first target stopping distance; and control the vehicle to decelerate when the vehicle's speed at the first moment is greater than or equal to the initial parking speed limit.

[0212] For example, for descriptions of the passage instruction information, the safe parking instruction information, the first target parking distance, the first moment, the initial parking speed limit, etc., reference may be made to the relevant records of the method 300 .

[0213] For example, FIG11 is a schematic block diagram of another apparatus provided in an embodiment of the present application. The apparatus 2000 may correspond to the control apparatus 220 or 230, or may also be a component or unit implementing the control apparatus. The apparatus 2000 may include an acquisition unit 2010 and a processing unit 2020.

[0214] When the apparatus 2000 is used to execute the method 400 of FIG. 4 , the acquiring unit 2010 may be used to execute step S410 , and the processing unit 2020 may be used to execute step S420 .

[0215] Specifically, the acquisition unit 2010 may be configured to: acquire a vehicle control instruction, the vehicle control instruction including passage instruction information and safe parking instruction information. The processing unit 2020 may be configured to: control the vehicle operation according to the vehicle control instruction.

[0216] Exemplarily, the control device 2000 may be a brake controller, a steering controller, a VCU or other control device, or a chip or processor in the above control device, or a computing platform or vehicle equipped with the above control device.

[0217] In some possible implementations, the vehicle control command may include a first vehicle control command corresponding to the first detection period, and the second detection period is subsequent to the first detection period. The processing unit 2020 may be configured to, when the autonomous driving function is not in a valid output state during the second detection period, control the vehicle to stop according to the safe parking instruction information in the first vehicle control command.

[0218] In some possible implementations, the processing unit 2020 may be further configured to: when the autonomous driving function is not in a valid output state, determine, based on a first vehicle speed at the first control node, a target driving distance and a first target deceleration of the vehicle between the first control node and a second control node, where the second control node is later than the first control node.

[0219] In some possible implementations, the second control node is between the first control node and the second moment, and the processing unit 2020 can also be used to determine the first target steering angle of the vehicle at the second control node based on the first target driving distance at the second moment, the first target steering angle at the second moment, the position of the vehicle at the first control node, and the target driving distance of the vehicle between the first control node and the second control node.

[0220] In some possible implementations, the processing unit 2020 can also be used to: determine a first steering limit based on the first vehicle speed at the first control node; when the first target steering angle at the second control node is less than the first steering angle limit, determine the first target steering angle as the target steering angle of the second control node, and control the steering of the vehicle; or, when the first target steering angle of the second control node is greater than or equal to the first steering angle limit, determine the first steering limit as the target steering angle of the second control node, and control the steering of the vehicle.

[0221] In some possible implementations, the processing unit 2020 can also be used to: determine a first deceleration limit based on the maximum target steering angle of the vehicle between the first control node and the second control node; when the first target deceleration is less than the first deceleration limit, determine the first target deceleration as the target braking deceleration between the first control node and the second control node, and control vehicle braking; or, when the first target deceleration is greater than or equal to the first deceleration limit, determine the first deceleration limit as the target braking deceleration between the first control node and the second control node, and control vehicle braking.

[0222] It should be understood that the division of the various units in the above devices is merely a division of logical functions. In actual implementation, they may be fully or partially integrated into a single physical entity, or physically separated. All units in the above devices may be implemented entirely through a processor calling software, entirely through hardware circuits, or partially through a processor calling software, with the remainder implemented through hardware circuits.

[0223] For example, FIG12 is a schematic block diagram of another control device 3000 (hereinafter referred to as device 3000) provided in an embodiment of the present application. The device 3000 may include: a processor 3010, an interface circuit 3020, and a memory 3030. The processor 3010, the interface circuit 3020, and the memory 3030 are connected via an internal connection path. The memory 3030 is used to store instructions, and the processor 3010 is used to execute the instructions stored in the memory 3030, and receive / send some parameters through the interface circuit 3020. Optionally, the memory 3030 can be coupled to the processor 3010 via an interface or integrated with the processor 3010.

[0224] It should be noted that the interface circuit 3020 may include, but is not limited to, a transceiver device such as an input / output interface to enable communication between the device 3000 and other devices or communication networks. For example, communication with a radar and / or internal circuits of an intelligent driving device may be achieved through the interface circuit 3020.

[0225] In one embodiment, the processor 3010 can implement the functions of the control device 210 in the aforementioned method embodiment by executing instructions stored in the memory 3030.

[0226] In another embodiment, the processor 3010 can implement the functions of the control devices 220 and 230 in the aforementioned method embodiments by executing instructions stored in the memory 3030.

[0227] The present application also provides a chip (or chip system). The chip (or chip system) 30 may include a circuit 31 and an input / output interface 32. The circuit 31 may be a logic circuit, an integrated circuit, etc., and the input / output interface 32 may also be an input / output circuit, or an interface circuit, which can input information (or receive information) and output information (or send information). Optionally, the chip system can be composed of chips, or it can include chips and other discrete devices. The chip 30 can be used to execute the method performed by the control device 210, 220 or 230 in each embodiment of the present application.

[0228] An embodiment of the present application also provides a computer program product, which includes: computer program code, which, when running on a computer, enables the computer to execute any one of the method embodiments in Figures 3 to 9 above, and any possible implementation thereof.

[0229] An embodiment of the present application also provides a computer-readable storage medium, which stores program code or instructions. When the computer program code or instructions are executed by a computer processor, the processor implements any method embodiment in Figures 3 to 9 above, and any possible implementation method thereof.

[0230] An embodiment of the present application further provides a system including a first control device and a second control device, wherein the first control device is used to execute method 300 , and the second control device is used to execute method 400 .

[0231] For example, the first control device may include the control device 210 , and the second control device may include the control devices 220 and 230 .

[0232] An embodiment of the present application also provides an intelligent driving device, which may include the above-mentioned system, or may include the above-mentioned device 1000, 2000 or 3000.

[0233] Exemplarily, the intelligent driving device can be a vehicle. The vehicle involved in the embodiments of the present application is a vehicle in a broad sense, which can be a means of transportation (such as a commercial vehicle, a passenger car, a motorcycle, a flying car, a train, etc.), an industrial vehicle (such as a forklift, a trailer, a tractor, etc.), an engineering vehicle (such as an excavator, a bulldozer, a crane, etc.), agricultural equipment (such as a lawn mower, a harvester, etc.), amusement equipment, a toy vehicle, etc. The embodiments of the present application do not specifically limit the type of vehicle. For example, the vehicle in the present application can include a pure electric vehicle / battery electric vehicle (pure EV / battery EV), a hybrid electric vehicle (hybrid electric vehicle, HEV), a range extended electric vehicle (REEV), a plug-in hybrid electric vehicle (PHEV) or a new energy vehicle (NEV), etc.

[0234] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel 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.

[0235] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0236] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0237] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0238] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0239] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0240] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A control method, characterized in that: include: When the vehicle is in an automatic driving state, obtaining environmental information around the vehicle; According to the environmental information, a vehicle control instruction is sent, wherein the vehicle control instruction includes passage instruction information and safe parking instruction information. The passage instruction information indicates: when the automatic driving function is in a valid output state, the target posture of the vehicle during driving; The safe parking instruction information indicates: the target position of the vehicle during parking when the automatic driving function is not in the valid output state.

2. The method according to claim 1, characterized in that The vehicle control instruction includes a first vehicle control instruction corresponding to a first detection cycle, and the second detection cycle is after the first detection cycle; When the automatic driving function is in the valid output state during the first detection period, the vehicle operates according to the target posture indicated by the passage instruction information in the first vehicle control instruction; When the automatic driving function is not in the valid output state in the second detection cycle, the vehicle operates according to the target posture indicated by the safe parking instruction information in the first vehicle control instruction.

3. The method according to claim 1 or 2, characterized in that The vehicle is in an automatic driving state at a first moment, the vehicle is in a first lane at the first moment, the vehicle control instruction corresponds to the first moment, and the target posture of the vehicle during parking includes the target posture of the vehicle during parking in the first lane.

4. The method according to claim 3, characterized in that The safe parking instruction information indicates: the target position of the vehicle during parking when the automatic driving function is not in the valid output state, including: a first target driving distance of the vehicle at at least one moment and a first target steering angle at the at least one moment when the autonomous driving function is not in the valid output state; The at least one moment includes a second moment, and the second moment is later than the first moment. The first target driving distance at the second moment includes: a distance along a lane direction of the first lane between a target position of the vehicle at the second moment and a position of the vehicle at the first moment when the automatic driving function is not in the valid output state; The first target steering angle at the second moment indicates: when the automatic driving function is not in the valid output state, the target steering angle of the vehicle at the second moment.

5. The method according to claim 4, characterized in that The first target steering angle includes at least one of a target steering wheel angle, a target yaw angle, and a target heading angle.

6. The method according to claim 5, characterized in that The first target steering angle includes a target yaw angle or a target heading angle, and the safe parking instruction information also includes the target posture of the vehicle at at least one moment. The target steering wheel angle of the vehicle at the second moment is determined based on the target posture at the second moment, the first target steering angle at the second moment and the real-time posture of the vehicle.

7. The method according to any one of claims 3 to 6, characterized in that The method further comprises: determining the first target stopping distance based on the environmental information; Among them, the safe parking instruction information includes a first target parking distance, and the first target parking distance includes: the distance between the position of the vehicle at the first moment and the target parking position of the vehicle in the first lane when the automatic driving function is not in the valid output state.

8. The method according to claim 7, characterized in that The method further comprises: determining, based on the first target stopping distance and the braking capability of the vehicle, an initial parking speed limit allowed for the vehicle to stop within the first target stopping distance; When the vehicle speed at the first moment is greater than or equal to the initial parking speed limit, the vehicle is controlled to decelerate.

9. The method according to any one of claims 1 to 8, characterized in that The autonomous driving function is not in a valid output state, including at least one of the following: the autonomous driving domain controller is in a down state, the communication network used to transmit the output of the autonomous driving function is in a faulty state, or the autonomous driving controller sends a first request message, and the first request message is used to request control of the vehicle to stop.

10. A control method, characterized in that: include: Obtain vehicle control instructions, including traffic instruction information and safe parking instruction information, The passage instruction information indicates: when the automatic driving function is in a valid output state, the target position of the vehicle during driving; the safe parking instruction information indicates: when the automatic driving function is not in the valid output state, the target position of the vehicle during parking; According to the vehicle control instruction, the operation of the vehicle is controlled.

11. The method according to claim 10, characterized in that The vehicle control instruction includes a first vehicle control instruction corresponding to a first detection cycle, and the second detection cycle is after the first detection cycle; In the second detection period, the automatic driving function is not in a valid output state, including: not detecting a vehicle control command corresponding to the second detection period in the second detection period, or detecting first request information in the second period, the first request information being used to request control of the vehicle to stop; The step of controlling the vehicle operation according to the vehicle control instruction includes: When the automatic driving function is not in the valid output state during the second detection cycle, the vehicle is controlled to stop according to the safe parking instruction information in the first vehicle control instruction.

12. The method according to claim 10 or 11, characterized in that The vehicle is in an automatic driving state at a first moment, the vehicle is in a first lane at the first moment, the vehicle control instruction corresponds to the first moment, and the target posture of the vehicle during parking includes the target posture of the vehicle during parking in the first lane.

13. The method according to claim 12, characterized in that The safe parking instruction information indicates: the target position of the vehicle during parking when the automatic driving function is not in the valid output state, including: a first target driving distance of the vehicle at at least one moment and a first target steering angle at the at least one moment when the autonomous driving function is not in the valid output state; The at least one moment includes a second moment, and the second moment is later than the first moment. The first target driving distance at the second moment includes: a distance along a lane direction of the first lane between a target position of the vehicle at the second moment and a position of the vehicle at the first moment when the automatic driving function is not in the valid output state; The first target steering angle at the second moment indicates: when the automatic driving function is not in the valid output state, the target steering angle of the vehicle at the second moment.

14. The method according to claim 13, characterized in that The first target steering angle includes at least one of a target steering wheel angle, a target yaw angle, and a target heading angle.

15. The method according to claim 14, characterized in that The first target steering angle includes a target yaw angle or a target heading angle, and the safe parking instruction information also includes the target posture of the vehicle at at least one moment. The target steering wheel angle of the vehicle at the second moment is determined based on the target posture at the second moment, the first target steering angle at the second moment and the real-time posture of the vehicle.

16. The method according to any one of claims 10 to 15, characterized in that The method further comprises: When the automatic driving function is not in the valid output state, the target driving distance and the first target deceleration of the vehicle between the first control node and the second control node are determined according to the first vehicle speed of the vehicle at the first control node, and the second control node is later than the first control node.

17. The method according to claim 16, characterized in that The second control node is located between the first control node and the second time, and the method further includes: The first target steering angle of the vehicle at the second control node is determined based on the first target driving distance at the second moment, the first target steering angle at the second moment, the position of the vehicle at the first control node, and the target driving distance of the vehicle between the first control node and the second control node.

18. The method according to claim 17, characterized in that The position of the vehicle at the first control node is determined based on the vehicle speed and posture change information between the vehicle at the first moment and the first control node.

19. The method according to claim 17 or 18, characterized in that The method further comprises: determining a first steering limit value according to the first vehicle speed of the vehicle at the first control node, the first steering limit value comprising a limit value of a target steering angle allowed for the vehicle to stably travel at the first vehicle speed; When the first target steering angle of the second control node is less than the first steering limit, determining the first target steering angle as the target steering angle of the second control node and controlling the vehicle to steer; or, When the first target steering angle of the second control node is greater than or equal to the first steering limit value, the first steering limit value is determined as the target steering angle of the second control node, and the vehicle steering is controlled.

20. The method according to any one of claims 16 to 19, characterized in that The method further comprises: determining a first deceleration limit value according to a maximum target steering angle of the vehicle between the first control node and the second control node, the first deceleration limit value comprising a limit value of a target braking deceleration allowed for stable driving of the vehicle at the maximum target steering angle; When the first target deceleration is less than the first deceleration limit, using the first target deceleration as the target braking deceleration between the first control node and the second control node, and controlling the vehicle braking; or When the first target deceleration is greater than or equal to the first deceleration limit, the first deceleration limit is used as the target braking deceleration between the first control node and the second control node, and the vehicle braking is controlled.

21. The method according to any one of claims 10 to 20, characterized in that The autonomous driving function is not in the valid output state, including: the autonomous driving domain controller is in a down state, the communication network used to transmit the output of the autonomous driving function is in a faulty state, or the autonomous driving controller sends a first request message, and the first request message is used to request control of the vehicle to stop.

22. A system, characterized in that comprising a first control unit and a second control unit, a first control unit configured to: when the vehicle is in an automatic driving state, obtain environmental information surrounding the vehicle; and send a vehicle control instruction based on the environmental information, the vehicle control instruction including passage instruction information and safe parking instruction information, wherein the passage instruction information indicates a target position of the vehicle during driving when the automatic driving function is in an effective output state; and the safe parking instruction information indicates a target position of the vehicle during parking when the automatic driving function is not in the effective output state; The second control unit is used to: obtain the vehicle control instruction; and control the operation of the vehicle according to the vehicle control instruction.

23. The system according to claim 22, wherein: The vehicle control instruction includes a first vehicle control instruction corresponding to a first detection cycle, and the second detection cycle is after the first detection cycle; The second control unit is used to: when the automatic driving function is in the valid output state in the first detection cycle, control the operation of the vehicle according to the passage indication information in the first vehicle control instruction; when the automatic driving function is not in the valid output state in the second detection cycle, control the parking of the vehicle according to the safe parking indication information in the first vehicle control instruction.

24. The system according to claim 22 or 23, characterized in that The vehicle is in an automatic driving state at a first moment, the vehicle is in a first lane at the first moment, the vehicle control instruction corresponds to the first moment, and the target posture of the vehicle during parking includes the target posture of the vehicle during parking in the first lane.

25. The system according to any one of claims 22 to 24, characterized in that The safe parking instruction information indicates: a target position of the vehicle during parking when the automatic driving function is not in the valid output state, including: a first target driving distance of the vehicle at at least one moment and a first target steering angle at the at least one moment when the autonomous driving function is not in the valid output state; The at least one moment includes a second moment, and the second moment is later than the first moment. The first target driving distance at the second moment includes: a distance along a lane direction of the first lane between a target position of the vehicle at the second moment and a position of the vehicle at the first moment when the automatic driving function is not in the valid output state; The first target steering angle at the second moment indicates: when the automatic driving function is not in the valid output state, the target steering angle of the vehicle at the second moment.

26. The system according to any one of claims 22 to 25, characterized in that The first target steering angle includes at least one of a target steering wheel angle, a target yaw angle, and a target heading angle.

27. The system according to any one of claims 22 to 26, characterized in that The first target steering angle includes a target yaw angle or a target heading angle, and the safe parking instruction information also includes the target posture of the vehicle at at least one moment. The target steering wheel angle of the vehicle at the second moment is determined based on the target posture at the second moment, the first target steering angle at the second moment and the real-time posture of the vehicle.

28. The system according to any one of claims 22 to 27, characterized in that The first control unit is further configured to: determining the first target stopping distance based on the environmental information; Among them, the safe parking instruction information includes a first target parking distance, and the first target parking distance includes: the distance between the position of the vehicle at the first moment and the target parking position of the vehicle in the first lane when the automatic driving function is not in the valid output state.

29. The system according to claim 28, wherein The first control unit is further configured to: determining, based on the first target stopping distance and the braking capability of the vehicle, an initial parking speed limit allowed for the vehicle to stop within the first target stopping distance; When the vehicle speed at the first moment is greater than or equal to the initial parking speed limit, the vehicle is controlled to decelerate.

30. The system according to any one of claims 22 to 29, characterized in that The second control unit is further configured to: When the automatic driving function is not in the valid output state, the target driving distance and the first target deceleration of the vehicle between the first control node and the second control node are determined according to the first vehicle speed of the vehicle at the first control node, and the second control node is later than the first control node.

31. The system according to claim 30, wherein: The second control node is located between the first control node and the second time instant, and the second control unit is further configured to: The first target steering angle of the vehicle at the second control node is determined based on the first target driving distance at the second moment, the first target steering angle at the second moment, the position of the vehicle at the first control node, and the target driving distance of the vehicle between the first control node and the second control node.

32. The system according to claim 31, wherein: The position of the vehicle at the first control node is determined based on the vehicle speed and posture change information between the vehicle at the first moment and the first control node.

33. The system according to any one of claims 30 to 32, characterized in that The second control unit is further configured to: determining a first steering limit value according to the first vehicle speed of the vehicle at the first control node, the first steering limit value comprising a limit value of a target steering angle allowed for the vehicle to stably travel at the first vehicle speed; When the first target steering angle of the second control node is less than the first steering limit, determining the first target steering angle as the target steering angle of the second control node, and controlling the vehicle to steer; or, When the first target steering angle of the second control node is greater than or equal to the first steering limit value, the first steering limit value is determined as the target steering angle of the second control node, and the vehicle steering is controlled.

34. The system according to any one of claims 30 to 33, characterized in that The second control unit is further configured to: determining a first deceleration limit value according to a maximum target steering angle of the vehicle between the first control node and the second control node, the first deceleration limit value comprising a limit value of a target braking deceleration allowed for stable driving of the vehicle at the maximum target steering angle; When the first target deceleration is less than the first deceleration limit, using the first target deceleration as a target braking deceleration between the first control node and the second control node, and controlling the vehicle braking; or, When the first target deceleration is greater than or equal to the first deceleration limit, the first deceleration limit is used as the target braking deceleration between the first control node and the second control node, and the vehicle braking is controlled.

35. The system according to any one of claims 30 to 34, characterized in that The first control device includes an autonomous driving domain controller, and the autonomous driving function is not in the valid output state, including: the autonomous driving domain controller is in a down state, the communication network used to transmit the output of the autonomous driving function is in a fault state, or the autonomous driving controller sends a first request message, and the first request message is used to request control of the vehicle to stop.

36. A control device, characterized in that: The method comprises modules or units for executing the method according to any one of claims 1 to 9.

37. A control device, characterized in that: The method comprises modules or units for performing the method according to any one of claims 10 to 21.

38. A control device, characterized in that: The device comprises at least one processor coupled to at least one memory, and the at least one processor is configured to execute a computer program or instruction stored in the at least one memory so as to enable the device to perform the method according to any one of claims 1 to 21.

39. A computer-readable storage medium, characterized in that Instructions or program codes are stored thereon, and when the instructions or program codes are executed by a processor, the processor is caused to implement the method according to any one of claims 1 to 21.

40. A computer program product, characterized in that The computer program product comprises: a computer program code, and when the computer program code is executed, the method according to any one of claims 1 to 21 is implemented.

41. A chip, characterized in that: It includes a circuit and a communication interface, wherein the communication interface is used to receive information from other devices and input it into the circuit, and / or the communication interface is used to send the information in the circuit to other devices, and the circuit is used to execute the method as described in any one of claims 1 to 21.

Images