High-order automatic driving system safety redundancy method and system and medium

Abstract

The invention relates to a high-order automatic driving system safety redundancy method and system and a medium, and the method comprises the steps: M1, collecting the historical automatic driving data information of a vehicle when the vehicle runs on a road, and obtaining the automatic driving data information of the whole vehicle in real time based on a vehicle-mounted CAN transceiver; and M2, on the basis of the historical automatic driving data information of the vehicle, adopting an integrated learning algorithm of a random neural network based on sparrow optimization to predict the automatic driving of the whole vehicle, and obtaining the predicted automatic driving data information of the whole vehicle. The problem that the system continuity and the riding experience comfort are poor due to the fact that the safety redundancy architecture and the redundancy protection processing strategy are single is solved, the vehicle driving safety and the system reliability are fully guaranteed, and therefore the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a safety redundancy method, system and medium for a high-level autonomous driving system. Background Art

[0002] Unmanned driving technology has developed rapidly in recent years, and the safety of autonomous driving has always been a top priority to consider during design. Therefore, in the design of the autonomous driving system architecture, redundant design is particularly important. Since the autonomous driving system needs to handle a large number of environmental perception, decision-making planning, and execution control tasks, the failure of any single component may cause the failure of the entire system, and then cause a safety accident. Therefore, improving the safety and reliability of the autonomous driving system through redundant design is one of the important directions for the development of autonomous driving technology.

[0003] The current problem is that existing mainstream high-level autonomous driving usually executes an emergency parking strategy or the safety officer takes over depending on the situation when a core system failure is detected. The safety redundancy architecture and redundant protection processing strategy are relatively simple, resulting in poor system continuity and ride comfort. Summary of the invention

[0004] In view of the above problems, the present invention provides a safety redundancy method, system and medium for a high-level autonomous driving system, which not only solves the problem that the safety redundancy architecture and redundant protection processing strategy are relatively simple, resulting in poor system continuity and riding comfort, but also fully ensures vehicle driving safety and system reliability, thereby improving user experience.

[0005] In order to achieve the above-mentioned purpose and other related purposes, the technical solution provided by the present invention is as follows: a high-level autonomous driving system safety redundancy method, the method comprising:

[0006] M1. The vehicle is driving on the road, collecting the historical data information of the vehicle's autonomous driving, and obtaining the autonomous driving data information of the whole vehicle in real time based on the on-board CAN transceiver;

[0007] M2. Based on the historical autonomous driving data information of the vehicle, an ensemble learning algorithm based on a sparrow-optimized random neural network is used to predict the autonomous driving of the entire vehicle, and the predicted autonomous driving data information of the entire vehicle is obtained;

[0008] M3. Based on the predicted data information of the autonomous driving of the whole vehicle and the data information of the autonomous driving of the whole vehicle, a nonlinear regression algorithm based on multi-factor variance analysis is used to characterize the autonomous driving difference value of each node to obtain the difference value data information of the autonomous driving of the whole vehicle;

[0009] M4. Based on the difference value data information of the autonomous driving of the whole vehicle, establish the safety redundancy function G of the autonomous driving system, calculate the safety redundancy boundary value of the autonomous driving system, and obtain the data information of the safety redundancy boundary value of the autonomous driving system.

[0010] Furthermore, the method further comprises:

[0011] M5. Based on the data information of the safety redundancy boundary value of the autonomous driving system, a preset threshold is set. If the autonomous driving safety redundancy boundary value is less than the preset threshold, the autonomous driving system of the entire vehicle is normal and the vehicle drives normally. If the autonomous driving safety redundancy boundary value is greater than the preset threshold, the autonomous driving system of the entire vehicle fails and the vehicle cannot drive normally.

[0012] Furthermore, in step M2, the use of an integrated learning algorithm based on a sparrow-optimized random neural network to predict the autonomous driving of the entire vehicle includes:

[0013] M21. Inputting the historical autonomous driving data information of the vehicle into the ensemble learning model of the random neural network for training and learning, and extracting the model parameters to obtain the model parameter data information of the ensemble learning model of the random neural network;

[0014] M22. Based on the model parameter data information of the random neural network ensemble learning model, the sparrow population is initialized, the maximum number of iterations is determined, and the data information of the initialized sparrow population is obtained;

[0015] M23. Based on the data information of the initialized sparrow population, establish the fitness function Q of the individuals in the population,

[0016]

[0017] Among them, x is the data information of the initialized sparrow population, α1, α2 and α3 are the fitness determining factors of the population individuals, and the fitness values ​​of the population individuals are calculated to obtain the fitness value data information of the population individuals;

[0018] M24. Based on the fitness value data information of the population individuals, establish a target optimization function W,

[0019]

[0020] Among them, y is the fitness value data information of the population individuals, β1, β2 and β3 are optimization constant parameters, and the model parameters of the ensemble learning model of the random neural network are optimized to obtain the optimized ensemble learning model of the random neural network.

[0021] Furthermore, it also includes:

[0022] M25. Based on the optimized integrated learning model of the random neural network, the historical autonomous driving data information of the vehicle is input, the autonomous driving of the whole vehicle is predicted, and the predicted autonomous driving data information of the whole vehicle is obtained.

[0023] Furthermore, the constraint function f of the optimization constant parameters, β1, β2 and β3 is,

[0024] The value range of the constraint function f is (2,3).

[0025] Furthermore, in step M3, the characterization of the autonomous driving difference value of each node by using a nonlinear regression algorithm based on multi-factor variance analysis includes:

[0026] M31. Based on the predicted data information of the autonomous driving of the whole vehicle, a first expression function R1 of the autonomous driving of the whole vehicle is established.

[0027]

[0028] Among them, z1 is the predicted data information of the autonomous driving of the whole vehicle, δ1, δ2 and δ3 are the first expression factors of the autonomous driving, and the autonomous driving data of the whole vehicle is characterized to obtain the first expression matrix data information of the autonomous driving of the whole vehicle;

[0029] M32. Based on the data information of the autonomous driving of the whole vehicle, a second expression function R2 of the autonomous driving of the whole vehicle is established,

[0030]

[0031] Among them, z2 is the data information of the autonomous driving of the whole vehicle, γ1, γ2 and γ3 are the second expression factors of the autonomous driving, and the autonomous driving data of the whole vehicle is represented to obtain the second expression matrix data information of the autonomous driving of the whole vehicle;

[0032] M33. Based on the second expression matrix data information of the whole vehicle autonomous driving and the first expression matrix data information of the whole vehicle autonomous driving, a function P of multi-factor variance analysis of the whole vehicle autonomous driving is established.

[0033]

[0034] Among them, r1 is the first expression matrix data information of the whole vehicle's autonomous driving, r2 is the second expression matrix data information of the whole vehicle's autonomous driving, η1, η2 and η3 are the difference optimization factors of the whole vehicle's autonomous driving, and the difference value of the autonomous driving data of each node is represented to obtain the difference value data information of the whole vehicle's autonomous driving data.

[0035] Furthermore, the constraint conditions of the difference optimization factors η1, η2 and η3 of the whole vehicle autonomous driving are:

[0036]

[0037] The constraint function g2 of the second expression factors γ1, γ2 and γ3 of the autonomous driving is,

[0038]

[0039] The constraint function g1 of the first expression factors δ1, δ2 and δ3 of the autonomous driving is,

[0040]

[0041] Among them, the value range of constraint function g1 is (2,4), and the value range of constraint function g2 is (3,6).

[0042] Furthermore, the safety redundancy function G of the autonomous driving system is:

[0043]

[0044] Among them, a is the difference value data information of the autonomous driving of the whole vehicle, and λ1, λ2 and λ3 are the safety redundancy determining factors of the autonomous driving system.

[0045] In order to achieve the above-mentioned objectives and other related objectives, the present invention also provides a high-level autonomous driving system safety redundancy system, including a computer device, which is programmed or configured to execute the steps of any one of the high-level autonomous driving system safety redundancy methods described.

[0046] In order to achieve the above-mentioned objectives and other related objectives, the present invention also provides a computer-readable storage medium, which stores a computer program programmed or configured to execute any one of the high-order autonomous driving system safety redundancy methods described above.

[0047] The present invention has the following positive effects:

[0048] 1. The present invention predicts the autonomous driving of the whole vehicle by adopting an ensemble learning algorithm based on a sparrow-optimized random neural network, and characterizes the autonomous driving difference value of each node in combination with a nonlinear regression algorithm based on multi-factor variance analysis. It can not only accurately judge the safety redundancy of the autonomous driving system, but also fully ensure the vehicle driving safety and system reliability, thereby improving the user experience.

[0049] 2. The present invention establishes a safety redundancy function G of the autonomous driving system and calculates the safety redundancy boundary value of the autonomous driving system. This not only solves the problem that the safety redundancy architecture and redundant protection processing strategy are relatively simple, resulting in poor system continuity and riding comfort, but also formulates a redundant safety strategy to determine under what circumstances to start the redundant mechanism and how to perform fault switching and recovery. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0051] Figure 2 It is a flow chart of the integrated learning algorithm of the sparrow-optimized random neural network of the present invention;

[0052] Figure 3 It is a schematic diagram of the flow of the nonlinear regression algorithm based on multi-factor variance analysis of the present invention;

[0053] Figure 4 Schematic diagram of the system framework of the present invention. DETAILED DESCRIPTION

[0054] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0055] Example 1: Figure 1 As shown, a high-level autonomous driving system safety redundancy method, the method comprising:

[0056] M1. The vehicle is driving on the road, collecting the historical data information of the vehicle's autonomous driving, and obtaining the data information of the vehicle's autonomous driving in real time based on the on-board CAN transceiver;

[0057] M2. Based on the historical autonomous driving data information of the vehicle, an ensemble learning algorithm based on a sparrow-optimized random neural network is used to predict the autonomous driving of the entire vehicle, and the predicted autonomous driving data information of the entire vehicle is obtained;

[0058] M3. Based on the predicted data information of the autonomous driving of the whole vehicle and the data information of the autonomous driving of the whole vehicle, a nonlinear regression algorithm based on multi-factor variance analysis is used to characterize the autonomous driving difference value of each node to obtain the difference value data information of the autonomous driving of the whole vehicle;

[0059] M4. Based on the difference value data information of the autonomous driving of the whole vehicle, establish the safety redundancy function G of the autonomous driving system, calculate the safety redundancy boundary value of the autonomous driving system, and obtain the data information of the safety redundancy boundary value of the autonomous driving system.

[0060] In this embodiment, the method further includes:

[0061] M5. Based on the data information of the safety redundancy boundary value of the autonomous driving system, a preset threshold is set. If the autonomous driving safety redundancy boundary value is less than the preset threshold, the autonomous driving system of the entire vehicle is normal and the vehicle drives normally. If the autonomous driving safety redundancy boundary value is greater than the preset threshold, the autonomous driving system of the entire vehicle fails and the vehicle cannot drive normally.

[0062] In this embodiment, if Figure 2 As shown, in step M2, the use of an integrated learning algorithm based on a sparrow-optimized random neural network to predict the autonomous driving of the entire vehicle includes:

[0063] M21. Inputting the historical autonomous driving data information of the vehicle into the ensemble learning model of the random neural network for training and learning, and extracting the model parameters to obtain the model parameter data information of the ensemble learning model of the random neural network;

[0064] M22. Based on the model parameter data information of the random neural network ensemble learning model, the sparrow population is initialized, the maximum number of iterations is determined, and the data information of the initialized sparrow population is obtained;

[0065] M23. Based on the data information of the initialized sparrow population, establish the fitness function Q of the individuals in the population,

[0066]

[0067] Among them, x is the data information of the initialized sparrow population, α1, α2 and α3 are the fitness determining factors of the population individuals, and the fitness values ​​of the population individuals are calculated to obtain the fitness value data information of the population individuals;

[0068] M24. Based on the fitness value data information of the population individuals, establish a target optimization function W,

[0069]

[0070] Among them, y is the fitness value data information of the population individuals, β1, β2 and β3 are optimization constant parameters, and the model parameters of the ensemble learning model of the random neural network are optimized to obtain the optimized ensemble learning model of the random neural network.

[0071] In this embodiment, it also includes:

[0072] M25. Based on the optimized integrated learning model of the random neural network, the historical autonomous driving data information of the vehicle is input, the autonomous driving of the whole vehicle is predicted, and the predicted autonomous driving data information of the whole vehicle is obtained.

[0073] In this embodiment, the constraint function f of the optimization constant parameters, β1, β2 and β3 is,

[0074]

[0075] The value range of the constraint function f is (2,3).

[0076] Example 2: Based on the high-level autonomous driving system safety redundancy method of Example 1, the present invention is further illustrated and described below.

[0077] like Figure 1 As shown, a high-level autonomous driving system safety redundancy method, the method comprising:

[0078] M1. The vehicle is driving on the road, collecting the historical data information of the vehicle's autonomous driving, and obtaining the data information of the vehicle's autonomous driving in real time based on the on-board CAN transceiver;

[0079] M2. Based on the historical autonomous driving data information of the vehicle, an ensemble learning algorithm based on a sparrow-optimized random neural network is used to predict the autonomous driving of the entire vehicle, and the predicted autonomous driving data information of the entire vehicle is obtained;

[0080] M3. Based on the predicted data information of the autonomous driving of the whole vehicle and the data information of the autonomous driving of the whole vehicle, a nonlinear regression algorithm based on multi-factor variance analysis is used to characterize the autonomous driving difference value of each node to obtain the difference value data information of the autonomous driving of the whole vehicle;

[0081] M4. Based on the difference value data information of the autonomous driving of the whole vehicle, establish the safety redundancy function G of the autonomous driving system, calculate the safety redundancy boundary value of the autonomous driving system, and obtain the data information of the safety redundancy boundary value of the autonomous driving system.

[0082] In this embodiment, if Figure 3 As shown, in step M3, the nonlinear regression algorithm based on multi-factor variance analysis is used to characterize the autonomous driving difference value of each node, including:

[0083] M31. Based on the predicted data information of the autonomous driving of the whole vehicle, a first expression function R1 of the autonomous driving of the whole vehicle is established.

[0084]

[0085] Among them, z1 is the predicted data information of the autonomous driving of the whole vehicle, δ1, δ2 and δ3 are the first expression factors of the autonomous driving, and the autonomous driving data of the whole vehicle is characterized to obtain the first expression matrix data information of the autonomous driving of the whole vehicle;

[0086] M32. Based on the data information of the autonomous driving of the whole vehicle, a second expression function R2 of the autonomous driving of the whole vehicle is established,

[0087]

[0088] Among them, z2 is the data information of the autonomous driving of the whole vehicle, γ1, γ2 and γ3 are the second expression factors of the autonomous driving, and the autonomous driving data of the whole vehicle is represented to obtain the second expression matrix data information of the autonomous driving of the whole vehicle;

[0089] M33. Based on the second expression matrix data information of the whole vehicle autonomous driving and the first expression matrix data information of the whole vehicle autonomous driving, a function P of multi-factor variance analysis of the whole vehicle autonomous driving is established.

[0090]

[0091] Among them, r1 is the first expression matrix data information of the whole vehicle's autonomous driving, r2 is the second expression matrix data information of the whole vehicle's autonomous driving, η1, η2 and η3 are the difference optimization factors of the whole vehicle's autonomous driving, and the difference value of the autonomous driving data of each node is represented to obtain the difference value data information of the whole vehicle's autonomous driving data.

[0092] In this embodiment, the constraint conditions of the difference optimization factors η1, η2 and η3 of the whole vehicle automatic driving are:

[0093]

[0094] The constraint function g2 of the second expression factors γ1, γ2 and γ3 of the autonomous driving is,

[0095]

[0096] The constraint function g1 of the first expression factors δ1, δ2 and δ3 of the autonomous driving is,

[0097]

[0098] Among them, the value range of constraint function g1 is (2,4), and the value range of constraint function g2 is (3,6).

[0099] In this embodiment, the safety redundancy function G of the autonomous driving system is:

[0100]

[0101] Among them, a is the difference value data information of the autonomous driving of the whole vehicle, and λ1, λ2 and λ3 are the safety redundancy determining factors of the autonomous driving system.

[0102] In this embodiment, the present invention provides a high-level autonomous driving system safety redundancy system, including a computer device, which is programmed or configured to execute the steps of any one of the high-level autonomous driving system safety redundancy methods.

[0103] In this embodiment, if Figure 4 As shown, autonomous driving domain control redundant backup, communication redundant backup and actuator (steering, braking) redundant backup.

[0104] (1) Redundant backup of autonomous driving domain control: A new minimum safety control unit is added and connected to the auxiliary CANFD.

[0105] (2) Communication redundancy backup: In addition to the original CANFD communication, a new independent CANFD is added, namely auxiliary CANFD.

[0106] (3) Actuator (steering, braking) redundant backup: The braking system consists of ESC and EB, and there are two independent control units in the steering system.

[0107] The specific implementation plan is to add a backup CANFD to the communication links of the autonomous driving system, braking system, steering system and drive system, with two independent CANFD communication capabilities. The main HAD controller is connected to both the main and auxiliary CANFD, and the newly added minimum safety control unit is connected to the auxiliary CANFD. The braking system consists of ESC and EB, which are respectively connected to the main CAN and the backup CAN. There are two independent control units EPS-A and EPS-B in the steering system, both of which can realize the steering control of the whole vehicle. EPS-A is connected to the main CANFD, and EPS-B is connected to the auxiliary CANFD. For safety and cost considerations, the drive system PDCU does not need to be a redundant backup of the control unit, but needs to be connected to the main and auxiliary CANFD respectively as a redundant backup of the communication.

[0108] This system has designed 10 different failure modes and response strategies. The specific safety redundancy protection strategies are as follows:

[0109]

[0110] In this embodiment, the present invention provides a computer-readable storage medium, on which is stored a computer program programmed or configured to execute any one of the high-order autonomous driving system safety redundancy methods described.

[0111] Any reference to memory, storage, database or other media used in the embodiments provided in the present application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM) and memory bus dynamic RAM (RDRAM).

[0112] In summary, the present invention not only solves the problem that the safety redundant architecture and redundant protection processing strategy are relatively simple, resulting in poor system continuity and riding comfort, but also fully guarantees vehicle driving safety and system reliability, thereby improving user experience.

[0113] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A high-level autonomous driving system safety redundancy method, characterized in that: The method comprises: M1. The vehicle is driving on the road, collecting the historical data information of the vehicle's autonomous driving, and obtaining the data information of the vehicle's autonomous driving in real time based on the on-board CAN transceiver; M2. Based on the historical autonomous driving data information of the vehicle, an ensemble learning algorithm based on a sparrow-optimized random neural network is used to predict the autonomous driving of the entire vehicle, and the predicted autonomous driving data information of the entire vehicle is obtained; M3. Based on the predicted data information of the autonomous driving of the whole vehicle and the data information of the autonomous driving of the whole vehicle, a nonlinear regression algorithm based on multi-factor variance analysis is used to characterize the autonomous driving difference value of each node to obtain the difference value data information of the autonomous driving of the whole vehicle; M4. Based on the difference value data information of the autonomous driving of the whole vehicle, establish the safety redundancy function G of the autonomous driving system, calculate the safety redundancy boundary value of the autonomous driving system, and obtain the data information of the safety redundancy boundary value of the autonomous driving system.

2. The high-level autonomous driving system safety redundancy method according to claim 1, characterized in that: The method further comprises: M5. Based on the data information of the safety redundancy boundary value of the autonomous driving system, a preset threshold is set. If the autonomous driving safety redundancy boundary value is less than the preset threshold, the autonomous driving system of the entire vehicle is normal and the vehicle drives normally. If the autonomous driving safety redundancy boundary value is greater than the preset threshold, the autonomous driving system of the entire vehicle fails and the vehicle cannot drive normally.

3. The high-level autonomous driving system safety redundancy method according to claim 1, characterized in that: In step M2, the use of an ensemble learning algorithm based on a sparrow-optimized random neural network to predict the autonomous driving of the entire vehicle includes: M21. Inputting the historical autonomous driving data information of the vehicle into the ensemble learning model of the random neural network for training and learning, and extracting the model parameters to obtain the model parameter data information of the ensemble learning model of the random neural network; M22. Based on the model parameter data information of the random neural network ensemble learning model, the sparrow population is initialized, the maximum number of iterations is determined, and the data information of the initialized sparrow population is obtained; M23. Based on the data information of the initialized sparrow population, establish the fitness function Q of the individuals in the population, Among them, x is the data information of the initialized sparrow population, α1, α2 and α3 are the fitness determining factors of the population individuals, and the fitness values ​​of the population individuals are calculated to obtain the fitness value data information of the population individuals; M24. Based on the fitness value data information of the population individuals, establish a target optimization function W, Among them, y is the fitness value data information of the population individuals, β1, β2 and β3 are optimization constant parameters, and the model parameters of the ensemble learning model of the random neural network are optimized to obtain the optimized ensemble learning model of the random neural network.

4. The high-level autonomous driving system safety redundancy method according to claim 3, characterized in that: Also includes: M25. Based on the optimized integrated learning model of the random neural network, the historical autonomous driving data information of the vehicle is input, the autonomous driving of the whole vehicle is predicted, and the predicted autonomous driving data information of the whole vehicle is obtained.

5. The high-level autonomous driving system safety redundancy method according to claim 3, characterized in that: The constraint function f of the optimization constant parameters, β1, β2 and β3 is, The value range of the constraint function f is (2,3).

6. The high-level autonomous driving system safety redundancy method according to claim 1, characterized in that: In step M3, the characterization of the autonomous driving difference value of each node by using a nonlinear regression algorithm based on multi-factor variance analysis includes: M31. Based on the predicted data information of the autonomous driving of the whole vehicle, a first expression function R1 of the autonomous driving of the whole vehicle is established. Among them, z1 is the predicted data information of the autonomous driving of the whole vehicle, δ1, δ2 and δ3 are the first expression factors of the autonomous driving, and the autonomous driving data of the whole vehicle is characterized to obtain the first expression matrix data information of the autonomous driving of the whole vehicle; M32. Based on the data information of the autonomous driving of the whole vehicle, a second expression function R2 of the autonomous driving of the whole vehicle is established, Among them, z2 is the data information of the autonomous driving of the whole vehicle, γ1, γ2 and γ3 are the second expression factors of the autonomous driving, and the autonomous driving data of the whole vehicle is represented to obtain the second expression matrix data information of the autonomous driving of the whole vehicle; M33. Based on the second expression matrix data information of the whole vehicle autonomous driving and the first expression matrix data information of the whole vehicle autonomous driving, a function P of multi-factor variance analysis of the whole vehicle autonomous driving is established. Among them, r1 is the first expression matrix data information of the whole vehicle's autonomous driving, r2 is the second expression matrix data information of the whole vehicle's autonomous driving, η1, η2 and η3 are the difference optimization factors of the whole vehicle's autonomous driving, and the difference value of the autonomous driving data of each node is represented to obtain the difference value data information of the whole vehicle's autonomous driving data.

7. The high-level autonomous driving system safety redundancy method according to claim 6, characterized in that: The constraints of the difference optimization factors η1, η2 and η3 of the whole vehicle autonomous driving are: The constraint function g2 of the second expression factors γ1, γ2 and γ3 of the autonomous driving is, The constraint function g1 of the first expression factors δ1, δ2 and δ3 of the autonomous driving is, Among them, the value range of constraint function g1 is (2,4), and the value range of constraint function g2 is (3,6).

8. The high-level autonomous driving system safety redundancy method according to claim 1, characterized in that: The safety redundancy function G of the automatic driving system is: Among them, a is the difference value data information of the autonomous driving of the whole vehicle, and λ1, λ2 and λ3 are the safety redundancy determining factors of the autonomous driving system.

9. A high-level autonomous driving system safety redundancy system, comprising a computer device, characterized in that: The computer device is programmed or configured to execute the steps of the high-level automated driving system safety redundancy method as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program that is programmed or configured to execute the high-level autonomous driving system safety redundancy method as described in any one of claims 1 to 8.

Images