Safety planning system for autonomous driving vehicle and safety planning method therefor

By integrating active safety control functions into path planning control in autonomous vehicles and utilizing various types of sensors and controllers to calculate dynamic boundaries, the problem of autonomous driving controllers losing control under extreme conditions is solved, achieving higher safety performance and stability.

WO2024244106A1PCT designated stage expired Publication Date: 2024-12-05TSINGHUA UNIVERSITY

Patent Information

Application Number
PCT/CN2023/104904
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-26
Filing Date
2023-06-30
Publication Date
2024-12-05

AI Technical Summary

Technical Problem

Under extreme dynamic conditions, the sudden intervention of the active safety controller of an autonomous vehicle can cause the autonomous driving controller to temporarily lose its control capabilities, making it unable to fully control the dynamics of the vehicle, which can easily lead to safety accidents and fail to fully utilize autonomous driving perception information and high computing power to improve safety performance.

Method used

Active safety control functions are integrated into vehicle path planning and control. By using various types of sensors, autonomous driving domain controllers and chassis domain controllers, perception information is fused to calculate dynamic boundaries and impose safety restrictions on the path, generating wheel speed control commands to ensure that safety functions such as ABS are not triggered during chassis path tracking control and dynamic control.

Benefits of technology

It improves the safety performance of autonomous vehicles, reduces the triggering of safety functions such as ABS/ESC/TCS, makes full use of autonomous driving perception and decision-making capabilities, and improves the safety and stability of vehicles.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2023104904_05122024_PF_FP_ABST
    Figure CN2023104904_05122024_PF_FP_ABST
Patent Text Reader

Abstract

A safety planning system for an autonomous driving vehicle and a safety planning method therefor. The system comprises: multiple types of sensors (10), which are used for collecting a plurality of sensor signals of a vehicle; an autonomous driving domain controller (20), which generates a trajectory signal and a wheel-speed signal according to a dynamics safety boundary signal and a planning decision-making signal; and a chassis domain controller (30), which performs distribution calculation on a vehicle estimation and prediction signal and a motion control signal, so as to obtain a control signal corresponding to a vehicle-related system.
Need to check novelty before this filing date? Find Prior Art

Description

Safety planning system and safety planning method for autonomous driving vehicles

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application is based on the Chinese patent application with application number 2023106108644 and application date May 26, 2023, and claims the priority of the Chinese patent application. The entire content of the Chinese patent application is hereby introduced into this application as a reference. Technical Field

[0003] The present disclosure relates to the field of automotive technology, and in particular to a safety planning system and a safety planning method for autonomous driving vehicles. Background Art

[0004] The development of intelligent and electrified autonomous vehicles requires a higher control priority for the chassis of autonomous vehicles to fully leverage the advantages of vehicle domain control and autonomous driving intelligent decision-making, and improve the safety of autonomous vehicles.

[0005] At present, when an autonomous vehicle enters extreme dynamic conditions such as low-adhesion roads and high-speed skidding, the vehicle is completely taken over by extreme dynamic controllers such as ABS, ESC, and TCS controllers. The autonomous driving controller loses control of the vehicle until the active safety controller exits. This sudden intervention of the active safety controller causes the autonomous driving domain controller to be temporarily unable to fully control the dynamics of the entire vehicle, which is prone to unexpected safety accidents. At the same time, active safety control has failed to fully utilize the more perception information and high computing power of autonomous driving to enhance its potential.

[0006] Summary of the Invention

[0007] The present disclosure aims to solve one of the technical problems in the related art at least to a certain extent.

[0008] To this end, the first purpose of the present disclosure is to propose a safety planning system for autonomous vehicles, which integrates active safety control functions into vehicle path planning and control. During the path planning process, the vehicle's dynamic boundaries are calculated based on fused perception information and safety restrictions are imposed on the path. Wheel speed control commands are generated along with the path to ensure that the generated trajectory does not trigger safety functions such as ABS during the chassis path tracking control and dynamic control process, and to fully utilize the perception and decision-making capabilities of the autonomous driving part to improve the safety performance of the autonomous driving domain controller.

[0009] To achieve the above objectives, the present disclosure provides a safety planning system for autonomous driving vehicles, including multiple types of sensors, an autonomous driving domain controller, and a chassis domain controller.

[0010] The multiple types of sensors are used to collect multiple sensor signals of the autonomous driving vehicle;

[0011] The autonomous driving domain controller includes a fusion perception module, a safety boundary analysis module, a planning and decision module, and a safety planning module; wherein the fusion perception module fuses and calculates multiple sensor signals to output vehicle-related information, the safety boundary analysis module calculates vehicle-related information to output a dynamic safety boundary signal, the planning and decision module outputs a planning decision signal based on the dynamic safety boundary signal, and the safety planning module generates and outputs a trajectory signal and a wheel speed signal based on the planning decision signal and the dynamic safety boundary signal;

[0012] The chassis domain controller includes a state estimation and prediction module, a trajectory / wheel speed tracking controller, and a chassis dynamics controller; wherein the state estimation and prediction module solves multiple sensor signals and vehicle dynamics control signals to output vehicle estimation and prediction signals; the trajectory / wheel speed tracking controller performs coordinated control based on the trajectory signal, wheel speed signal, and vehicle estimation and prediction signals to generate motion control signals; the chassis dynamics controller distributes and calculates the vehicle estimation and prediction signals and the motion control signals to generate a first control signal for the vehicle-related system and sends it to the corresponding actuator.

[0013] The safety planning system for autonomous vehicles in the disclosed embodiment fully utilizes the greater perception information and high computing power of autonomous driving to enhance its safety potential, reduce the triggering of safety functions such as ABS / ESC / TCS, and improve the safety performance of the vehicle.

[0014] In addition, the safety planning system for autonomous driving vehicles according to the above embodiments of the present disclosure may also have the following additional technical features:

[0015] In one embodiment of the present disclosure, the chassis domain controller further includes a safety status identification module and an ABS / ESC / TCS function module; wherein,

[0016] The safety state identification module is configured to verify vehicle-related physical quantities based on the dynamic safety boundary signal to verify whether the vehicle-related physical quantities meet the dynamic safety boundary constraint conditions. If not, the ABS / ESC / TCS functional modules are activated and a verification failure signal is sent to the autonomous driving domain controller.

[0017] The ABS / ESC / TCS functional module is used to perform vehicle dynamics control after activation, and to generate a second control signal for the vehicle-related system and send it to the corresponding actuator.

[0018] In one embodiment of the present disclosure, the safety boundary analysis module is further used to calculate the vehicle-related information using the vehicle dynamics model and the tire model to obtain a dynamic safety boundary signal, and send the dynamic safety boundary signal to the safety planning module and the safety state identification module.

[0019] In one embodiment of the present disclosure, the safety planning module is further configured to calculate the planning decision signal and the dynamic safety boundary signal to obtain the trajectory signal and the wheel speed signal when the current vehicle dynamic state satisfies the dynamic safety boundary constraint condition.

[0020] In one embodiment of the present disclosure, the safety state identification module is further configured to identify the vehicle estimation and prediction signals to estimate the current vehicle dynamic state, and determine whether the current vehicle dynamic state satisfies the dynamic safety boundary constraint conditions based on the dynamic safety boundary signal received from the safety boundary analysis module.

[0021] In one embodiment of the present disclosure, the vehicle-related systems include a vehicle drive system, a braking system, a steering system, and a suspension system; the planning decision signals include lane change, straight driving, and obstacle avoidance decision signals; the dynamic safety boundary signals include yaw rate limits and slip rate limits; the trajectory signals meet road boundary limits, yaw rate limits, acceleration limits, and lateral acceleration limits; the wheel speed signals meet slip rate limits; and the vehicle dynamics control signals include feedback signals from the drive system, braking system, steering system, and suspension system.

[0022] In one embodiment of the present disclosure, the vehicle-related information includes multiple types of obstacle information, road information, posture signals, vehicle position and speed signals; the multiple sensor signals include multiple types of lidar signals, camera signals, combined inertial navigation signals and wheel speed signals of the autonomous driving vehicle.

[0023] The second objective of the present disclosure is to propose a safety planning method for a safety planning system for autonomous driving vehicles.

[0024] To achieve the above objectives, an embodiment of the present disclosure provides a safety planning method for a safety planning system for an autonomous driving vehicle, comprising:

[0025] Calculating vehicle-related information obtained based on multiple sensor signals to obtain a dynamic safety boundary signal;

[0026] generating a trajectory signal and a wheel speed signal according to the dynamic safety margin signal and a planning decision signal obtained based on the dynamic safety margin signal;

[0027] Solving the plurality of sensor signals and the vehicle dynamics control signal to obtain vehicle estimation and prediction signals;

[0028] Based on the trajectory signal and the wheel speed signal and the vehicle estimation and prediction signal, collaborative control is performed to generate a motion control signal, and the vehicle estimation and prediction signal and the motion control signal are distributed and calculated to obtain a control signal corresponding to a vehicle-related system.

[0029] The safety planning method of the safety planning system for autonomous driving vehicles in the disclosed embodiment fully utilizes the more perceptual information and high computing power of autonomous driving to enhance its safety potential, reduce the triggering of safety functions such as ABS / ESC / TCS, and improve the safety performance of the vehicle.

[0030] A third object of the present disclosure is to provide a computer device comprising a processor and a memory;

[0031] The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to implement a safety planning method for a safety planning system for autonomous driving vehicles.

[0032] The fourth object of the present disclosure is to provide a non-temporary computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a safety planning method for a safety planning system for an autonomous driving vehicle.

[0033] A fifth objective of the present disclosure is to provide a computer program product, comprising a computer program, which implements the security planning method described in any of the above embodiments when executed by a processor.

[0034] The sixth objective of the present disclosure is to provide a computer program, which includes computer program code. When the computer program code runs on a computer, the computer executes the security planning method described in any one of the above embodiments.

[0035] Additional aspects and advantages of the present disclosure will be given in part in the description below and in part will be obvious from the description below, or will be learned through practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The above and / or additional aspects and advantages of the present disclosure will become apparent and readily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0037] FIG1 is a schematic diagram of the structure of a safety planning system for an autonomous driving vehicle according to one embodiment of the present disclosure;

[0038] FIG2 is a flowchart of a safety planning method for a safety planning system for an autonomous driving vehicle according to one embodiment of the present disclosure;

[0039] FIG3 is a flowchart of another safety planning method for a safety planning system for an autonomous driving vehicle according to an embodiment of the present disclosure;

[0040] FIG4 shows a computer device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0041] The following describes in detail embodiments of the present disclosure, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present disclosure, and should not be construed as limiting the present disclosure.

[0042] The following describes a safety planning system, method, device, and storage medium for autonomous driving vehicles according to embodiments of the present disclosure with reference to the accompanying drawings.

[0043] FIG1 is a schematic diagram of the structure of a safety planning system for an autonomous driving vehicle according to an embodiment of the present disclosure.

[0044] As shown in Figure 1, the system includes: multiple types of sensors 10, an autonomous driving domain controller 20 and a chassis domain controller 30;

[0045] Multiple types of sensors 10 (sensor combination supporting high-level autonomous driving) for collecting multiple sensor signals of the autonomous driving vehicle;

[0046] The autonomous driving domain controller 20 includes a fusion perception module, a safety margin analysis module, a planning and decision module, and a safety planning module. The fusion perception module fuses and calculates multiple sensor signals to output vehicle-related information. The safety margin analysis module calculates vehicle-related information to output a dynamic safety margin signal. The planning and decision module outputs a planning decision signal based on the dynamic safety margin signal. The safety planning module generates and outputs a trajectory signal and a wheel speed signal based on the planning decision signal and the dynamic safety margin signal.

[0047] The chassis domain controller 30 includes a state estimation and prediction module, a trajectory / wheel speed tracking controller, and a chassis dynamics controller; wherein the state estimation and prediction module solves multiple sensor signals and vehicle dynamics control signals to output vehicle estimation and prediction signals; the trajectory / wheel speed tracking controller performs coordinated control based on the trajectory signal, wheel speed signal, and vehicle estimation and prediction signal to generate a motion control signal; the chassis dynamics controller distributes and calculates the vehicle estimation and prediction signal and the motion control signal to generate a first control signal for the vehicle-related system and sends it to the corresponding actuator.

[0048] It can be understood that there are multiple types of sensors 10 (sensor combinations supporting high-level autonomous driving), among which the multiple types of sensors include lidar, cameras, combined inertial navigation and wheel speed sensors in the chassis domain for autonomous driving sensing.

[0049] In one embodiment of the present disclosure, the autonomous driving domain controller 20 includes a fusion perception module 21, a safety boundary analysis module 22, a planning and decision module 23, and a safety planning module 24.

[0050] The fusion perception module 21 receives multiple sensor signals of the autonomous driving vehicle, and obtains obstacle information, road information, vehicle position, and speed signals through fusion calculation. At the same time, it sends the road safety boundary signal, including obstacle information and road information, to the safety boundary analysis module 22 and the planning and decision module 23. The multiple types of sensor signals include lidar signals, camera signals, combined inertial navigation signals, and wheel speed signals in the chassis domain for autonomous driving sensing.

[0051] The safety boundary analysis module 23 combines the road adhesion signal, posture signal, and speed signal calculated by the fusion perception module 21 with the vehicle dynamics model and tire model to calculate a dynamic safety boundary signal, where the dynamic safety boundary signal includes the yaw angular velocity limit and slip rate limit in this state, and sends the safety boundary signal to the safety planning module 24 and the safety state identification module 34 of the chassis domain controller 30.

[0052] The planning and decision module 23 makes intelligent decisions for autonomous driving based on the received safety boundary information, including decisions on lane changing, straight driving, and obstacle avoidance, and sends decision signals to the safety planning module 24.

[0053] The safety planning module 24 calculates an optimized trajectory signal constrained by the dynamic safety boundary based on the received planning decision signal and dynamic safety boundary information when the vehicle dynamic state does not exceed the dynamic safety boundary limit, and generates a wheel speed command along with the path to ensure that the generated trajectory is within the vehicle safety dynamic boundary during execution. At the same time, the trajectory signal and wheel speed signal are sent to the chassis domain controller 30, where the commands of the trajectory signal and wheel speed signal can adopt an optimization method, such as model predictive control, or an intelligent learning method, such as reinforcement learning. The generated trajectory signal must ensure that the road boundary limit, yaw angular velocity limit, acceleration limit, and lateral acceleration limit are met, and the generated wheel speed signal must meet the slip rate limit to ensure that the planned path and wheel speed of the vehicle meet the dynamic safety requirements.

[0054] In one embodiment of the present disclosure, the chassis domain controller 30 includes a state estimation and prediction module 31 , a trajectory / wheel speed tracking controller 32 , a chassis dynamics controller 33 , a safety state identification module 34 and an ABS / ESC / TCS functional module 35 .

[0055] The state estimation and prediction module 31 mainly calculates the current vehicle body dynamic state, solves multiple autonomous driving sensor signals and vehicle dynamic control signals based on the vehicle dynamic model, obtains the vehicle position, speed, posture, and tire force signals, and sends them to the safety state identification module 34, the chassis dynamic control module 33, and the trajectory / wheel speed tracking control module 32. The sensor signals include combined inertial navigation signals and wheel speed signals, and the vehicle dynamic control signals include feedback signals from the drive system, braking system, steering system, and suspension system.

[0056] The trajectory / wheel speed tracking controller 32 receives the trajectory signal, wheel speed signal and estimation and prediction signal from the safety planning module 24 and the state estimation and prediction module 31, performs longitudinal and lateral coordinated control on the chassis dynamic motion state, generates longitudinal and lateral motion control commands for tracking trajectory and wheel speed, including lateral force, longitudinal force and yaw moment commands, and sends them to the chassis dynamics controller 33.

[0057] The chassis dynamics controller 33, the motion control commands generated by the trajectory / wheel speed tracking controller 32, and the estimation and prediction signals of the state estimation and prediction module 31 are used to perform execution allocation of the wire-controlled actuators according to the vehicle dynamics control algorithm, generate control signals for the vehicle drive system 41, the braking system 42, the steering system 43 and the suspension system 44, and send them to the corresponding actuators.

[0058] The safety state identification module 34 receives the dynamic safety boundary signal calculated by the safety boundary analysis module 22 and the current vehicle dynamic state estimated by the state estimation and prediction module 31, and verifies selected physical quantities related to vehicle stability, such as wheel speed, yaw rate, and lateral acceleration. If the relevant physical quantities are within the dynamic safety boundary threshold, safety planning and dynamic control continue according to the safety planning method for autonomous driving domain control. If the relevant physical quantities exceed the dynamic safety boundary threshold, indicating that the vehicle's motion state is critical and the currently planned path and wheel speed are no longer guaranteed, and vehicle stability is the primary control objective, the ABS / ESC / TCS function module 35 is activated and a verification failure signal is sent to the autonomous driving domain controller 20, causing the autonomous driving domain controller 20 to temporarily relinquish vehicle control until the vehicle returns to within the safety boundary.

[0059] The ABS / ESC / TCS functional module 35 is activated when the vehicle dynamics state exceeds the dynamic safety boundary limit, temporarily takes over the vehicle dynamics control, generates control signals for the vehicle drive system 41, braking system 42, steering system 43 and suspension system 44, and sends them to the corresponding actuators, and exits after controlling the vehicle state to within the safety boundary.

[0060] Through the safety planning system for autonomous vehicles in the embodiment of the present disclosure, active safety control functions are integrated into the vehicle path planning control. During the path planning process, the vehicle's dynamic boundaries are calculated based on the fused perception information and safety restrictions are imposed on the path. Wheel speed control commands are generated along with the path to ensure that the generated trajectory does not trigger safety functions such as ABS during the chassis path tracking control and dynamic control processes, thereby fully utilizing the perception and decision-making capabilities of the autonomous driving part to improve the safety performance of the autonomous driving domain controller.

[0061] Next, a safety planning method for a safety planning system for an autonomous driving vehicle proposed according to an embodiment of the present disclosure will be described with reference to the accompanying drawings.

[0062] FIG2 is a flowchart of a safety planning method of a safety planning system for an autonomous driving vehicle according to an embodiment of the present disclosure.

[0063] As shown in FIG2 , the method includes the following steps:

[0064] S1, calculating vehicle-related information obtained based on multiple sensor signals to obtain a dynamic safety margin signal;

[0065] S2, generating a trajectory signal and a wheel speed signal according to the dynamic safety margin signal and a planning decision signal obtained based on the dynamic safety margin signal;

[0066] S3, solving multiple sensor signals and vehicle dynamics control signals to obtain vehicle estimation and prediction signals;

[0067] S4, performing coordinated control based on the trajectory signal, the wheel speed signal, and the vehicle estimation and prediction signal to generate a motion control signal, and performing distribution calculation on the vehicle estimation and prediction signal and the motion control signal to obtain a control signal corresponding to the vehicle-related system.

[0068] Understandably, the current safety control scheme for autonomous vehicles primarily relies on the chassis dynamics controller tracking the path calculated by the autonomous driving controller. Safety risks arising in emergency conditions such as low-load conditions and sudden braking directly trigger safety features such as ABS / ESC / TCS. However, this scheme makes emergency conditions more likely to be triggered, and the autonomous driving domain controller is temporarily unable to fully control vehicle dynamics, making unexpected safety accidents more likely. In response, this disclosure fully utilizes the increased perception information and high-performance computing power of autonomous driving to enhance its safety potential, reduce the triggering of safety features such as ABS / ESC / TCS, and improve vehicle safety performance.

[0069] In one embodiment of the present disclosure, FIG3 is a logic diagram of a safety planning method of a safety planning system for an autonomous driving vehicle according to an embodiment of the present disclosure, as shown in FIG3 :

[0070] Fusion perception S10, which receives signals from multiple sensors for autonomous driving and fuses them to calculate obstacle information, road adhesion information, vehicle position, posture, and speed signals;

[0071] Safety margin analysis S20 is used to combine the road adhesion signal, attitude signal, and speed signal obtained from the fusion perception calculation with the vehicle dynamics model and tire model to calculate the dynamic safety margin signal, including the yaw rate limit and slip rate limit in this state;

[0072] Safety state identification S30 identifies and estimates the vehicle state estimation and prediction signals and receives the safety boundary information of the safety boundary analysis module to determine whether the vehicle dynamic state is within the safety boundary state limit.

[0073] When the vehicle's dynamic state does not exceed the dynamic safety boundary limit, safety planning S41 is performed. Based on the received planning decision signal and dynamic safety boundary information, the optimized trajectory signal constrained by the dynamic safety boundary is calculated, and the wheel speed command is generated along with the path to ensure that the generated trajectory is within the vehicle's safety dynamic boundary during execution. At the same time, chassis dynamic fusion control S42 is performed to calculate and allocate control commands for the wire-controlled actuator. Finally, step S50 is performed, and the chassis wire-controlled actuator executes relevant control commands, including each wheel drive braking force command, steering system steering angle command, active suspension main force command, etc.

[0074] When the vehicle's dynamic state exceeds the dynamic safety boundary limit, the S43 ABS / ESC / TCS function is directly triggered to temporarily take over the vehicle's dynamic control. The traditional ABS / ESC / TCS safety algorithm quickly restores the vehicle's stability and improves the vehicle's adhesion utilization rate. Finally, step S50 is performed, and the chassis wire control actuator executes relevant control commands, including each wheel drive braking force command, steering system steering angle command, active suspension main force command, etc.

[0075] To sum up, with the rise of intelligent automobiles, smart cars have gradually improved their computing power and perception capabilities, increased their safety requirements, and deepened the collaborative interaction between the chassis domain and the autonomous driving domain. This disclosure utilizes autonomous driving perception information and planning capabilities while ensuring safety, reduces the triggering of risk scenarios, improves the safety of autonomous driving vehicles, and has broad application prospects.

[0076] According to the embodiment of the present disclosure, a safety planning method for a safety planning system for autonomous vehicles is proposed. The chassis domain controller for safety planning for autonomous vehicles disclosed in the present disclosure can fully utilize the perception and computing capabilities of autonomous vehicles, reduce unexpected triggering of functions such as ABS / TCS / ESC, improve the body stability of the autonomous vehicle during driving, and retain active safety capabilities under emergency conditions.

[0077] In order to implement the method of the above embodiment, the embodiment of the present disclosure further provides a computer device, as shown in Figure 4, the computer device 600 includes a memory 601 and a processor 602; wherein the processor 602 runs a program corresponding to the executable program code by reading the executable program code stored in the memory 601, so as to implement the various steps of the safety planning method of the safety planning system for autonomous driving vehicles described above.

[0078] In order to implement the above embodiments, the embodiments of the present disclosure also propose a non-temporary computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the safety planning method of the safety planning system for autonomous driving vehicles as described in the above embodiments is implemented.

[0079] In order to implement the above embodiments, the embodiments of the present disclosure further provide a computer program product, including a computer program. When the computer program is executed by a processor, the security planning method described in the above embodiments is implemented.

[0080] In order to implement the above embodiment, the embodiment of the present disclosure further proposes a computer program, which includes computer program code. When the computer program code runs on a computer, it enables the computer to execute the security planning method described in the above method embodiment.

[0081] It should be noted that the aforementioned explanations of the embodiments of the security planning method are also applicable to the non-transitory computer-readable storage medium, computer program product, and computer program of the embodiments of the present disclosure, and will not be repeated here.

[0082] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. Throughout the present disclosure, "plurality" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0083] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0084] Although the embodiments of the present disclosure have been shown and described above, it is understood that the above embodiments are illustrative and are not to be construed as limitations on the present disclosure. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present disclosure.

Claims

1. A safety planning system for an autonomous driving vehicle, comprising: Various types of sensors, autonomous driving domain controllers and chassis domain controllers; among them, The multiple types of sensors are used to collect multiple sensor signals of the autonomous driving vehicle; The autonomous driving domain controller includes a fusion perception module, a safety boundary analysis module, a planning decision module and a safety planning module; wherein the fusion perception module fuses and calculates multiple sensor signals to output vehicle-related information, the safety boundary analysis module calculates vehicle-related information to output a dynamic safety boundary signal, the planning decision module outputs a planning decision signal based on the dynamic safety boundary signal, and the safety planning module generates and outputs a trajectory signal and a wheel speed signal based on the planning decision signal and the dynamic safety boundary signal; The chassis domain controller includes a state estimation and prediction module, a trajectory / wheel speed tracking controller, and a chassis dynamics controller; wherein the state estimation and prediction module solves multiple sensor signals and vehicle dynamics control signals to output vehicle estimation and prediction signals; the trajectory / wheel speed tracking controller performs collaborative control based on the trajectory signal, the wheel speed signal, and the vehicle estimation and prediction signal to generate a motion control signal; the chassis dynamics controller distributes and calculates the vehicle estimation and prediction signal and the motion control signal to generate a first control signal of a vehicle-related system and sends it to a corresponding actuator.

2. The safety planning system for autonomous driving vehicles according to claim 1, wherein: The chassis domain controller also includes a safety status identification module and an ABS / ESC / TCS function module; wherein, The safety state identification module is used to verify the vehicle-related physical quantities according to the dynamic safety boundary signal to verify whether the vehicle-related physical quantities meet the dynamic safety boundary constraint conditions. If not, the ABS / ESC / TCS functional module is activated and a verification failure signal is sent to the automatic driving domain controller; The ABS / ESC / TCS functional module is used to perform vehicle dynamics control after activation, and to generate a second control signal for a vehicle-related system and send it to a corresponding actuator.

3. The safety planning system for autonomous driving vehicles according to claim 1 or 2, wherein: The safety boundary analysis module is also used to calculate the vehicle-related information using the vehicle dynamics model and the tire model to obtain a dynamic safety boundary signal, and send the dynamic safety boundary signal to the safety planning module and the safety state identification module.

4. The safety planning system for an autonomous driving vehicle according to any one of claims 1 to 3, wherein: The safety planning module is also used to calculate the planning decision signal and the dynamic safety boundary signal to obtain the trajectory signal and the wheel speed signal when the current vehicle dynamic state meets the dynamic safety boundary constraint condition.

5. The safety planning system for autonomous driving vehicles according to claim 4, wherein: The safety state identification module is also used to identify the vehicle estimation and prediction signal to estimate the current vehicle dynamic state, and determine whether the current vehicle dynamic state meets the dynamic safety boundary constraint condition based on the received dynamic safety boundary signal of the safety boundary analysis module.

6. The safety planning system for an autonomous driving vehicle according to any one of claims 1 to 5, wherein: The vehicle-related systems include vehicle drive system, braking system, steering system and suspension system; the planning decision signals include lane change, straight driving and obstacle avoidance decision signals; the dynamic safety boundary signals include yaw rate limit and slip rate limit; the trajectory signal satisfies road boundary limit, yaw rate limit, acceleration limit and lateral acceleration limit; the wheel speed signal satisfies slip rate limit; the whole vehicle dynamics control signal includes feedback signals of the drive system, braking system, steering system and suspension system.

7. A safety planning system for autonomous driving vehicles according to any one of claims 1 to 6, wherein the vehicle-related information includes multiple types of obstacle information, road information, posture signals, vehicle position and speed signals; and the multiple sensor signals include multiple types of lidar signals, camera signals, combined inertial navigation signals and wheel speed signals of the autonomous driving vehicle.

8. A safety planning method for a safety planning system for an autonomous driving vehicle, applied to any one of claims 1 to 7, comprising the following steps: Calculating vehicle-related information obtained based on multiple sensor signals to obtain a dynamic safety boundary signal; Generate a trajectory signal and a wheel speed signal according to the dynamic safety boundary signal and a planning decision signal obtained based on the dynamic safety boundary signal; Solving the multiple sensor signals and vehicle dynamics control signals to obtain vehicle estimation and prediction signals; Based on the trajectory signal and the wheel speed signal and the vehicle estimation and prediction signal, collaborative control is performed to generate a motion control signal, and the vehicle estimation and prediction signal and the motion control signal are distributed and calculated to obtain a control signal corresponding to a vehicle-related system.

9. A computer device comprising a processor and a memory; in, The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to implement the security planning method as claimed in claim 8.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, wherein the program implements the security planning method as claimed in claim 8 when executed by a processor.

11. A computer program product, comprising a computer program, wherein the computer program implements the security planning method of claim 8 when executed by a processor. 12 . A computer program, comprising computer program code, which enables the computer to execute the security planning method according to claim 8 when the computer program code is run on a computer.

Citation Information

Patent Citations

  • Vehicle stability system based on safety boundary and control method

    CN111605542A

  • Automobile integrated stability augmentation control method and system

    CN113928306A

  • Chassis domain controller for automatic driving, control method and vehicle

    CN115571160A

  • Multi-axle distributed vehicle auxiliary steering safety constraint calculation method

    CN115817511A

  • Function decomposition and control architecture for complex vehicle control system

    US20110098886A1

Cited By

  • Automatic driving path tracking and vehicle stability control cooperation method and system

    CN119928830A

  • Vehicle body and chassis cooperative control system and method, vehicle and medium

    CN120704183A

  • Vehicle driving control method and system

    CN121671646A

  • Drive-by-wire chassis key parameter active identification and control collaborative optimization method and system

    CN122143929A

  • Vehicle control method and related product

    WO2026149201A1