Vehicle control methods and vehicles

By synchronously receiving vehicle control commands and environmental information during the normal operation of the intelligent driving master control chip, backup safety control parameters are formed, and braking and steering control quantities are generated through a smooth transition strategy in case of failure. This solves the problem of unstable vehicle control after the failure of the intelligent driving master control chip and achieves reliable and safe control takeover.

CN123104677APending Publication Date: 2026-11-17CHERY AUTOMOBILE CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202611593981.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-10-14
Publication Date
2026-11-17

AI Technical Summary

Technical Problem

When the main control chip for intelligent driving fails, existing technology cannot effectively maintain the stability and safety of vehicle control. This can lead to sudden changes in longitudinal deceleration and lateral steering commands during control switching, affecting vehicle stability and ride comfort.

Method used

During normal operation of the intelligent driving main control chip, it synchronously receives vehicle control commands and environmental information to form backup safety control parameters. When a fault occurs, it generates braking and steering control quantities through a smooth transition strategy to achieve a smooth switch.

Benefits of technology

By pre-backing up environmental information and control parameters, it ensures reliable and safe takeover of control in the event of a main control chip failure, avoids the fallback control from deviating from actual road conditions, reduces the abrupt changes in control commands, and improves the smoothness and reliability of vehicle control switching.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123104677A_ABST
    Figure CN123104677A_ABST
Patent Text Reader

Abstract

The vehicle control method and vehicle provided in this application include: receiving vehicle control commands and safety field information of the vehicle's surrounding environment synchronously sent by the intelligent driving main control chip during normal operation; calculating and storing backup safety control parameters based on the safety field information during the transmission of vehicle control commands to the vehicle actuators; detecting the operating status of the intelligent driving main control chip; when it is determined that the intelligent driving main control chip has failed, locking the safety field information of the last frame before the failure and the corresponding backup safety control parameters as the initial reference for mode switching; generating braking control quantities and steering control quantities based on the initial reference and through a preset smooth transition strategy; and sending the braking control quantities and steering control quantities to the vehicle actuators to switch control modes, thereby achieving the technical effect of improving the smoothness and reliability of vehicle control when the chip fails.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of intelligent driving control, and more particularly to a vehicle control method and a vehicle. Background Technology

[0002] With the widespread adoption of Advanced Driver Assistance Systems (ADAS) and advanced intelligent driving, vehicles generally adopt a dual-domain control architecture that combines a System on Chip (SOC) and a Microcontroller Unit (MCU). The SOC is responsible for perception fusion and trajectory planning, while the MCU is responsible for underlying execution and safety monitoring.

[0003] However, after the SOC fails, the MCU can usually only rely on fixed thresholds to perform degraded braking or disengage from autonomous driving. It lacks continuous support for real-time traffic topology and lane geometry information, resulting in a disconnect between the fallback control and road conditions. At the same time, longitudinal deceleration and lateral steering commands are prone to sudden changes when control is switched, affecting vehicle stability and ride comfort.

[0004] Therefore, it is urgent to solve the problem of how to achieve reliable and safe takeover based on existing environmental information while maintaining control stability after SOC failure. Summary of the Invention

[0005] This application provides a vehicle control method and a vehicle to solve the aforementioned technical problems. When the intelligent driving main control chip is operating normally, the method continuously receives vehicle control commands and safety field information of the vehicle's surrounding environment, and simultaneously forms backup safety control parameters matching the current environment during the transmission of vehicle control commands. When a fault is detected in the intelligent driving main control chip, the method uses the last frame of safety field information before the fault and the corresponding backup safety control parameters as the initial reference for mode switching. Then, according to a preset smooth transition strategy, it generates braking control and steering control quantities for takeover and sends them to the vehicle's actuators, thereby achieving a smooth transition from autonomous driving control to safety takeover control.

[0006] In a first aspect, this application provides a vehicle control method, comprising:

[0007] During normal operation of the intelligent driving main control chip, it receives vehicle control commands and safety field information of the vehicle's surrounding environment synchronously sent by the intelligent driving main control chip;

[0008] During the process of transmitting vehicle control commands to the vehicle actuators, backup safety control parameters are calculated and stored based on safety field information;

[0009] The system detects the operating status of the intelligent driving main control chip. When it is determined that the intelligent driving main control chip has failed, it locks the safety field information of the last frame before the failure and the corresponding backup safety control parameters as the initial reference for mode switching.

[0010] Based on the initial baseline, braking control and steering control quantities are generated using a preset smooth transition strategy.

[0011] The braking control and steering control signals are sent to the vehicle actuators to switch the control mode.

[0012] In one possible implementation, detecting the operating status of the intelligent driving main control chip includes:

[0013] Acquire the health status indicator signal sent by the intelligent driving main control chip;

[0014] Perform end-to-end integrity verification on the communication link between the main control chip and the intelligent driving system.

[0015] The operating status of the intelligent driving main control chip is determined based on the health status indicator signal and the verification result of the end-to-end integrity check.

[0016] In one possible implementation, a malfunction in the intelligent driving main control chip is determined in the following way:

[0017] If the health status indicator signal is inconsistent with the preset normal status, or if the verification result is not passed, it will be marked as an abnormality and the duration of the abnormality will begin to accumulate.

[0018] When the duration of the anomaly exceeds the preset fault tolerance threshold, the intelligent driving main control chip is determined to have malfunctioned.

[0019] In one possible implementation, based on an initial baseline, braking control and steering control quantities are generated using a preset smooth transition strategy, including:

[0020] Use the spare safety control parameters in the initial baseline as the transition starting values;

[0021] The target control value is calculated based on the safety field information in the initial reference and used as the transition final value.

[0022] By using a smooth transition strategy, the current control quantity of the first control cycle is set as the transition start value. In each subsequent control cycle, the current control quantity is adjusted gradually based on the current control quantity of the previous control cycle, with an adjustment range not exceeding the preset change rate limit, until the current control quantity reaches the transition end value, thereby obtaining the braking control quantity and steering control quantity respectively.

[0023] In one possible implementation, the target control variable value is calculated based on the safety field information in the initial reference, and used as the transition final value, including:

[0024] Perform longitudinal target spatial location clustering analysis on the safety field information in the initial baseline to identify whether there are obstacles ahead;

[0025] If it exists, the real-time deceleration is calculated based on the following distance between the vehicle and the obstacle, the relative speed difference, and the preset safety boundary, and is used as the transition final value of the braking dimension.

[0026] If it does not exist, then the two corresponding deceleration values ​​are calculated based on the preset maximum allowable deceleration time and the longest safe deceleration distance, and the smaller value is taken as the transition final value of the braking dimension.

[0027] In one possible implementation, the target control variable value is calculated based on the safety field information in the initial reference, and used as the transition final value, including:

[0028] Extract the coefficients of the lane line polynomial equation from the safety field information in the initial benchmark to construct the lane line polynomial equation as a static lane line model.

[0029] The instantaneous vehicle speed and yaw rate are obtained to perform kinematic integration and determine the spatial offset of the vehicle reference frame relative to the static lane line model.

[0030] Adjust the lane line polynomial equation based on the spatial offset to determine the target lane line curvature at the current moment.

[0031] The corresponding numerical value is generated based on the curvature mapping of the target lane line, serving as the transitional final value for the steering dimension.

[0032] In one possible implementation, it also includes:

[0033] When switching control modes, a multimodal driver takeover alert signal is generated;

[0034] The multimodal driver takeover alert signal is output to the in-vehicle human-machine interaction device for visual display.

[0035] In one possible implementation, it also includes:

[0036] Continuously collect the driver's control input signals;

[0037] When the control input signal meets the preset takeover judgment conditions, stop sending braking control and steering control quantities, and resume transmitting driver operation commands.

[0038] In one possible implementation, backup safety control parameters are calculated and stored based on safety field information, including:

[0039] After time synchronization correction, the security field information is stored in the internal cache;

[0040] Based on the cached safety field information, braking backup parameters and steering backup parameters are calculated separately and used as backup safety control parameters. The backup safety control parameters are bound to and updated with the safety field information of the corresponding frame.

[0041] Secondly, this application provides a vehicle control device, comprising:

[0042] The receiving module is used to receive vehicle control commands and safety field information of the vehicle's surrounding environment synchronously sent by the intelligent driving main control chip during normal operation.

[0043] The processing module is used to calculate and store backup safety control parameters based on safety field information during the process of transmitting vehicle control commands to vehicle actuators.

[0044] The processing module is also used to detect the operating status of the intelligent driving main control chip. When it is determined that the intelligent driving main control chip has failed, it locks the safety field information of the last frame before the failure and the corresponding backup safety control parameters as the initial reference for mode switching.

[0045] The processing module is also used to generate braking control and steering control quantities based on the initial reference and through a preset smooth transition strategy.

[0046] The processing module is also used to send braking control quantities and steering control quantities to the vehicle actuators for control mode switching.

[0047] In one possible implementation, the processing module is further configured to:

[0048] Acquire the health status indicator signal sent by the intelligent driving main control chip;

[0049] Perform end-to-end integrity verification on the communication link between the main control chip and the intelligent driving system.

[0050] The operating status of the intelligent driving main control chip is determined based on the health status indicator signal and the verification result of the end-to-end integrity check.

[0051] In one possible implementation, the processing module is further configured to:

[0052] If the health status indicator signal is inconsistent with the preset normal status, or if the verification result is not passed, it will be marked as an abnormality and the duration of the abnormality will begin to accumulate.

[0053] When the duration of the anomaly exceeds the preset fault tolerance threshold, the intelligent driving main control chip is determined to have malfunctioned.

[0054] In one possible implementation, the processing module is further configured to:

[0055] Use the spare safety control parameters in the initial baseline as the transition starting values;

[0056] The target control value is calculated based on the safety field information in the initial reference and used as the transition final value.

[0057] By using a smooth transition strategy, the current control quantity of the first control cycle is set as the transition start value. In each subsequent control cycle, the current control quantity is adjusted gradually based on the current control quantity of the previous control cycle, with an adjustment range not exceeding the preset change rate limit, until the current control quantity reaches the transition end value, thereby obtaining the braking control quantity and steering control quantity respectively.

[0058] In one possible implementation, the processing module is further configured to:

[0059] Perform longitudinal target spatial location clustering analysis on the safety field information in the initial baseline to identify whether there are obstacles ahead;

[0060] If it exists, the real-time deceleration is calculated based on the following distance between the vehicle and the obstacle, the relative speed difference, and the preset safety boundary, and is used as the transition final value of the braking dimension.

[0061] If it does not exist, then the two corresponding deceleration values ​​are calculated based on the preset maximum allowable deceleration time and the longest safe deceleration distance, and the smaller value is taken as the transition final value of the braking dimension.

[0062] In one possible implementation, the processing module is further configured to:

[0063] Extract the coefficients of the lane line polynomial equation from the safety field information in the initial benchmark to construct the lane line polynomial equation as a static lane line model.

[0064] The instantaneous vehicle speed and yaw rate are obtained to perform kinematic integration and determine the spatial offset of the vehicle reference frame relative to the static lane line model.

[0065] Adjust the lane line polynomial equation based on the spatial offset to determine the target lane line curvature at the current moment.

[0066] The corresponding numerical value is generated based on the curvature mapping of the target lane line, serving as the transitional final value for the steering dimension.

[0067] In one possible implementation, the processing module is further configured to:

[0068] When switching control modes, a multimodal driver takeover alert signal is generated;

[0069] The multimodal driver takeover alert signal is output to the in-vehicle human-machine interaction device for visual display.

[0070] In one possible implementation, the processing module is further configured to:

[0071] Continuously collect the driver's control input signals;

[0072] When the control input signal meets the preset takeover judgment conditions, stop sending braking control and steering control quantities, and resume transmitting driver operation commands.

[0073] In one possible implementation, the processing module is further configured to:

[0074] After time synchronization correction, the security field information is stored in the internal cache;

[0075] Based on the cached safety field information, braking backup parameters and steering backup parameters are calculated separately and used as backup safety control parameters. The backup safety control parameters are bound to and updated with the safety field information of the corresponding frame.

[0076] Thirdly, this application provides an electronic device, including: a memory and a processor;

[0077] The memory stores instructions that the computer executes;

[0078] The processor executes computer execution instructions stored in memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0079] Fourthly, this application provides a vehicle including a vehicle body and a microcontroller disposed on the vehicle body, wherein the microcontroller performs the first aspect and / or various possible implementations of the first aspect as described above.

[0080] Fifthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible embodiments of the first aspect.

[0081] In a sixth aspect, this application provides a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0082] This application provides a vehicle control method and vehicle. During the normal operation of the intelligent driving main control chip, the method synchronously receives vehicle control commands sent by the intelligent driving main control chip and safety field information of the vehicle's surrounding environment. During the transmission of vehicle control commands to the vehicle actuators, backup safety control parameters are calculated and stored based on the safety field information, thus pre-completing hot backup of environmental information and control parameters. When a fault is detected in the intelligent driving main control chip, the method locks the safety field information of the last frame before the fault and the corresponding backup safety control parameters as the initial reference for mode switching. Based on this initial reference, braking control and steering control quantities are generated through a preset smooth transition strategy and sent to the vehicle actuators to complete the control mode switch. In this way, in the scenario of intelligent driving main control chip failure, control takeover is achieved by relying on the pre-reserved effective environmental cognition, avoiding the fallback control from deviating from actual road conditions. At the same time, the smooth transition control quantity generation method reduces the abrupt amplitude of control commands, improves the smoothness of vehicle control switching, and effectively improves the reliability of vehicle control after the main control chip fails. Attached Figure Description

[0083] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0084] Figure 1 This application provides a schematic diagram of an application data processing system architecture.

[0085] Figure 2 Flowchart of the vehicle control method provided in the embodiments of this application Figure 1 ;

[0086] Figure 3 Flowchart of the vehicle control method provided in the embodiments of this application Figure 2 ;

[0087] Figure 4 Flowchart of the vehicle control method provided in the embodiments of this application Figure 3 ;

[0088] Figure 5 Flowchart of the vehicle control method provided in the embodiments of this application Figure 4 ;

[0089] Figure 6 This is a schematic diagram of the structure of the vehicle control device provided in the embodiments of this application;

[0090] Figure 7 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application;

[0091] Figure 8This is a structural schematic diagram of the vehicle provided in an embodiment of this application.

[0092] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0093] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0094] In the field of intelligent driving assistance systems and advanced autonomous driving systems, a dual-domain architecture is typically adopted, where the main control chip and the execution microcontroller work together. The main control chip is responsible for environmental perception, trajectory planning, and control decisions, while the execution microcontroller is responsible for forwarding low-level control commands, driving actuators, and safety monitoring. When the vehicle is operating in scenarios such as high-speed cruising, following other vehicles on urban expressways, and lane keeping, the system needs to continuously process the traffic flow around the vehicle, lane geometry, and the vehicle's motion status, and send relevant control quantities to the steering and braking actuators in real time.

[0095] In existing technologies, when the main control chip is working normally, it typically sends vehicle control commands to the execution microcontroller. The execution microcontroller only performs pass-through and basic verification of the commands. When the main control chip experiences abnormalities such as deadlock, overheating, or communication interruption, the system often switches to emergency braking, disengages from autonomous driving, or retains the control quantity at the moment of the fault based on a fixed threshold. This approach does not continuously cache the environmental context before the fault, making it difficult for the execution microcontroller to obtain continuous information about obstacles ahead, lane geometry, and traffic topology after taking over. Braking and steering control often become detached from real-time road conditions. At the same time, the fault switching process lacks constraints on the rate of change of control quantity, which can easily lead to sudden deceleration or steering angle changes at the moment of takeover, affecting vehicle stability and ride comfort. In severe cases, it can also cause lateral drift, sudden braking impact, and secondary safety risks.

[0096] In view of this, it is urgent to solve the problem of how to achieve reliable and safe takeover based on existing environmental information while maintaining control stability after the main control chip fails.

[0097] To address the aforementioned issues, this application provides a vehicle control method and a vehicle. During the normal operation of the intelligent driving main control chip, the method synchronously receives vehicle control commands sent by the intelligent driving main control chip and safety field information of the vehicle's surrounding environment. During the transmission of vehicle control commands to the vehicle actuators, backup safety control parameters are calculated and stored based on the safety field information, thus pre-completing a hot backup of the environmental information and control parameters. When a fault is detected in the intelligent driving main control chip, the method locks the safety field information of the last frame before the fault occurred and the corresponding backup safety control parameters as the initial reference for mode switching. Based on this initial reference, braking control and steering control quantities are generated using a preset smooth transition strategy, and then sent to the vehicle actuators to complete the control mode switch. In this way, in scenarios where the intelligent driving main control chip fails, control takeover is achieved based on pre-reserved effective environmental awareness, avoiding the fallback control from actual road conditions. Simultaneously, the smooth transition control quantity generation method reduces the abrupt change in control commands, improving the smoothness of the vehicle control switching process and effectively enhancing the reliability of vehicle control after the main control chip fails.

[0098] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0099] Figure 1 This is a schematic diagram of an application data processing system architecture provided in an embodiment of this application. The application data processing system 100 is a vehicle domain controller. Figure 1 As shown, the above architecture includes a data acquisition unit 101 and a processing unit 102.

[0100] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the architecture of the application data processing system. In other feasible embodiments of this application, the above architecture may include more or fewer components than illustrated, or combine some components, or split some components, or arrange different components, which can be determined according to the actual application scenario and is not limited here. Figure 1 The components shown can be implemented in hardware, software, or a combination of both.

[0101] In the specific implementation process, the data acquisition unit 101 may include an input / output interface or a communication interface, and the data acquisition unit 101 may be connected to the processing unit through the input / output interface or the communication interface.

[0102] The processing unit 102 can synchronously receive vehicle control commands and safety field information from the intelligent driving main control chip when it is running normally, and calculate and store backup safety control parameters during the transmission of commands. When a fault is detected in the main control chip, the last frame of safety field information and corresponding backup parameters before the fault are locked as the initial reference. Braking and steering control quantities are generated through a smooth transition strategy and sent to the vehicle actuators to achieve smooth control takeover under the failure of the main control chip.

[0103] It should be understood that the aforementioned processing device can be implemented by a processor reading instructions from memory and executing those instructions, or it can be implemented by a chip circuit.

[0104] Furthermore, the network architecture and business scenarios described in the embodiments of this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0105] Figure 2 Flowchart of the vehicle control method provided in the embodiments of this application Figure 1 ,like Figure 2 As shown, the vehicle control method provided in this embodiment includes:

[0106] S201. During normal operation of the intelligent driving main control chip, receive vehicle control commands and safety field information of the vehicle's surrounding environment synchronously sent by the intelligent driving main control chip.

[0107] For example, the intelligent driving master control chip can serve as the upper-level decision-making end for vehicle control. When it is in normal working condition, it can synchronously send vehicle control commands for controlling vehicle actuators and safety field information representing the traffic environment around the vehicle to the execution side through the vehicle high-speed communication bus. The execution side can be the execution microcontroller, the control execution sub-module in the domain control unit, or the edge control unit that undertakes forwarding and safety takeover functions.

[0108] In one possible implementation, the vehicle control command may include target values ​​corresponding to longitudinal and lateral control quantities, control mode identifiers, and control parameters related to the current driving conditions. The safety field information may include the position of obstacles ahead, relative speed, lane line position, lane geometry, and state information related to the vehicle's attitude.

[0109] After receiving the above information, the execution side will transmit the vehicle control command to the vehicle actuator through the original control link.

[0110] In one possible implementation, during normal communication, the intelligent driving main control chip generates a safety field feature vector stream with priority weights in real time based on the current driving topology complexity, and periodically broadcasts it with a high-precision time synchronization stamp. The execution microcontroller constructs a sliding window time alignment engine at the receiving end, combining high-frequency sampling data from the vehicle's inertial measurement unit to perform timestamp drift correction and state interpolation on the safety field feature vector stream, eliminating clock skew and data latency between heterogeneous chips. For the safety field information that has achieved time base unification and spatial alignment, the execution microcontroller stores it in an internal circular buffer, establishing a correspondence between frame number, timestamp, and parameter index on a frame-by-frame basis, achieving lossless caching and hot backup of environmental context data.

[0111] S202. During the process of transmitting vehicle control commands to the vehicle actuators, backup safety control parameters are calculated and stored based on the safety field information.

[0112] For example, during the transmission of vehicle control commands to the vehicle actuators, backup safety control parameters are calculated based on the current frame's safety field information and written to a preset storage area to maintain a control baseline corresponding to the current driving scenario. These backup safety control parameters can be control reference quantities for failover, including backup braking and steering parameters. During calculation, backup control quantities matching the current environment can be generated based on target distances, relative speeds, lane center offsets, and the vehicle's speed from the safety field information. If the safety field information is continuously updated, the backup safety control parameters are also updated accordingly, ensuring that the actuator always maintains a set of control backups corresponding to the current driving state.

[0113] The core of this step is to introduce safety field information into the execution side and form a backup of control parameters while the main control chip is controlling the vehicle normally, so that subsequent takeover can obtain control basis without relying on the environment to be sensed again after a fault.

[0114] Based on the above analysis, this step enables the execution side to hold the control reference corresponding to the current environment before the main control chip fails. After the fault occurs, the data of the last valid frame can be directly used for control transition, reducing the parameter gap when the control link is interrupted.

[0115] In one possible implementation, backup safety control parameters are calculated and stored based on safety field information, including:

[0116] After time synchronization correction, the safety field information is stored in the internal cache. Based on the cached safety field information, the braking backup parameters and steering backup parameters are calculated and used as backup safety control parameters. The backup safety control parameters are bound and updated with the safety field information of the corresponding frame.

[0117] In this embodiment, time synchronization correction refers to aligning the acquisition time of the security field information with the unified time reference of the main control chip before it enters the internal buffer, and compensating for the time delay deviation and sampling drift introduced by communication transmission, so that the same frame of security field information is consistent with the buffer timing on the execution microcontroller side.

[0118] The internal cache can be implemented by the storage unit inside the controller. The storage unit is used to save the corrected security field information and the backup security control parameters derived therefrom on a frame-by-frame basis. It can be continuously written in the form of a ring buffer so that the data of the most recent valid frame can be directly read when the main control chip is abnormal.

[0119] Braking reserve parameters are used to characterize the longitudinal control backup amount. Their calculation can generate corresponding deceleration or braking force requests based on information such as the distance to the target ahead, relative speed, road slope, and current vehicle speed in the buffer. Steering reserve parameters are used to characterize the lateral control backup amount. Their calculation can generate corresponding steering angles or steering angle increments based on lane geometry, lane curvature, vehicle lateral offset, and heading angle error.

[0120] Optionally, when the backup safety control parameters are bound and updated with the safety field information of the corresponding frame, a correspondence between the frame number, timestamp, and parameter index can be established in the cache entry, so that each frame of safety field information stores a set of backup braking parameters and backup steering parameters, and the binding relationship of the previous frame is overwritten and updated when a new frame arrives.

[0121] In one possible implementation, the execution microcontroller continuously monitors the computational load curve, memory usage slope, and communication link jitter frequency of the intelligent driving main control chip during the transmission of vehicle control commands. When an abnormal upward trend is detected but the hard fault threshold has not yet been triggered, the execution microcontroller proactively enters a pre-takeover preparation state. In this state, the computational boundaries of the backup safety control parameters are dynamically relaxed, and the initial phase and integral state of the smooth transition curve are initialized in advance, realizing a soft landing rehearsal of control and parameter warm-up before the fault occurs.

[0122] Through the above processing, the microcontroller simultaneously calculates longitudinal and lateral backup control parameters while caching safety field information, ensuring a one-to-one correspondence between parameters and frame data. This allows for direct retrieval of backup safety control parameters matching the last valid environmental state in the event of a main control chip failure, enabling continuous control of subsequent braking and steering. This approach maintains the timing consistency of cached data, clarifies the correspondence between backup control parameters and environmental context, and improves the accuracy of parameter retrieval during fault switching.

[0123] S203. Detect the operating status of the intelligent driving main control chip. When it is determined that the intelligent driving main control chip has failed, lock the safety field information of the last frame before the failure and the corresponding backup safety control parameters as the initial reference for mode switching.

[0124] For example, the execution side can continuously receive the operating status information of the main control chip; when the status information meets the fault judgment conditions within the preset detection window, it can be determined that the main control chip has failed.

[0125] Fault determination criteria may include abnormal operating status, communication verification error, or processing delay exceeding a threshold.

[0126] Upon detecting a fault, the execution side no longer uses potentially distorted new data. Instead, it stores the last frame of safety field information before the fault occurred, along with the corresponding backup safety control parameters, in a preset storage area as the starting data for subsequent control mode switching. Here, "last frame" refers to the data frame with the latest timestamp and completed reception verification before the fault is confirmed. This data frame maintains a one-to-one correspondence with the vehicle state and environmental state at that time.

[0127] To ensure the reference baseline is not overwritten during subsequent handover, the execution side can set a read-only lock flag for the data frame or freeze its contents in a separate buffer until the control mode switch is complete. Here, safety field information exists not only as the environmental context but is also bound to backup safety control parameters, ensuring the initial baseline includes both environmental state and control reference. In this way, the input no longer changes with invalid outputs after a main control chip failure during mode switching, thus maintaining data consistency during the takeover process.

[0128] Based on the above analysis, locking the last frame of information before the fault as the initial reference can ensure that the subsequently generated control quantities are directly based on the actual driving scenario before the fault, thus avoiding reference drift during the switching process.

[0129] In one possible implementation, detecting the operating status of the intelligent driving main control chip includes:

[0130] Acquire the health status flag signal sent by the intelligent driving main control chip; perform end-to-end integrity verification on the communication link with the intelligent driving main control chip; determine the operating status of the intelligent driving main control chip based on the health status flag signal and the verification result of the end-to-end integrity verification.

[0131] In this embodiment, the health status flag signal is used to characterize the current healthy operating status of the intelligent driving main control chip. It is usually sent by the main control chip in the form of periodic heartbeat frames, status codes or health indicator bits. After receiving it, the execution side compares it with the preset normal status.

[0132] The communication link is used to carry data transmission between the intelligent driving main control chip and the execution side. The end-to-end integrity check is used to verify whether the data transmitted by the link is complete, valid and without frame loss, out-of-order or tampering. The check can be completed based on the incremental sequence number, cyclic redundancy check code and reception delay threshold.

[0133] The operating status is used to describe whether the main control chip is currently in a normal working state, and serves as the basis for subsequent fault diagnosis and control switching.

[0134] In its implementation, the intelligent driving main control chip sends a health status flag signal through its communication-connected execution microcontroller. This signal can be encapsulated within the status field of a control message or set up as an independent health monitoring message. The sending cycle is synchronized with or slightly shorter than the control cycle. Upon receiving the health status flag signal, the execution microcontroller first verifies whether the signal content matches a preset normal state. Then, it performs a joint verification of the sequence number, checksum, and reception timestamp in the message to confirm whether the communication link maintains end-to-end integrity during transmission, forwarding, and reception.

[0135] When the health status indicator signal is normal and the end-to-end integrity check passes, the main control chip is determined to be in normal operating condition; when the health status indicator signal is abnormal, the message times out, the sequence number changes continuously, or the check code is inconsistent, the main control chip is determined to be in abnormal operating condition, and the determination result is output to the subsequent control logic.

[0136] The aforementioned determination method confirms the status of the main control chip by combining health status flag signals with communication link integrity verification. The health characteristics of the main control chip and the validity of link transmission can mutually verify each other, providing a stable status input for fault takeover. Using this method, the operational status judgment results are more suitable for directly triggering the activation of backup control parameters and mode switching, thereby improving the consistency and reliability of fault identification.

[0137] In one possible implementation, based on the above, a fault in the intelligent driving main control chip is determined in the following way:

[0138] If the health status indicator signal is inconsistent with the preset normal status, or if the verification result is not passed, it is marked as an abnormality and the duration of the abnormality begins to accumulate; when the duration of the abnormality exceeds the preset fault tolerance threshold, it is determined that the intelligent driving main control chip has malfunctioned.

[0139] In the specific implementation, the execution microcontroller receives the health status flag signal and performs link verification in each monitoring cycle. When any result indicates an anomaly, the current time is set as the starting point of the anomaly and the duration of the anomaly is accumulated. The accumulation can be achieved based on the system clock count or calculated based on the number of consecutive abnormal frames.

[0140] If the health status indicator signal recovers to the preset normal state and the verification result passes in a subsequent cycle, the abnormal timer is cleared and monitoring is restarted; if the abnormal state persists and the cumulative duration reaches the set boundary, the fault judgment result is output and reported to the control logic.

[0141] This judgment method ensures that short-term jitter, instantaneous packet loss, or single-frame verification failure are only recorded as detection anomalies, rather than being immediately escalated to a fault state.

[0142] During operation, the accumulation of anomalies is compared with a threshold to form the fault confirmation condition. Only when the anomaly exceeds the preset fault tolerance threshold continuously is the fault state confirmed and transmitted to the subsequent control module. This processing method can distinguish between transient disturbances and persistent failures, making the fault judgment of the main control chip more stable, and providing a reliable trigger condition for locking the last frame of safety field information and switching control modes.

[0143] S204. Based on the initial reference, generate braking control quantity and steering control quantity through a preset smooth transition strategy.

[0144] For example, the smooth transition strategy can be implemented by the transition control logic built into the execution side, with the input being the safety field information and backup safety control parameters locked in step S203, and the output being the braking control quantity and steering control quantity used to take over the actuator.

[0145] In one possible implementation, the execution side gradually adjusts the current control quantity based on backup safety control parameters and the current vehicle state, so that it smoothly approaches the control target that matches the current environment, thereby avoiding abrupt changes in the control quantity.

[0146] Braking control variables are used to control the longitudinal deceleration of the vehicle. When generating them, the distance to the forward target, relative speed, target motion trend, and current vehicle speed in the safety field information can be combined to determine the deceleration target suitable for failover. Steering control variables are used to control the lateral trajectory of the vehicle. When generating them, the lane line position, lane centerline offset, vehicle heading angle, and yaw rate can be combined to determine the steering target suitable for maintaining stable vehicle driving.

[0147] The smooth transition strategy does not directly switch the control quantity to the target value, but adjusts it gradually according to the initial reference and the current vehicle state, so that both longitudinal and lateral control change along a continuous curve.

[0148] If the vehicle is in a straight-ahead, following, or lane-keeping mode when the switch is initiated, the braking control and steering control quantities can be generated at different convergence rates, but both are limited by a preset smoothing strategy to ensure that the control actions do not undergo synchronous abrupt changes during mode switching.

[0149] The purpose of this step is to smoothly extend the control baseline before the fault to the control output after the takeover, so that the vehicle maintains continuous operation when control is transferred.

[0150] Based on the above analysis, it can be seen that by generating control quantities through a smooth transition strategy, the actuator can obtain continuously changing braking and steering inputs, thereby enabling a smooth transition between the fault takeover process and the original control state.

[0151] S205. The braking control quantity and steering control quantity are sent to the vehicle actuator to switch the control mode.

[0152] For example, after generating the braking control quantity and steering control quantity corresponding to the current control cycle, the execution side can synchronously send them to the braking execution unit and steering execution unit through the control interface corresponding to the vehicle actuator. The control interface can be a vehicle bus, a pulse width modulation interface, an analog output interface, or other control channels that match the actuator drive circuit.

[0153] In one possible implementation, the braking control quantity is used to replace the longitudinal control command before the main control chip fails, and the braking actuator establishes or adjusts the braking torque accordingly; the steering control quantity is used to replace the lateral control command before the main control chip fails, and the steering actuator establishes or adjusts the front wheel angle accordingly.

[0154] The actuator can output both types of control quantities simultaneously within the same control cycle to maintain the timing consistency of longitudinal and lateral control, avoiding asynchronous braking and steering during mode switching. After the control mode switch is completed, the vehicle actuator enters the control mode based on the actuator takeover logic, and subsequent control quantities continue to be updated according to the smooth transition strategy until the vehicle enters a safer operating state or other preset termination state.

[0155] If the system detects that the vehicle has entered a stable deceleration phase or the vehicle speed has dropped below the threshold, the execution side can maintain the current control quantity or end the takeover mode according to the preset exit strategy.

[0156] The core of this step is to directly apply the aforementioned generated control quantity to the actuator, so that the vehicle can continue to receive continuous control even after the main control chip fails.

[0157] In one possible implementation, when switching control modes, a multimodal driver takeover alert signal is generated; the multimodal driver takeover alert signal is output to the in-vehicle human-machine interaction device for visualization; the driver's operation input signals are continuously collected; when the operation input signals meet the preset takeover judgment conditions, the transmission of braking control and steering control quantities is stopped, and the transparent transmission of driver operation commands is resumed.

[0158] Specifically, after triggering the takeover alert, the microcontroller collects real-time data on the driver's eye gaze direction, hand contact resistance, and micro-motion posture to construct a driver takeover readiness index. When the takeover readiness index reaches the decision threshold, instead of directly cutting off the autonomous control output, a time-varying hybrid coefficient is introduced. The braking control quantity and steering control quantity are weighted and fused with the driver's operation command respectively. As the amplitude of the driver's operation input signal increases and the fluctuation frequency tends to stabilize, the time-varying hybrid coefficient dynamically shifts towards the manual command until the autonomous control weight corresponding to the backup safety control parameter naturally decays to zero, thus completing the handover of control.

[0159] Based on the above analysis, it can be seen that by sending the braking control quantity and steering control quantity to the vehicle actuator, the control can be smoothly transferred from the failed main control chip to the execution side, realizing continuous control and mode switching after the fault.

[0160] In one possible implementation, after sending the braking control quantity and steering control quantity to the vehicle actuators to switch the control mode, the method further includes:

[0161] When switching control modes, a multimodal driver takeover alert signal is generated; the multimodal driver takeover alert signal is output to the in-vehicle human-machine interaction device for visual display.

[0162] In this embodiment, the multimodal driver takeover alert signal is a composite alert signal used to issue a takeover alert to the driver during the control mode switching phase. It can be composed of at least one combination of visual cues, auditory cues, and tactile cues, and corresponds to the current control state of the vehicle.

[0163] The vehicle-mounted human-machine interaction device is a vehicle-mounted display terminal used to receive, analyze and present the prompt signal. It can correspond to one or more of the following: instrument display screen, central control display screen, head-up display device, steering wheel prompt unit or sound and light linkage prompt unit. In practical applications, other models of the device can also be selected, and this application does not limit them.

[0164] When the control mode switch is triggered, the controller generates a multimodal driver takeover reminder signal based on the main control chip fault determination result, the current takeover request status, and the vehicle operating status. The signal is then encoded to include information such as the takeover reason, takeover level, reminder duration, and the current vehicle control mode.

[0165] Subsequently, the controller sends the signal to the vehicle human-machine interface via the vehicle communication interface. After receiving the signal, the vehicle human-machine interface controls the corresponding display interface to display the visual information through icons, text, color changes, or flashing animations. At the same time, it can also issue prompt sounds or vibration feedback, so that the driver can visually perceive the change in vehicle control and perform takeover operations in a timely manner.

[0166] This structure synchronously transmits takeover requests to the driver during control mode switching, and the information is displayed on the in-vehicle human-machine interface, ensuring that takeover prompts are consistent with changes in vehicle control status. Because the prompt signals contain multimodal information and are visualized via the in-vehicle terminal, the driver's recognition of the takeover timing is more direct, thus establishing a temporal correspondence between control switching and driver intervention.

[0167] With the above implementation, the takeover information during control mode switching can be conveyed to the driver in a timely and clear manner, reducing the driver's misjudgment of system status changes and enabling the driver to complete the takeover response more quickly. At the same time, the combination of multimodal prompts and visual display can enhance the perception intensity of the takeover signal and make the connection between the control mode switching process and the driver's operation more stable.

[0168] In one possible implementation, based on the above-described implementation, the vehicle control method further includes:

[0169] The system continuously collects the driver's control input signals; when the control input signals meet the preset takeover judgment conditions, it stops sending braking control and steering control signals and resumes transmitting driver operation commands.

[0170] In this embodiment, the control input signal is used to characterize the driver's intention to control the vehicle. It can be composed of one or more of the following: steering wheel angle, steering wheel torque, brake pedal opening, and accelerator pedal opening, and is acquired in real time by a data acquisition unit installed on the steering wheel shaft, pedal assembly, or steering column.

[0171] The preset takeover judgment condition is used to identify whether the driver has the intention and ability to take over the vehicle. It can be determined by the amplitude and duration of the control input and the trend of signal change. For example, when the steering wheel torque continuously exceeds the preset threshold, the brake pedal opening is continuously kept within the set range, or the steering input shows a stable and continuous change, it is determined that the driver requests takeover.

[0172] The driver's operating commands are used as vehicle control inputs again after the handover of control. After receiving the takeover determination result, the microcontroller sets the braking control and steering control quantities that were originally output to the vehicle actuators to a stop sending state and switches to a pass-through forwarding state for driver input signals, so that the driver's operating inputs directly act on the corresponding actuators.

[0173] In practical implementation, the microcontroller can filter, debouncing, and perform time window statistics on the acquired control input signals to distinguish between short-term false triggers and genuine takeover intentions. The analog signals output by the acquisition unit are converted into digital signals through analog-to-digital conversion, or directly transmitted to the microcontroller via the vehicle bus. The microcontroller performs a comparison based on preset takeover judgment conditions. Once the conditions are met, it immediately closes the original control signal transmission channel and maps the driver's operation commands to the steering and braking output channels.

[0174] It should be noted that if the vehicle adopts a dual-domain architecture, the switching process can be completed independently by the execution microcontroller, while the main control chip only retains state synchronization and does not participate in the direct control after takeover. In practical applications, other models of this component can also be selected, and this application does not limit this.

[0175] In this way, the system can promptly exit autonomous control and restore manual operation when the driver clearly takes over, so that the vehicle control is smoothly transferred back to the driver, maintaining the consistency between the executed instructions and the driver's intentions, and making the control handover process work in conjunction with the aforementioned fault fallback control logic, thereby improving the control continuity and operational responsiveness during takeover.

[0176] This application provides a vehicle control method that, during the normal operation of the intelligent driving main control chip, synchronously receives vehicle control commands sent by the intelligent driving main control chip and safety field information of the vehicle's surrounding environment. During the transmission of vehicle control commands to the vehicle actuators, backup safety control parameters are calculated and stored based on the safety field information, thus pre-completing a hot backup of the environmental information and control parameters. When a fault is detected in the intelligent driving main control chip, the safety field information of the last frame before the fault and the corresponding backup safety control parameters are locked as the initial reference for mode switching. Based on this initial reference, braking control and steering control quantities are generated through a preset smooth transition strategy and sent to the vehicle actuators to complete the control mode switch. In this way, in scenarios where the intelligent driving main control chip fails, control takeover is achieved based on pre-reserved effective environmental knowledge, avoiding the fallback control from deviating from actual road conditions. Simultaneously, the smooth transition control quantity generation method reduces the abrupt change in control commands, improving the smoothness of the vehicle control switching process and effectively enhancing the reliability of vehicle control after the main control chip fails.

[0177] Figure 3 Flowchart of the vehicle control method provided in the embodiments of this application Figure 2 ,like Figure 3 As shown, this embodiment, based on the above embodiments, provides a detailed explanation of the specific process for generating braking control quantities and steering control quantities, including:

[0178] S301. Use the spare safety control parameters in the initial reference as the transition start value.

[0179] For example, the initial baseline is the last frame of information locked before the intelligent driving main control chip fails. The backup safety control parameters are hot backups of control parameters that are synchronously calculated and continuously updated during the transmission of vehicle control commands by the intelligent driving main control chip during normal operation, covering two independent dimensions: braking control and steering control.

[0180] Setting this backup safety control parameter as the transition start value ensures the complete inheritance of the vehicle control state at the moment of the fault, guaranteeing a seamless transition between the mode switching start point and the original control state, and providing a continuous initial benchmark for a smooth transition. Backup parameter values ​​for the corresponding dimensions are extracted from the braking and steering control channels respectively, serving as the transition start value for each channel.

[0181] S302. Based on the safety field information in the initial reference, calculate the target control quantity value as the transition final value.

[0182] For example, the safety field information in the initial reference includes motion state parameters of obstacles in all directions around the vehicle, geometric feature parameters of the lane lines ahead, and intersection-related information.

[0183] Based on this safety field information, target values ​​are calculated for both the braking and steering dimensions:

[0184] The braking dimension first identifies whether there are obstacles ahead, and then matches the corresponding deceleration calculation logic to obtain the target deceleration value;

[0185] The steering dimension is calculated based on lane line geometry parameters and the real-time motion state of the vehicle to obtain the target steering control value.

[0186] The calculation results of the two dimensions together constitute the target control quantity value, which serves as the final transition value that the smooth transition process needs to achieve, so that the final control output can match the actual traffic environment and road conditions before the fault occurred.

[0187] S303. Using a smooth transition strategy, the current control quantity of the first control cycle is set as the transition start value. In each subsequent control cycle, the current control quantity is adjusted gradually based on the current control quantity of the previous control cycle, with an adjustment range not exceeding the preset change rate limit, until the current control quantity reaches the transition end value, thereby obtaining the braking control quantity and steering control quantity respectively.

[0188] For example, the smooth transition strategy achieves continuous change of control quantity by limiting the maximum change of control quantity per unit time. Independent change rate limits are set for braking dimension and steering dimension respectively. The maximum allowable adjustment within a single control cycle is determined by the change rate limit and the control cycle duration.

[0189] The change in the control quantity in the braking dimension satisfies the following constraint relationship:

[0190]

[0191] in, For the first Braking control quantity during the control cycle For the first Braking control quantity during the control cycle The preset limit for the rate of change of deceleration. The duration of a single control cycle.

[0192] The changes in the control quantity in the steering dimension satisfy the following constraints:

[0193]

[0194] in, For the first Steering control quantity during the control cycle. For the first Steering control quantity during the control cycle. The preset limit for the rate of change of steering angle. The duration of a single control cycle.

[0195] In the first control cycle, the initial transition value is directly output as the current control quantity. Starting from the second control cycle, each cycle uses the current control quantity of the previous cycle as a reference and adjusts the control quantity towards the final transition value, with the adjustment range within a single cycle not exceeding the preset rate of change limit. Through this cycle-by-cycle progressive adjustment, the current control quantity gradually approaches the final transition value. When the current control quantity matches the final transition value, the smooth transition process is completed, and the final braking and steering control quantities are output.

[0196] The vehicle control method provided in this application, by using backup safety control parameters as transition start values, can completely inherit the vehicle control state at the moment of fault occurrence, ensuring a seamless connection between the mode switching start point and the original control state. The target control quantity calculated based on locked safety field information is used as the transition end value, allowing the final control output to match the actual traffic environment and road conditions before the fault. By gradually adjusting the control quantity through a cycle-by-cycle amplitude-limited smooth transition strategy, abrupt changes in the control quantity can be avoided, ensuring vehicle stability and ride comfort during mode switching.

[0197] Figure 4 Flowchart of the vehicle control method provided in the embodiments of this application Figure 3 ,like Figure 4 As shown, this embodiment, based on the above embodiments, provides a detailed explanation of a specific process for calculating the target control variable value based on the safety field information in the initial reference, as a transitional final value, including:

[0198] S401. Perform longitudinal target spatial location clustering analysis on the safety field information in the initial benchmark to identify whether there are obstacles ahead.

[0199] For example, the safety field information in the initial baseline includes environmental data such as the longitudinal distance, longitudinal speed, and lateral position of each target in the area in front of the vehicle. The longitudinal target spatial position clustering analysis is based on the longitudinal coordinates of the target, the lateral lane affiliation, and the distance between adjacent targets. It groups and aggregates the forward discrete target points, distinguishes the same-direction targets and stationary obstacles in the same lane from other lanes and distant irrelevant targets, and clarifies the obstacle objects occupying the vehicle's driving lane, providing a basis for subsequent deceleration calculations in different scenarios.

[0200] S402. If present, calculate the real-time deceleration based on the following distance between the vehicle and the obstacle, the relative speed difference, and the preset safety boundary, as the transition final value of the braking dimension.

[0201] For example, the preset safety boundary is used to limit the minimum safe approach margin of the vehicle at the current vehicle speed. During the calculation process, the closer the following distance is to the preset safety boundary and the greater the relative speed difference between the vehicle and the obstacle, the higher the output real-time deceleration. The obtained deceleration can match the current following conditions and ensure that the vehicle maintains a safe distance from the obstacle in front. This real-time deceleration serves as the transition final value of the braking dimension and participates in the subsequent smooth transition calculation.

[0202] S403. If not, calculate the two corresponding deceleration values ​​based on the preset maximum allowable deceleration time and the longest safe deceleration distance, and take the smaller value as the transition final value of the braking dimension.

[0203] For example, the deceleration obtained by working backward from the maximum permissible deceleration time corresponds to the comfort braking constraint, and the deceleration obtained by working backward from the longest safe deceleration distance corresponds to the braking distance safety constraint.

[0204] The formula for calculating deceleration based on the maximum permissible deceleration time is as follows:

[0205]

[0206] in, The deceleration corresponding to the maximum permissible deceleration time. The instantaneous speed of the vehicle. This is the preset maximum allowable deceleration time.

[0207] The formula for calculating deceleration based on the longest safe deceleration distance is:

[0208]

[0209] in, The deceleration corresponding to the longest safe deceleration distance. The instantaneous speed of the vehicle. This is the preset maximum safe deceleration distance.

[0210] Finally, the smaller of the two deceleration values ​​is taken as the transition final value of the braking dimension, that is:

[0211]

[0212] Taking the smaller of the two values ​​prioritizes ride comfort at low speeds and ensures sufficient braking distance at high speeds. The resulting deceleration is adapted to driving conditions without obstacles ahead and serves as the transitional final value for the braking dimension.

[0213] The vehicle control method provided in this application performs longitudinal target spatial position clustering analysis on the safety field information in the initial reference, which can accurately identify the state of obstacles ahead and provide a basis for calculating braking target values ​​in different scenarios. When there are obstacles ahead, the real-time deceleration is calculated by combining the following distance, relative speed difference, and preset safety boundary to ensure that the vehicle maintains a safe distance from the target ahead. When there are no obstacles ahead, the smaller deceleration corresponding to the maximum allowable deceleration time and the longest safe deceleration distance is taken into account, which can balance ride comfort and braking distance safety.

[0214] Figure 5 Flowchart of the vehicle control method provided in the embodiments of this application Figure 4 ,like Figure 5 As shown, this embodiment, based on the above embodiments, provides a detailed explanation of another specific process for calculating the target control variable value based on the safety field information in the initial reference, as a transitional final value, including:

[0215] S501. Extract the coefficients of the lane line polynomial equation from the safety field information in the initial benchmark to construct the lane line polynomial equation as a static lane line model.

[0216] For example, the safety field information in the initial baseline includes the lane line fitting parameters acquired in the last frame before the fault. The lane line polynomial equation uses a fifth-order form to describe the corresponding geometric relationship between the lane lateral offset and the longitudinal distance, and is constructed by the extracted coefficients and intercepts of each order.

[0217] The specific form of the lane line polynomial equation is as follows:

[0218]

[0219] in, This represents the lateral offset of the lane line relative to the vehicle's reference frame. This represents the longitudinal distance of the lane line relative to the vehicle's reference frame. to Let be the coefficients of the lane line polynomial equation, where For the intercept term, to These are the coefficients of the first to fifth degree terms, respectively.

[0220] This static lane line model provides a fixed geometric reference for steering calculations after a fault takeover. It is no longer updated after the main control chip fails, and always uses the lane geometry at the time of the fault as the basis for calculation.

[0221] S502. Obtain the instantaneous vehicle speed and yaw rate to perform kinematic integration and determine the spatial offset of the vehicle reference frame relative to the static lane line model.

[0222] For example, the instantaneous vehicle speed reflects the longitudinal motion state of the vehicle, and the yaw rate reflects the attitude change of the vehicle around the vertical axis. Based on the vehicle's planar motion model, the two types of motion parameters are kinematically integrated within the control cycle to calculate the longitudinal displacement change and lateral pose offset of the vehicle. These are then integrated into the spatial offset of the vehicle's reference frame relative to the static lane line model, reflecting the relative position change of the vehicle with respect to the original lane line model after it has started moving.

[0223] S503. Adjust the lane line polynomial equation according to the spatial offset to determine the target lane line curvature at the current moment.

[0224] For example, the static lane line polynomial equation is corrected by lateral translation and yaw rotation according to the spatial offset to obtain the real-time lane line equation that matches the current vehicle position. Then, the modified lane line polynomial equation is differentiated to calculate the curvature of the target lane line corresponding to the current vehicle position, so that the curvature calculation result matches the real-time driving position of the vehicle.

[0225] S504. Generate corresponding values ​​based on the curvature mapping of the target lane line, as the transition final value of the steering dimension.

[0226] For example, based on a preset mapping relationship between curvature and steering control quantity, and combined with the current instantaneous vehicle speed, the curvature of the target lane line is converted into the corresponding steering control value.

[0227] The mapping relationship of the steering control values ​​satisfies:

[0228]

[0229] in, The transition terminal value for the shift dimension. For the target lane line curvature, The instantaneous speed of the vehicle. This is a preset curvature-steering amount mapping function.

[0230] The aforementioned steering control values ​​are the transition final values ​​of the steering dimension, which can be directly input into the subsequent smooth transition process as the target values ​​that the steering control quantity gradually approaches.

[0231] The vehicle control method provided in this application constructs a static lane line model by extracting the coefficients of the lane line polynomial equation. This provides a fixed geometric reference for steering calculations after fault takeover, inheriting the lane geometry at the time of the fault. By combining the vehicle's instantaneous speed and yaw rate to perform kinematic integration to determine the spatial offset, the relative pose change between the vehicle and the original lane line model can be accurately calculated. Adjusting the lane line polynomial equation based on the spatial offset to determine the target lane line curvature allows the curvature calculation results to match the vehicle's real-time driving position. Generating the transition final value of the steering dimension through target lane line curvature mapping provides a steering target reference that matches lane conditions for subsequent smooth transitions.

[0232] Figure 6 This is a schematic diagram of the vehicle control device provided in an embodiment of this application. The device in this embodiment can be in the form of software and / or hardware. Figure 6 As shown, the vehicle control device 600 provided in this application embodiment includes: a receiving module 601 and a processing module 602.

[0233] The receiving module 601 is used to receive vehicle control commands and safety field information of the vehicle's surrounding environment synchronously sent by the intelligent driving main control chip during normal operation of the intelligent driving main control chip.

[0234] The processing module 602 is used to calculate and store backup safety control parameters based on safety field information during the process of transmitting vehicle control commands to the vehicle actuators.

[0235] The processing module 602 is also used to detect the operating status of the intelligent driving main control chip. When it is determined that the intelligent driving main control chip has failed, it locks the safety field information of the last frame before the failure and the corresponding backup safety control parameters as the initial reference for mode switching.

[0236] The processing module 602 is also used to generate braking control quantity and steering control quantity based on the initial reference and through a preset smooth transition strategy;

[0237] The processing module 602 is also used to send braking control quantities and steering control quantities to the vehicle actuators for control mode switching.

[0238] In one possible implementation, the processing module 602 is further configured to:

[0239] Acquire the health status indicator signal sent by the intelligent driving main control chip;

[0240] Perform end-to-end integrity verification on the communication link between the main control chip and the intelligent driving system.

[0241] The operating status of the intelligent driving main control chip is determined based on the health status indicator signal and the verification result of the end-to-end integrity check.

[0242] In one possible implementation, the processing module 602 is further configured to:

[0243] If the health status indicator signal is inconsistent with the preset normal status, or if the verification result is not passed, it will be marked as an abnormality and the duration of the abnormality will begin to accumulate.

[0244] When the duration of the anomaly exceeds the preset fault tolerance threshold, the intelligent driving main control chip is determined to have malfunctioned.

[0245] In one possible implementation, the processing module 602 is further configured to:

[0246] Use the spare safety control parameters in the initial baseline as the transition starting values;

[0247] The target control value is calculated based on the safety field information in the initial reference and used as the transition final value.

[0248] By using a smooth transition strategy, the current control quantity of the first control cycle is set as the transition start value. In each subsequent control cycle, the current control quantity is adjusted gradually based on the current control quantity of the previous control cycle, with an adjustment range not exceeding the preset change rate limit, until the current control quantity reaches the transition end value, thereby obtaining the braking control quantity and steering control quantity respectively.

[0249] In one possible implementation, the processing module 602 is further configured to:

[0250] Perform longitudinal target spatial location clustering analysis on the safety field information in the initial baseline to identify whether there are obstacles ahead;

[0251] If it exists, the real-time deceleration is calculated based on the following distance between the vehicle and the obstacle, the relative speed difference, and the preset safety boundary, and is used as the transition final value of the braking dimension.

[0252] If it does not exist, then the two corresponding deceleration values ​​are calculated based on the preset maximum allowable deceleration time and the longest safe deceleration distance, and the smaller value is taken as the transition final value of the braking dimension.

[0253] In one possible implementation, the processing module 602 is further configured to:

[0254] Extract the coefficients of the lane line polynomial equation from the safety field information in the initial benchmark to construct the lane line polynomial equation as a static lane line model.

[0255] The instantaneous vehicle speed and yaw rate are obtained to perform kinematic integration and determine the spatial offset of the vehicle reference frame relative to the static lane line model.

[0256] Adjust the lane line polynomial equation based on the spatial offset to determine the target lane line curvature at the current moment.

[0257] The corresponding numerical value is generated based on the curvature mapping of the target lane line, serving as the transitional final value for the steering dimension.

[0258] In one possible implementation, the processing module 602 is further configured to:

[0259] When switching control modes, a multimodal driver takeover alert signal is generated;

[0260] The multimodal driver takeover alert signal is output to the in-vehicle human-machine interaction device for visual display.

[0261] In one possible implementation, the processing module 602 is further configured to:

[0262] Continuously collect the driver's control input signals;

[0263] When the control input signal meets the preset takeover judgment conditions, stop sending braking control and steering control quantities, and resume transmitting driver operation commands.

[0264] In one possible implementation, the processing module 602 is further configured to:

[0265] After time synchronization correction, the security field information is stored in the internal cache;

[0266] Based on the cached safety field information, braking backup parameters and steering backup parameters are calculated separately and used as backup safety control parameters. The backup safety control parameters are bound to and updated with the safety field information of the corresponding frame.

[0267] The vehicle control device 600 provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0268] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 7 As shown, the electronic device 700 provided in this embodiment includes at least one processor 701 and a memory 702. Optionally, the electronic device 700 further includes a communication component 703. The processor 701, memory 702, and communication component 703 are connected via a bus.

[0269] In a specific implementation, at least one processor 701 executes computer execution instructions stored in memory 702, causing at least one processor 701 to perform the above-described method.

[0270] The specific implementation process of processor 701 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0271] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0272] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0273] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0274] Figure 8 This is a structural schematic diagram of the vehicle provided in the embodiments of this application, such as... Figure 8 As shown, the vehicle 800 provided in this embodiment includes a vehicle body 801 and a microcontroller 802 disposed on the vehicle body 801;

[0275] In the specific implementation process, the microcontroller 802 is used to implement the above method.

[0276] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0277] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0278] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0279] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0280] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0281] The units described as separate components may or may not be physically separate. 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 the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0282] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0283] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0284] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0285] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A vehicle control method characterized by, include: During normal operation of the intelligent driving main control chip, the vehicle receives vehicle control commands and safety field information of the vehicle's surrounding environment synchronously sent by the intelligent driving main control chip. During the process of transmitting the vehicle control commands to the vehicle actuators, backup safety control parameters are calculated and stored based on the safety field information; The operating status of the intelligent driving main control chip is detected. When it is determined that the intelligent driving main control chip has failed, the safety field information and the corresponding backup safety control parameters of the last frame before the failure are locked as the initial reference for mode switching. Based on the initial reference, braking control and steering control quantities are generated using a preset smooth transition strategy. The braking control quantity and the steering control quantity are sent to the vehicle actuator to switch the control mode.

2. The method of claim 1, wherein, The detection of the operating status of the intelligent driving main control chip includes: Obtain the health status indicator signal sent by the intelligent driving main control chip; Perform end-to-end integrity verification on the communication link with the intelligent driving main control chip; The operating status of the intelligent driving main control chip is determined based on the health status flag signal and the verification result of the end-to-end integrity check.

3. The method of claim 2, wherein, The fault in the intelligent driving main control chip is determined in the following ways: If the health status indicator signal is inconsistent with the preset normal status, or if the verification result is not passed, it is marked as an abnormality and the duration of the abnormality begins to accumulate. When the duration of the anomaly exceeds a preset fault tolerance threshold, the intelligent driving main control chip is determined to have malfunctioned.

4. The method of claim 1, wherein, The step of generating braking control and steering control quantities based on the initial reference and through a preset smooth transition strategy includes: The backup safety control parameters in the initial benchmark are used as the transition start values; The target control value is calculated based on the safety field information in the initial reference, and is used as the transition final value; The smooth transition strategy sets the current control quantity of the first control cycle as the transition start value. In each subsequent control cycle, the current control quantity is adjusted gradually based on the current control quantity of the previous control cycle, with an adjustment range not exceeding a preset change rate limit, until the current control quantity reaches the transition end value, thereby obtaining the braking control quantity and the steering control quantity.

5. The method of claim 4, wherein, The step of calculating the target control variable value based on the safety field information in the initial reference, as the transition final value, includes: Perform longitudinal target spatial location clustering analysis on the safety field information in the initial benchmark to identify whether there are obstacles ahead; If present, the real-time deceleration is calculated based on the following distance between the vehicle and the obstacle, the relative speed difference, and the preset safety boundary, and is used as the transition final value of the braking dimension. If it does not exist, then the two corresponding deceleration values ​​are calculated based on the preset maximum allowable deceleration time and the longest safe deceleration distance, and the smaller value is taken as the transition final value of the braking dimension.

6. The method of claim 4, wherein, The step of calculating the target control variable value based on the safety field information in the initial reference, as the transition final value, includes: Extract the coefficients of the lane line polynomial equation from the safety field information in the initial reference to construct the lane line polynomial equation as a static lane line model. The instantaneous vehicle speed and yaw rate are obtained to perform kinematic integration and determine the spatial offset of the vehicle reference frame relative to the static lane line model. The lane line polynomial equation is adjusted based on the spatial offset to determine the target lane line curvature at the current moment. The corresponding numerical value is generated based on the curvature mapping of the target lane line, serving as the transitional final value for the steering dimension.

7. The method according to any one of claims 1-6, characterized in that, Also includes: When switching the control mode, a multimodal driver takeover alert signal is generated; The multimodal driver takeover alert signal is output to the in-vehicle human-machine interaction device for visualization.

8. The method according to claim 7, characterized in that, Also includes: Continuously collect the driver's control input signals; When the control input signal meets the preset takeover judgment condition, the transmission of the braking control quantity and the steering control quantity is stopped, and the transmission of driver operation commands is resumed.

9. The method according to claim 1, characterized in that, The step of calculating and storing backup safety control parameters based on the safety field information includes: The security field information is stored in the internal cache after time synchronization correction. Based on the cached safety field information, braking backup parameters and steering backup parameters are calculated respectively and used as backup safety control parameters. The backup safety control parameters are bound and updated with the safety field information of the corresponding frame.

10. A vehicle, characterized in that, The system includes a vehicle body and a microcontroller disposed on the vehicle body; wherein the microcontroller performs the method as described in any one of claims 1-9.