A multi-scenario autonomous driving vehicle safety and comfort parameter calibration method and system

Abstract

The present invention relates to a multi-scenario safety and comfort parameter adjustment and calibration method and system for autonomous driving vehicles. The method comprises: Q1. While the vehicle is traveling on the road, real-time collection of vehicle status data, environmental perception data, and passenger comfort feedback data is performed, and the data is cleaned, denoised, and standardized to obtain processed vehicle status data, environmental perception data, and passenger comfort feedback data; Q2. Based on the processed vehicle status data, environmental perception data, and passenger comfort feedback data, the present invention is not only capable of automatically adapting to a variety of complex functional scenarios and achieving intelligent parameter adjustment and calibration without manual intervention, but also, while ensuring the safe driving of the autonomous vehicle, takes into account the passenger comfort experience and improves the overall driving quality.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving vehicle technology, and in particular to a method and system for calibrating safety and comfort parameters of autonomous driving vehicles in multiple scenarios. Background Art

[0002] As autonomous driving technology matures, its application in real-world road environments is becoming increasingly widespread. However, autonomous vehicles face diverse driving scenarios, such as congested urban roads, highways, complex intersections, and adverse weather conditions. This places extremely high demands on the safety and comfort of autonomous driving software. Traditional manual parameter tuning methods are not only time-consuming and labor-intensive, but also difficult to adapt to rapidly changing environmental demands. Summary of the Invention

[0003] In view of the above problems, the present invention provides a multi-scenario autonomous driving vehicle safety and comfort parameter adjustment and calibration method and system, which can not only automatically adapt to a variety of complex functional scenarios and realize intelligent adjustment and calibration of parameters without human intervention, but also ensure the safe driving of autonomous vehicles while taking into account the comfort experience of passengers and improving the overall driving quality.

[0004] In order to achieve the above-mentioned and other related purposes, the present invention provides the following technical solutions:

[0005] A multi-scenario autonomous driving safety and comfort parameter calibration method, the method comprising:

[0006] Q1. While driving on the road, the vehicle collects real-time vehicle status data, environmental perception data, and passenger comfort feedback data. The data is then cleaned, denoised, and standardized to produce processed vehicle status data, environmental perception data, and passenger comfort feedback data.

[0007] Q2. Based on the processed vehicle status data, environmental perception data, and passenger comfort feedback data, use the autonomous vehicle multi-scenario recognition and classification algorithm to identify and classify the functional scenario the vehicle is currently in, and obtain the type of the vehicle scenario and classification result data;

[0008] Q3. Based on the type of scene in which the vehicle is located and the classification result data information, a parameter optimization model for the autonomous vehicle is constructed, and various parameters of the autonomous vehicle are optimized and adjusted to obtain optimized parameter data information of the autonomous vehicle;

[0009] Q4. Based on the parameter data information of the optimized autonomous driving vehicle, a comprehensive evaluation function P of the autonomous driving vehicle is established to evaluate the performance of the autonomous driving vehicle after parameter adjustment to obtain performance evaluation data information of the autonomous driving vehicle.

[0010] Furthermore, the method further comprises:

[0011] Q5. Based on the performance evaluation data information of the autonomous driving vehicle, a preset threshold is set. If the performance evaluation of the autonomous driving vehicle exceeds the preset threshold, the automatic parameter adjustment is completed. If the performance evaluation of the autonomous driving vehicle is less than the preset threshold, the automatic parameter adjustment is not completed, and return to step Q3.

[0012] Furthermore, in step Q2, the use of the multi-scenario recognition and classification algorithm for the autonomous driving vehicle to identify and classify the functional scenario in which the current vehicle is located includes:

[0013] Q21. Based on the processed vehicle status data information, environmental perception data information and passenger comfort feedback data information, establish a vehicle multimodal fusion function W,

[0014]

[0015] Among them, x1 is the processed vehicle status data information, x2 is the environmental perception data information, x3 is the passenger comfort feedback data information, α1, α2 and α3 are the multimodal fitting factors of the vehicle. The multimodal data of the vehicle is fused to obtain the fused vehicle multimodal data information;

[0016] Q22. Based on the fused vehicle multimodal data information, establish the recognition function R of the autonomous driving vehicle scene.

[0017]

[0018] Where y is the fused multimodal data information of the vehicle, β1 and β2 are the identification factors of the autonomous driving vehicle, and the scene type of the autonomous driving vehicle is identified to obtain the identified autonomous driving scene type data information;

[0019] Q23. Based on the identified autonomous driving scene type data information, establish a classification function U for the autonomous driving vehicle.

[0020]

[0021] Among them, z is the data information of the identified autonomous driving scene type, δ1, δ2 and δ3 are the scene classification gain constant parameters of the autonomous driving vehicle, which classify the functional scene in which the current vehicle is located to obtain the type of the vehicle scene and the classification result data information.

[0022] Furthermore, the multimodal fitting factors α1, α2 and α3 of the vehicle are,

[0023]

[0024]

[0025]

[0026] Among them, x1 is the processed vehicle status data information, x2 is the environmental perception data information, and x3 is the passenger comfort feedback data information.

[0027] Furthermore, the constraints of the scene classification gain constant parameters δ1, δ2 and δ3 of the autonomous driving vehicle are as follows:

[0028]

[0029] Furthermore, in step Q3, the construction of the parameter optimization model of the autonomous driving vehicle and the optimization and adjustment of various parameters of the autonomous driving vehicle include:

[0030] Q31. Based on the type of scene the vehicle is in and the classification result data information, establish the relationship function S between the various parameters of the autonomous driving vehicle and the scene classification,

[0031]

[0032] Among them, r1 is the type data information of the scene in which the vehicle is located, r2 is the classification result data information of the scene in which the vehicle is located, r3 is the parameter matrix of the autonomous driving vehicle, γ1, γ2 and γ3 are the relationship factors between the parameters of the autonomous driving vehicle and the scene classification. The relationship between the parameters of the autonomous driving vehicle and the scene classification is characterized to obtain the relationship matrix data information of the parameters of the autonomous driving vehicle and the scene classification;

[0033] Q32. Based on the relationship matrix data information between the various parameters of the autonomous driving vehicle and the scene classification, establish the objective function G for parameter optimization of the autonomous driving vehicle.

[0034]

[0035] Among them, h is the relationship matrix data information between various parameters of the autonomous driving vehicle and scene classification, η1, η2 and η3 are the parameter optimization factors of the autonomous driving vehicle;

[0036] Q33. Based on the objective function G of the parameter optimization of the autonomous driving vehicle, various parameters of the autonomous driving vehicle are optimized and adjusted to obtain the parameter data information of the optimized autonomous driving vehicle.

[0037] Furthermore, the constraint function f of the parameter optimization decision factors η1, η2 and η3 of the autonomous driving vehicle is,

[0038]

[0039] Among them, the value range of f is (2,3).

[0040] Furthermore, the comprehensive evaluation function P of the autonomous driving vehicle is:

[0041]

[0042] Among them, c is the optimized parameter data information of the autonomous driving vehicle, and θ1, θ2 and θ3 are the comprehensive evaluation factors of the parameters of the autonomous driving vehicle.

[0043] To achieve the above-mentioned and other related objectives, the present invention further provides a system for implementing any of the above-mentioned methods for calibrating safety and comfort parameters of autonomous driving vehicles in multiple scenarios, the system comprising:

[0044] The data acquisition and preprocessing module is used to collect various data during the driving process of the autonomous vehicle in real time, including vehicle status, environmental perception, and passenger comfort feedback data, and clean, denoise, and standardize the data;

[0045] The scene recognition and classification module uses deep learning algorithms and multi-sensor fusion technology to comprehensively analyze the collected data and identify the specific functional scenario the vehicle is currently in.

[0046] Intelligent adjustment and optimization model is used to build a parameter optimization model for autonomous driving vehicles, optimize and adjust various parameters of autonomous driving vehicles, and obtain optimized parameter data information of autonomous driving vehicles;

[0047] The calibration verification and feedback module is used to establish a comprehensive evaluation function P of the autonomous driving vehicle, evaluate the performance of the autonomous driving vehicle after parameter adjustment, and obtain performance evaluation data information of the autonomous driving vehicle.

[0048] 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 multi-scenario autonomous driving vehicle safety and comfort parameter adjustment and calibration methods.

[0049] The present invention has the following positive effects:

[0050] 1. The present invention uses a multi-scenario recognition and classification algorithm for autonomous vehicles to identify and classify the functional scenario in which the vehicle is currently located. Furthermore, by combining this with the construction of a parameter optimization model for autonomous vehicles, the present invention optimizes and adjusts various parameters of the autonomous vehicle to obtain optimized parameter data information for the autonomous vehicle. This not only enables intelligent data analysis and precise parameter adjustment, but also possesses self-learning capabilities, enabling the system to continuously optimize and adjust algorithm models and parameter settings during actual operation to adapt to ever-changing environments and needs.

[0051] 2. This invention establishes a comprehensive evaluation function P for autonomous vehicles to evaluate the performance of adjusted autonomous vehicles. This function not only automatically adapts to a variety of complex functional scenarios and intelligently adjusts and calibrates parameters without human intervention, but also ensures the safety of autonomous vehicles while also taking into account the comfort experience of passengers, thereby improving overall driving quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 Schematic diagram of the method flow of the present invention;

[0053] Figure 2 Schematic diagram of the flow of the multi-scene recognition and classification algorithm for autonomous driving vehicles of the present invention;

[0054] Figure 3 A schematic diagram of the process of constructing a parameter optimization model for an autonomous driving vehicle according to the present invention;

[0055] Figure 4 It is a schematic diagram of the system framework structure of the present invention. DETAILED DESCRIPTION

[0056] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize 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.

[0057] Example 1: Figure 1 As shown, a multi-scenario autonomous driving safety and comfort parameter calibration method includes:

[0058] Q1. While driving on the road, the vehicle collects real-time vehicle status data, environmental perception data, and passenger comfort feedback data. The data is then cleaned, denoised, and standardized to produce processed vehicle status data, environmental perception data, and passenger comfort feedback data.

[0059] Q2. Based on the processed vehicle status data, environmental perception data, and passenger comfort feedback data, use the autonomous vehicle multi-scenario recognition and classification algorithm to identify and classify the functional scenario the vehicle is currently in, and obtain the type of the vehicle scenario and classification result data;

[0060] Q3. Based on the type of scene in which the vehicle is located and the classification result data information, a parameter optimization model for the autonomous vehicle is constructed, and various parameters of the autonomous vehicle are optimized and adjusted to obtain optimized parameter data information of the autonomous vehicle;

[0061] Q4. Based on the parameter data information of the optimized autonomous driving vehicle, a comprehensive evaluation function P of the autonomous driving vehicle is established to evaluate the performance of the autonomous driving vehicle after parameter adjustment to obtain performance evaluation data information of the autonomous driving vehicle.

[0062] In this embodiment, the method further includes:

[0063] Q5. Based on the performance evaluation data information of the autonomous driving vehicle, a preset threshold is set. If the performance evaluation of the autonomous driving vehicle exceeds the preset threshold, the automatic parameter adjustment is completed. If the performance evaluation of the autonomous driving vehicle is less than the preset threshold, the automatic parameter adjustment is not completed, and return to step Q3.

[0064] In this embodiment, in step Q2, the use of the multi-scenario recognition and classification algorithm for the autonomous driving vehicle to identify and classify the functional scenario in which the current vehicle is located includes:

[0065] Q21. Based on the processed vehicle status data information, environmental perception data information and passenger comfort feedback data information, establish a vehicle multimodal fusion function W,

[0066]

[0067] Among them, x1 is the processed vehicle status data information, x2 is the environmental perception data information, x3 is the passenger comfort feedback data information, α1, α2 and α3 are the multimodal fitting factors of the vehicle. The multimodal data of the vehicle is fused to obtain the fused vehicle multimodal data information;

[0068] Q22. Based on the fused vehicle multimodal data information, establish the recognition function R of the autonomous driving vehicle scene.

[0069]

[0070] Where y is the fused multimodal data information of the vehicle, β1 and β2 are the identification factors of the autonomous driving vehicle, and the scene type of the autonomous driving vehicle is identified to obtain the identified autonomous driving scene type data information;

[0071] Q23. Based on the identified autonomous driving scene type data information, establish a classification function U for the autonomous driving vehicle.

[0072]

[0073] Among them, z is the data information of the identified autonomous driving scene type, δ1, δ2 and δ3 are the scene classification gain constant parameters of the autonomous driving vehicle, which classify the functional scene in which the current vehicle is located to obtain the type of the vehicle scene and the classification result data information.

[0074] In this embodiment, the multimodal fitting factors α1, α2 and α3 of the vehicle are,

[0075]

[0076]

[0077]

[0078] Among them, x1 is the processed vehicle status data information, x2 is the environmental perception data information, and x3 is the passenger comfort feedback data information.

[0079] In this embodiment, the constraints of the scene classification gain constant parameters δ1, δ2 and δ3 of the autonomous driving vehicle are:

[0080]

[0081] Example 2: Based on the multi-scenario autonomous driving safety and comfort parameter calibration method of Example 1, the present invention is further illustrated and described below.

[0082] like Figure 1 As shown, a multi-scenario autonomous driving safety and comfort parameter calibration method includes:

[0083] Q1. While driving on the road, the vehicle collects real-time vehicle status data, environmental perception data, and passenger comfort feedback data. The data is then cleaned, denoised, and standardized to produce processed vehicle status data, environmental perception data, and passenger comfort feedback data.

[0084] Q2. Based on the processed vehicle status data, environmental perception data, and passenger comfort feedback data, use the autonomous vehicle multi-scenario recognition and classification algorithm to identify and classify the functional scenario the vehicle is currently in, and obtain the type of the vehicle scenario and classification result data;

[0085] Q3. Based on the type of scene in which the vehicle is located and the classification result data information, a parameter optimization model for the autonomous vehicle is constructed, and various parameters of the autonomous vehicle are optimized and adjusted to obtain optimized parameter data information of the autonomous vehicle;

[0086] Q4. Based on the parameter data information of the optimized autonomous driving vehicle, a comprehensive evaluation function P of the autonomous driving vehicle is established to evaluate the performance of the autonomous driving vehicle after parameter adjustment to obtain performance evaluation data information of the autonomous driving vehicle.

[0087] In this embodiment, if Figure 3 As shown, in step Q3, the construction of the parameter optimization model of the autonomous driving vehicle and the optimization and adjustment of various parameters of the autonomous driving vehicle include:

[0088] Q31. Based on the type of scene the vehicle is in and the classification result data information, establish the relationship function S between the various parameters of the autonomous driving vehicle and the scene classification,

[0089]

[0090] Among them, r1 is the type data information of the scene in which the vehicle is located, r2 is the classification result data information of the scene in which the vehicle is located, r3 is the parameter matrix of the autonomous driving vehicle, γ1, γ2 and γ3 are the relationship factors between the parameters of the autonomous driving vehicle and the scene classification. The relationship between the parameters of the autonomous driving vehicle and the scene classification is characterized to obtain the relationship matrix data information of the parameters of the autonomous driving vehicle and the scene classification;

[0091] Q32. Based on the relationship matrix data information between the various parameters of the autonomous driving vehicle and the scene classification, establish the objective function G for parameter optimization of the autonomous driving vehicle.

[0092]

[0093] Among them, h is the relationship matrix data information between various parameters of the autonomous driving vehicle and scene classification, η1, η2 and η3 are the parameter optimization factors of the autonomous driving vehicle;

[0094] Q33. Based on the objective function G of the parameter optimization of the autonomous driving vehicle, various parameters of the autonomous driving vehicle are optimized and adjusted to obtain the parameter data information of the optimized autonomous driving vehicle.

[0095] In this embodiment, the constraint function f of the parameter optimization decision factors η1, η2 and η3 of the autonomous driving vehicle is,

[0096]

[0097] Among them, the value range of f is (2,3).

[0098] In this embodiment, the comprehensive evaluation function P of the autonomous driving vehicle is:

[0099]

[0100] Among them, c is the optimized parameter data information of the autonomous driving vehicle, and θ1, θ2 and θ3 are the comprehensive evaluation factors of the parameters of the autonomous driving vehicle.

[0101] In this embodiment, if Figure 4 As shown, the present invention provides a system for implementing any of the above-mentioned multi-scenario autonomous driving vehicle safety and comfort parameter calibration methods, the system comprising:

[0102] The data acquisition and preprocessing module is used to collect various data during the driving process of the autonomous vehicle in real time, including vehicle status, environmental perception, and passenger comfort feedback data, and clean, denoise, and standardize the data;

[0103] The scene recognition and classification module uses deep learning algorithms and multi-sensor fusion technology to comprehensively analyze the collected data and identify the specific functional scenario the vehicle is currently in.

[0104] Intelligent adjustment and optimization model is used to build a parameter optimization model for autonomous driving vehicles, optimize and adjust various parameters of autonomous driving vehicles, and obtain optimized parameter data information of autonomous driving vehicles;

[0105] The calibration verification and feedback module is used to establish a comprehensive evaluation function P of the autonomous driving vehicle, evaluate the performance of the autonomous driving vehicle after parameter adjustment, and obtain performance evaluation data information of the autonomous driving vehicle.

[0106] In this embodiment, the present invention provides a computer-readable storage medium, which stores a computer program programmed or configured to execute any one of the multi-scenario autonomous driving vehicle safety and comfort parameter adjustment and calibration methods.

[0107] Any reference to memory, storage, database or other media used in the embodiments provided herein 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).

[0108] In summary, the present invention can not only automatically adapt to a variety of complex functional scenarios and achieve intelligent adjustment and calibration of parameters without human intervention, but also take into account the passenger comfort experience while ensuring the safe driving of the autonomous vehicle, thereby improving the overall driving quality.

[0109] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A multi-scenario autonomous driving vehicle safety and comfort parameter calibration method, characterized by: The method comprises: Q1. While driving on the road, the vehicle collects real-time vehicle status data, environmental perception data, and passenger comfort feedback data. The data is then cleaned, denoised, and standardized to produce processed vehicle status data, environmental perception data, and passenger comfort feedback data. Q2. Based on the processed vehicle status data, environmental perception data, and passenger comfort feedback data, use the autonomous vehicle multi-scenario recognition and classification algorithm to identify and classify the functional scenario the vehicle is currently in, and obtain the type of the vehicle scenario and classification result data; Q3. Based on the type of scene in which the vehicle is located and the classification result data information, a parameter optimization model for the autonomous vehicle is constructed, and various parameters of the autonomous vehicle are optimized and adjusted to obtain optimized parameter data information of the autonomous vehicle; Q4. Based on the optimized parameter data of the autonomous driving vehicle, establish a comprehensive evaluation function P for the autonomous driving vehicle, evaluate the performance of the autonomous driving vehicle after parameter adjustment, and obtain performance evaluation data information of the autonomous driving vehicle; The method further comprises: Q5. Based on the performance evaluation data information of the autonomous driving vehicle, a preset threshold is set. If the performance evaluation of the autonomous driving vehicle exceeds the preset threshold, the automatic parameter adjustment is completed. If the performance evaluation of the autonomous driving vehicle is less than the preset threshold, the automatic parameter adjustment is not completed, and return to step Q3.

2. The multi-scenario autonomous driving vehicle safety and comfort parameter calibration method according to claim 1 is characterized in that: In step Q2, the use of the multi-scenario recognition and classification algorithm for the autonomous driving vehicle to identify and classify the functional scenario in which the current vehicle is located includes: Q21. Based on the processed vehicle status data information, environmental perception data information and passenger comfort feedback data information, establish a vehicle multimodal fusion function W, ， Among them, x1 is the processed vehicle status data information, x2 is the environmental perception data information, x3 is the passenger comfort feedback data information, α1, α2 and α3 are the multimodal fitting factors of the vehicle. The multimodal data of the vehicle is fused to obtain the fused vehicle multimodal data information; Q22. Based on the fused vehicle multimodal data information, establish the recognition function R of the autonomous driving vehicle scene. ， Where y is the fused multimodal data information of the vehicle, β1 and β2 are the identification factors of the autonomous driving vehicle, and the scene type of the autonomous driving vehicle is identified to obtain the identified autonomous driving scene type data information; Q23. Based on the identified autonomous driving scene type data information, establish a classification function U for the autonomous driving vehicle. ， Among them, z is the data information of the identified autonomous driving scene type, δ1, δ2 and δ3 are the scene classification gain constant parameters of the autonomous driving vehicle, which classify the functional scene in which the current vehicle is located to obtain the type of the vehicle scene and the classification result data information.

3. The multi-scenario autonomous driving vehicle safety and comfort parameter calibration method according to claim 2 is characterized in that: The multimodal fitting factors α1, α2 and α3 of the vehicle are, ， ， ， Among them, x1 is the processed vehicle status data information, x2 is the environmental perception data information, and x3 is the passenger comfort feedback data information.

4. The multi-scenario autonomous driving vehicle safety and comfort parameter calibration method according to claim 2, characterized in that: The constraints of the scene classification gain constant parameters δ1, δ2 and δ3 of the autonomous driving vehicle are: 。 5. The multi-scenario autonomous driving vehicle safety and comfort parameter calibration method according to claim 1 is characterized in that: In step Q3, the construction of the parameter optimization model of the autonomous driving vehicle and the optimization and adjustment of various parameters of the autonomous driving vehicle include: Q31. Based on the type of scene the vehicle is in and the classification result data information, establish the relationship function S between the various parameters of the autonomous driving vehicle and the scene classification, ， Among them, r1 is the type data information of the scene in which the vehicle is located, r2 is the classification result data information of the scene in which the vehicle is located, r3 is the parameter matrix of the autonomous driving vehicle, γ1, γ2 and γ3 are the relationship factors between the parameters of the autonomous driving vehicle and the scene classification. The relationship between the parameters of the autonomous driving vehicle and the scene classification is characterized to obtain the relationship matrix data information of the parameters of the autonomous driving vehicle and the scene classification; Q32. Based on the relationship matrix data information between the various parameters of the autonomous driving vehicle and the scene classification, establish the objective function G for parameter optimization of the autonomous driving vehicle. ， Among them, h is the relationship matrix data information between various parameters of the autonomous driving vehicle and scene classification, η1, η2 and η3 are the parameter optimization factors of the autonomous driving vehicle; Q33. Based on the objective function G of the parameter optimization of the autonomous driving vehicle, various parameters of the autonomous driving vehicle are optimized and adjusted to obtain the parameter data information of the optimized autonomous driving vehicle.

6. The multi-scenario autonomous driving vehicle safety and comfort parameter calibration method according to claim 5 is characterized by: The constraint function f of the parameter optimization decision factors η1, η2 and η3 of the autonomous driving vehicle is, ， Among them, the value range of f is (2,3).

7. The multi-scenario autonomous driving vehicle safety and comfort parameter calibration method according to claim 1, characterized in that: The comprehensive evaluation function P of the autonomous driving vehicle is: ， Among them, c is the optimized parameter data information of the autonomous driving vehicle, and θ1, θ2 and θ3 are the comprehensive evaluation factors of the parameters of the autonomous driving vehicle.

8. A system for implementing the multi-scenario autonomous driving vehicle safety and comfort parameter calibration method according to any one of claims 1 to 7, characterized in that: The system comprises: The data acquisition and preprocessing module is used to collect various data during the driving process of the autonomous vehicle in real time, including vehicle status, environmental perception, and passenger comfort feedback data, and clean, denoise, and standardize the data; The scene recognition and classification module uses deep learning algorithms and multi-sensor fusion technology to comprehensively analyze the collected data and identify the specific functional scenario the vehicle is currently in. Intelligent adjustment and optimization model is used to build a parameter optimization model for autonomous driving vehicles, optimize and adjust various parameters of autonomous driving vehicles, and obtain optimized parameter data information of autonomous driving vehicles; The calibration verification and feedback module is used to establish a comprehensive evaluation function P of the autonomous driving vehicle, evaluate the performance of the autonomous driving vehicle after parameter adjustment, and obtain performance evaluation data information of the autonomous driving vehicle.

9. 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 multi-scenario autonomous driving vehicle safety and comfort parameter adjustment and calibration method as described in any one of claims 1 to 7.

Images