Methods, computer systems, storage media, and software products for analyzing road surface conditions

By analyzing road conditions using non-visual sensors and visual transformation technology, the high cost of existing driving environment perception technologies is solved, enabling effective classification of road conditions and improved vehicle comfort without relying on onboard vision equipment.

CN123115997APending Publication Date: 2026-11-17NIO TECH ANHUI CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202611230684.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-08-13
Publication Date
2026-11-17

AI Technical Summary

Technical Problem

Existing driving environment perception technologies rely on in-vehicle cameras and high-performance computing devices, which are costly and difficult to implement in all vehicles.

Method used

Sensor signals are acquired by non-visual sensors such as inertial measurement units and suspension travel sensors, semantic enhancement is performed using a vision transformer, and road conditions are classified through encoders and classifiers, reducing reliance on on-board vision technology.

Benefits of technology

It enables the analysis of road conditions without relying on onboard vision technology, improving vehicle driving comfort and reducing costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123115997A_ABST
    Figure CN123115997A_ABST
Patent Text Reader

Abstract

This application relates to a method, computer system, storage medium, and program product for analyzing road surface conditions. The method includes: acquiring sensor signals from a non-visual sensor used to perceive road surface conditions; inputting time-frequency plot data of the sensor signals into a trained encoder, wherein the feature vectors of the sensor signals are semantically enhanced based on visual information; and inputting the semantically enhanced feature vectors of the sensor signals into a trained classifier to obtain a classification result of the road surface conditions.
Need to check novelty before this filing date? Find Prior Art