A road adhesion coefficient estimation method based on time-space synchronization and information fusion

Abstract

The present invention provides a method for estimating road surface adhesion coefficient based on time-space synchronization and information fusion, simultaneously collects road surface image information in front of the vehicle and vehicle dynamic response information, extracts effective road surface areas in the collected road surface image in front of the vehicle through a semantic segmentation network, and then sends Enter the road surface type recognition network to obtain the road surface type recognition results, according to the collected vehicle dynamics response information, use the unscented Kalman filter estimation method to obtain the estimated value of the road surface adhesion coefficient, and obtain the road surface type recognition results that meet the fusion conditions through the time-space synchronization method and the estimated value of the road surface adhesion coefficient; finally judge the comparison result of the confidence threshold value of the preset road surface type recognition result and the weighted probability value, and fuse and output the final estimated value of the road surface adhesion coefficient; this method can realize the road surface type data in front of the vehicle and the vehicle The time-space synchronization of dynamic response information data ensures the predictability and accuracy of the fused pavement adhesion coefficient estimation results.

Description

technical field [0001] The invention belongs to the field of road surface adhesion coefficient identification, and relates to a road surface adhesion coefficient estimation method, more specifically, to a road surface adhesion coefficient estimation method based on time-space synchronization and information fusion. Background technique [0002] The quality of the road surface is the most direct factor affecting whether the vehicle can drive safely, and the road surface adhesion coefficient represents the maximum interaction force that can be generated between the tire and the road surface, which directly affects the driving performance, braking performance and handling stability of the car. sex. Accurately obtaining the road surface adhesion coefficient can expand the working condition adaptation range of the active safety system of the vehicle, and the early perception of changes in the state of the road ahead can help the active safety system adjust the control strategy in...

AI Technical Summary

Problems solved by technology

[0003] The present invention aims to solve the problems of a certain degree of recognition error and hysteresis in existing road surface adhesion coefficient recognition methods, and combines the road surface type recognition method based on vision with the road surface adhesion coefficient estimation method based on vehicle dynamics response information, and proposes a method based on The road surface adhesion coefficient estimation method based on space-time synchronization and information fusion has the advantages of predictability and accuracy; firstly, the image information of the road surface in front of the vehicle and the vehicle dynamic response information are collected simultaneously; the road surface image in front of the vehicle is extracted through the semantic segmentation network The effective road surface area in the center is sent to the road surface type recognition network to obtain the road surface type recognition result. At the same time, according to the vehicle dynamic response information collected, the estimated value of the road surface adhesion coefficient is obtained by using the unscented Kalman filter estimation method; and then through the space-time synchronization The method screens out the road surface type identification results and the estimated value of the road surface adhesion coefficient that meet the fusion conditions; finally judges the comparison result of the confidence threshold value of the preset road surface type identification result and the weighted probability value, and fuses and outputs the final estimated value of the road surface adhesion coefficient

Images