Detection method for drive-by-wire chassis of automatic driving vehicle
By collecting the vehicle's wire-controlled chassis parameters in real time in preset detection scenarios and using genetic algorithms and cluster analysis to calculate evaluation values, the problems of long detection cycle and low accuracy in existing technologies are solved, and efficient and accurate detection of the wire-controlled chassis of autonomous driving vehicles is achieved.
Patent Information
- Application Number
- CN202510879604.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-27
- Publication Date
- 2025-09-12
AI Technical Summary
Existing detection methods for the wire-controlled chassis of autonomous vehicles rely on manual operations, resulting in long testing cycles, high costs and low accuracy.
By collecting various parameter data of the vehicle's wire-controlled chassis in real time in the preset detection scenario, using genetic algorithms and cluster analysis to calculate the evaluation value, combining the optimal value and fitness value, and dynamically correcting the risk level, accurate detection of the vehicle's wire-controlled chassis can be achieved.
It improves the accuracy and objectivity of the wire-controlled chassis detection of autonomous driving vehicles, ensuring the accuracy and reliability of the detection results.
Smart Images
Figure CN120628632A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of autonomous driving detection technology, and in particular to a method for detecting a wire-controlled chassis of an autonomous driving vehicle. Background Art
[0002] Autonomous driving refers to the ability of vehicles to drive themselves without human intervention, enabled by artificial intelligence, sensors, and other technologies. Self-driving cars rely on a collaborative effort between artificial intelligence, visual computing, radar, monitoring devices, and global positioning systems, enabling computers to safely and autonomously operate motor vehicles without any active human input.
[0003] Currently, the drive-by-wire chassis is one of the most important aspects of autonomous driving technology. Its primary role in autonomous driving is improving handling performance, safety, and responsiveness, while simplifying vehicle structure, reducing weight, and increasing range. By replacing traditional mechanical and hydraulic connections with electronic signals, the drive-by-wire chassis achieves electronic and intelligent vehicle control, significantly enhancing vehicle handling performance and safety.
[0004] Therefore, the performance and stability of the wire-controlled chassis are crucial to autonomous driving technology. However, existing wire-controlled chassis detection methods mostly rely on manual operation, with long testing cycles, high costs and low accuracy.
[0005] Therefore, there is an urgent need to provide a method for detecting the wire-controlled chassis of an autonomous driving vehicle, which can improve the accuracy of the wire-controlled chassis detection of the autonomous driving vehicle compared with the existing technology. Summary of the Invention
[0006] The present invention solves the technical problems existing in the prior art and provides a method for detecting a wire-controlled chassis of an autonomous driving vehicle.
[0007] To achieve the above object, the technical solution adopted by the present invention is as follows: A method for detecting a wire-controlled chassis of an autonomous driving vehicle comprises the following steps: S1. Set a preset detection scene, drive the vehicle to the preset detection scene, set a set time, and collect data information of various parameters of the vehicle's wire-controlled chassis in real time. Each parameter includes multiple items within each set time; S2. Calculate the evaluation value of the vehicle within each set time; specifically, the following steps are included: S21. For each parameter, use a genetic algorithm to obtain the optimal value corresponding to the parameter, and at the same time obtain the adaptive value of the optimal value corresponding to each parameter; S22, obtaining the average response value of each parameter; S23. For each parameter, obtain the correlation value between the average response value and the optimal value; S24. Obtaining an evaluation value of the vehicle within the set time based on the relevant value of each parameter and the adaptation value of the optimal value corresponding to each parameter; S3. Calculate a total evaluation value based on the evaluation values within the entire set time, set an evaluation grade, and compare the total evaluation value with the evaluation grade to obtain the evaluation level of the vehicle.
[0008] Furthermore, in step S22, the method for obtaining the average reaction value of each parameter is as follows: cluster analysis is performed on all real-time collected values of each parameter to obtain K clusters, the center points of the K clusters are screened out, the cluster average reaction value of the real-time collected values in the cluster is calculated based on each center point, and then the average reaction value of the parameter is calculated based on the cluster average reaction value of all clusters.
[0009] Furthermore, the mean response value of each parameter was calculated using the following formula: ; ; In the above formula, represents the cluster average of the nth cluster corresponding to the jth parameter within the dth setting time, It represents the average response value of the jth parameter in the dth setting time, d ranges from 1 to D, D is the total number of all setting times, j ranges from 1 to J, J represents the total number of all parameters, Indicates the center point value of the nth cluster corresponding to the jth parameter in the dth setting time, where n ranges from 1 to K. It represents the i-th real-time collected value in the n-th cluster corresponding to the j-th parameter within the d-th set time. i ranges from 1 to I, and I represents the total number of real-time collected values in the cluster.
[0010] Furthermore, in step S23, the correlation value between the average response value and the optimal value of each parameter is calculated by the following formula: ; In the above formula, It represents the correlation value between the average response value of the jth parameter and the optimal value within the dth setting time. represents the optimal value of the jth parameter within the dth setting time, Indicates the first weight value of the jth parameter within the dth setting time, Indicates the second weight value of the jth parameter within the dth setting time, It represents the mth real-time collected value of the jth parameter within the dth set time, where m ranges from 1 to M, and M represents all real-time collected values of the jth parameter within the dth set time.
[0011] Furthermore, 、 The following constraints are met: ; ; In the above formula, It represents the fitness value of the optimal value corresponding to the jth parameter within the dth setting time.
[0012] Furthermore, in step S24, the evaluation value of the vehicle within each set time is calculated by the following formula: ; In the above formula, represents the evaluation value within the d-th set time, It represents the fitness value of the optimal value corresponding to the jth parameter within the dth setting time.
[0013] Furthermore, the total evaluation value obtained in step S3 is calculated according to the following formula: ; In the above formula, Indicates the total evaluation value.
[0014] Furthermore, the evaluation levels set in step S3 include low risk level, medium risk level and high risk level, and a first risk value and a second risk value are set. The first risk value is less than the second risk value. When the total evaluation value is less than or equal to the first risk value, the vehicle is judged to be at a low risk level. When the total evaluation value is greater than the first risk value and less than or equal to the second risk value, the vehicle is judged to be at a medium risk level. When the total evaluation value is greater than the second risk value, the vehicle is judged to be at a high risk level.
[0015] Furthermore, according to the total evaluation value obtained after each vehicle inspection, the first risk value and the second risk value are dynamically corrected, specifically by the following formula: ; ; In the above formula, represents the first risk value after correction, represents the first risk value initially set, represents the first correction factor, represents the second correction factor, Indicates the maximum total evaluation value in the previous vehicle detection process, represents the modified second risk value, Indicates the second risk value initially set; 、 The following constraints are met: .
[0016] Furthermore, the parameters in step S1 include steering performance parameters, braking performance parameters, driving performance parameters, and stability parameters.
[0017] Compared with the prior art, the present invention has the following beneficial effects: The present invention presets a detection scenario and drives the vehicle into the preset detection scenario to simulate the driving process of the vehicle in normal operation, thereby obtaining data information of various parameters related to the vehicle's wire-controlled chassis. Within each set time, each parameter includes multiple real-time collected values. For the real-time collected values of each parameter within each set time, a genetic algorithm is used to obtain the optimal value of the parameter at the set time and the fitness value corresponding to the optimal value. At the same time, based on the real-time collected values of each parameter at each set time, the average reaction value of the parameter at the set time is obtained. Then, based on the correlation value of the optimal value and the reaction value, an evaluation value of the vehicle at the set time is obtained according to the correlation value and the fitness value. Based on the evaluation values at all set times, a total evaluation value is obtained; and based on the total evaluation value, the risk level of the vehicle is evaluated. The detection and evaluation method of the vehicle's wire-controlled chassis of the present invention takes into account the correlation between the actual parameter reaction value of the vehicle and the optimal parameter reaction value. The evaluation value calculated based on the correlation and the fitness value of the optimal value is more objective and more accurate, thereby ensuring that the detection result of the vehicle's wire-controlled chassis is more precise and accurate. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] Figure 1 It is a flow chart of the present invention. DETAILED DESCRIPTION
[0019] The technical solution of the present invention will be clearly described below in conjunction with the accompanying drawings. Obviously, the described embodiments are not all embodiments of the present invention. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.
[0020] like Figure 1 As shown, the present invention provides a method for detecting a wire-controlled chassis of an autonomous driving vehicle, comprising the following steps: S1. Set a preset detection scene and drive the vehicle to the preset detection scene. During the detection period, set multiple set times. During each set time, data information of various parameters of the vehicle's wire-controlled chassis is collected in real time to obtain a real-time collection value of each parameter. Within each set time, the real-time collection value of each parameter includes multiple.
[0021] The various parameters of the vehicle's wire-controlled chassis collected in real time include steering performance parameters, braking performance parameters, driving performance parameters and stability parameters.
[0022] S2. Calculate the vehicle evaluation value within each set time based on the real-time collected values of various parameters collected in real time. This specifically includes the following steps: S21. For each parameter, use a genetic algorithm to obtain the optimal value corresponding to the parameter and the adaptive value of the optimal value corresponding to each parameter. The specific method is as follows: (1) Multiple real-time collected values of each parameter are used to generate an initial population, where each individual represents a potential solution.
[0023] (2) Use the fitness function to evaluate each individual and calculate its pros and cons in the current problem.
[0024] (3) Based on the fitness value of each individual, select individuals for reproduction. Specifically, roulette selection method, tournament selection method or ranking selection method can be used for selection, and the selected individuals are the parents.
[0025] (4) Select two or more individuals from the selected individuals for crossover to generate new offspring, which will carry the characteristics of the parent genes.
[0026] (5) Gene mutations are performed on the offspring to introduce random changes to increase the diversity of the population and prevent premature convergence.
[0027] (6) Based on the results of selection, crossover, and mutation, the population is updated and enters the next generation.
[0028] (7) Repeat steps (2) to (6) until the maximum number of iterations is reached, stop the iteration, output the optimal value corresponding to the parameter, and use the fitness function to obtain the fitness value of the optimal value.
[0029] S22. Obtain the average reaction value of each parameter, specifically: perform cluster analysis on all real-time collected values of each parameter using the K-means clustering method to obtain K clusters, filter out the center points of the K clusters, calculate the cluster average reaction value of all real-time collected values in the cluster based on each center point, and then calculate the average reaction value of the parameter based on the cluster average reaction value of all clusters.
[0030] In the dth setting time, the cluster average of the nth cluster corresponding to the jth parameter is calculated by the following formula: ; In the above formula, It represents the cluster average of the nth cluster corresponding to the jth parameter in the dth setting time, d ranges from 1 to D, D is the total number of all setting times, j ranges from 1 to J, J represents the total number of all parameters, Indicates the center point value of the nth cluster corresponding to the jth parameter in the dth setting time, where n ranges from 1 to K. It represents the i-th real-time collected value in the n-th cluster corresponding to the j-th parameter within the d-th set time. i ranges from 1 to I, and I represents the total number of real-time collected values in the cluster.
[0031] According to the cluster average of all clusters corresponding to the jth parameter within the dth set time, the average response value of the parameter is calculated by the following formula: ; In the above formula, It represents the average response value of the jth parameter within the dth setting time.
[0032] S23. For each parameter, obtain the correlation value between its average response value and the optimal value; the correlation value between the average response value and the optimal value of each parameter is specifically calculated by the following formula: ; In the above formula, It represents the correlation value between the average response value of the jth parameter and the optimal value within the dth setting time. represents the optimal value of the jth parameter within the dth setting time, Indicates the first weight value of the jth parameter within the dth setting time, Indicates the second weight value of the jth parameter within the dth setting time, It represents the mth real-time collected value of the jth parameter within the dth set time, where m ranges from 1 to M, and M represents all real-time collected values of the jth parameter within the dth set time.
[0033] 、 The following constraints are met: ; ; In the above formula, It represents the fitness value of the optimal value corresponding to the jth parameter within the dth setting time.
[0034] S24. Obtain an evaluation value of the vehicle within the set time based on the relevant value of each parameter and the adaptation value of the optimal value corresponding to each parameter. The evaluation value of the vehicle within the set time is specifically calculated using the following formula: ; In the above formula, Indicates the evaluation value within the d-th set time.
[0035] S3. Calculate the total evaluation value based on the evaluation values within the entire set time, set the evaluation level, and compare the total evaluation value with the evaluation level to obtain the evaluation level of the vehicle; the evaluation level includes low risk level, medium risk level and high risk level, set a first risk value and a second risk value, the first risk value is greater than the second risk value, and compare the total evaluation value with the first risk value and the second risk value to obtain the specific evaluation level of the vehicle. When the total evaluation value is greater than or equal to the first risk value, the vehicle is determined to be at a low risk level; when the total evaluation value is less than the first risk value and greater than or equal to the second risk value, the vehicle is determined to be at a medium risk level; when the total evaluation value is less than the second risk value, the vehicle is determined to be at a high risk level.
[0036] The total evaluation value is calculated by the following formula: ; In the above formula, Indicates the total evaluation value.
[0037] According to the detection results of each vehicle, the first risk value and the second risk value are dynamically corrected, specifically using the following formula: ; ; In the above formula, represents the first risk value after correction, represents the first risk value initially set, represents the first correction factor, represents the second correction factor, Indicates the maximum total evaluation value in the previous vehicle detection process, represents the modified second risk value, Indicates the second risk value initially set.
[0038] 、 The following constraints are met: .
[0039] In the present invention, a vehicle is driven into a preset detection scenario to simulate the driving process of the vehicle under normal operating conditions, thereby obtaining data information of various parameters related to the vehicle's wire-controlled chassis. Within each set time, each parameter includes multiple real-time collected values. For the real-time collected values of each parameter within each set time, a genetic algorithm is used to obtain the optimal value of the parameter at the set time and the fitness value corresponding to the optimal value. At the same time, based on the real-time collected values of each parameter at each set time, the average reaction value of the parameter at the set time is obtained. Then, based on the correlation value of the optimal value and the reaction value, an evaluation value of the vehicle at the set time is obtained according to the correlation value and the fitness value. Based on the evaluation values at all set times, a total evaluation value is obtained; and based on the total evaluation value, the risk level of the vehicle is evaluated. The detection and evaluation method of the vehicle's wire-controlled chassis of the present invention takes into account the correlation between the actual parameter reaction value of the vehicle and the optimal parameter reaction value. The evaluation value calculated based on the correlation and the fitness value of the optimal value is more objective and more accurate, thereby ensuring that the detection result of the vehicle's wire-controlled chassis is more precise and accurate.
[0040] Finally, it should be noted that the above content is only used to illustrate the technical solution of the present invention, rather than to limit the scope of protection of the present invention. Simple modifications or equivalent substitutions of the technical solution of the present invention by ordinary technicians in this field do not deviate from the essence and scope of the technical solution of the present invention.
Claims
1. A method for detecting a wire-controlled chassis of an autonomous driving vehicle, characterized in that: The following steps are involved: S1. Set a preset detection scene, drive the vehicle to the preset detection scene, set a set time, and collect data information of various parameters of the vehicle's wire-controlled chassis in real time. Each parameter includes multiple items within each set time; S2. Calculate the evaluation value of the vehicle within each set time; specifically, the following steps are included: S21. For each parameter, use a genetic algorithm to obtain the optimal value corresponding to the parameter, and at the same time obtain the adaptive value of the optimal value corresponding to each parameter; S22, obtaining the average response value of each parameter; S23. For each parameter, obtain the correlation value between the average response value and the optimal value; S24. Obtaining an evaluation value of the vehicle within the set time based on the relevant value of each parameter and the adaptation value of the optimal value corresponding to each parameter; S3. Calculate a total evaluation value based on the evaluation values within the entire set time, set an evaluation grade, and compare the total evaluation value with the evaluation grade to obtain the evaluation level of the vehicle.
2. The method for detecting a wire-controlled chassis of an autonomous driving vehicle according to claim 1, characterized in that: In step S22, the method for obtaining the average reaction value of each parameter is as follows: perform cluster analysis on all real-time collected values of each parameter to obtain K clusters, filter out the center points of the K clusters, calculate the cluster average reaction value of the real-time collected values in the cluster based on each center point, and then calculate the average reaction value of the parameter based on the cluster average reaction value of all clusters.
3. The method for detecting a wire-controlled chassis of an autonomous driving vehicle according to claim 2, wherein: The mean response value for each parameter was calculated using the following formula: ； ； In the above formula, represents the cluster average of the nth cluster corresponding to the jth parameter within the dth setting time, It represents the average response value of the jth parameter in the dth setting time, d ranges from 1 to D, D is the total number of all setting times, j ranges from 1 to J, J represents the total number of all parameters, Indicates the center point value of the nth cluster corresponding to the jth parameter in the dth setting time, where n ranges from 1 to K. It represents the i-th real-time collected value in the n-th cluster corresponding to the j-th parameter within the d-th set time. i ranges from 1 to I, and I represents the total number of real-time collected values in the cluster.
4. The method for detecting a wire-controlled chassis of an autonomous driving vehicle according to claim 3, wherein: In step S23, the correlation value between the average response value and the optimal value of each parameter is calculated by the following formula: ； In the above formula, It represents the correlation value between the average response value of the jth parameter and the optimal value within the dth setting time. represents the optimal value of the jth parameter within the dth setting time, Indicates the first weight value of the jth parameter within the dth setting time, Indicates the second weight value of the jth parameter within the dth setting time, It represents the mth real-time collected value of the jth parameter within the dth set time, where m ranges from 1 to M, and M represents all real-time collected values of the jth parameter within the dth set time.
5. The method for detecting a wire-controlled chassis of an autonomous driving vehicle according to claim 4, wherein: 、 The following constraints are met: ； ； In the above formula, It represents the fitness value of the optimal value corresponding to the jth parameter within the dth setting time.
6. The method for detecting a wire-controlled chassis of an autonomous driving vehicle according to claim 4, wherein: In step S24, the evaluation value of the vehicle within each set time is calculated using the following formula: ； In the above formula, represents the evaluation value within the d-th set time, It represents the fitness value of the optimal value corresponding to the jth parameter within the dth setting time.
7. The method for detecting a wire-controlled chassis of an autonomous driving vehicle according to claim 6, wherein: The total evaluation value obtained in step S3 is calculated according to the following formula: ； In the above formula, Indicates the total evaluation value.
8. The method for detecting a wire-controlled chassis of an autonomous driving vehicle according to claim 7, wherein: The evaluation levels set in step S3 include low risk level, medium risk level and high risk level. A first risk value and a second risk value are set. The first risk value is less than the second risk value. When the total evaluation value is less than or equal to the first risk value, the vehicle is judged to be at a low risk level. When the total evaluation value is greater than the first risk value and less than or equal to the second risk value, the vehicle is judged to be at a medium risk level. When the total evaluation value is greater than the second risk value, the vehicle is judged to be at a high risk level.
9. The method for detecting a wire-controlled chassis of an autonomous driving vehicle according to claim 8, characterized in that: According to the total evaluation value obtained after each vehicle inspection, the first risk value and the second risk value are dynamically corrected, specifically using the following formula: ； ； In the above formula, represents the first risk value after correction, represents the first risk value initially set, represents the first correction factor, represents the second correction factor, Indicates the maximum total evaluation value in the previous vehicle detection process, represents the modified second risk value, Indicates the second risk value initially set; 、 The following constraints are met: 。 10. The method for detecting a wire-controlled chassis of an autonomous driving vehicle according to claim 1, wherein: The parameters in step S1 include steering performance parameters, braking performance parameters, driving performance parameters, and stability parameters.