All-terrain work vehicle autonomous obstacle avoidance method and system

By constructing a digital twin system and a multi-physics coupled simulation algorithm, and combining it with operator preferences, the problem of insufficient utilization of multi-source data in the traditional obstacle avoidance technology of all-terrain vehicles has been solved. This has enabled efficient and reliable obstacle avoidance decision-making and fault tolerance capabilities, thereby improving the autonomous obstacle avoidance capabilities of the vehicles.

CN121091879BActive Publication Date: 2026-07-07XIAN ELECTRIFICATION ENG CO LTD OF CHINA RAILWAY ELECTRIFICATION BUREAU GRP +1
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
XIAN ELECTRIFICATION ENG CO LTD OF CHINA RAILWAY ELECTRIFICATION BUREAU GRP
Filing Date
2025-11-06
Publication Date
2026-07-07

AI Technical Summary

Technical Problem

Traditional obstacle avoidance technology for all-terrain vehicles suffers from insufficient utilization of multi-source heterogeneous data, poor obstacle avoidance strategies, lack of operator preference integration and fault tolerance mechanisms, resulting in low environmental perception accuracy, poor robustness, and insufficient operational efficiency and safety.

Method used

A digital twin system is constructed to achieve real-time data synchronization between the physical work vehicle and the digital model. A 5G+edge computing low-latency transmission architecture is adopted, and a pre-simulation optimization algorithm with chaotic particle swarm optimization and Bayesian fusion and a real-time simulation algorithm with multi-physics coupling are combined to screen the optimal obstacle avoidance strategy and incorporate operator preferences. The decision is made through an improved non-dominated sorting genetic algorithm.

Benefits of technology

It significantly improves the accuracy and efficiency of obstacle avoidance decisions, enhances the reliability and fault tolerance of the system, reduces human judgment errors, and ensures the safe and continuous operation of the work vehicle in complex environments.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121091879B_ABST
    Figure CN121091879B_ABST
Patent Text Reader

Abstract

This invention discloses an autonomous obstacle avoidance method and system based on all-terrain vehicles, relating to the field of intelligent vehicle obstacle avoidance technology. The method includes the following components: S1, constructing a digital twin system; S2, real-time data synchronization; S3, multi-scheme pre-simulation; and S4, optimal strategy execution. This invention achieves real-time data synchronization between the physical vehicle and the digital model by constructing a digital twin of the all-terrain vehicle and a digital twin model of the operating environment. Utilizing the low-latency transmission architecture of 5G+edge computing, the real-time performance and accuracy of the data are ensured. In the digital twin system, a pre-simulation optimization algorithm based on chaotic particle swarm optimization-Bayesian fusion, combined with a real-time simulation algorithm involving multi-physics coupling, is used to perform multi-dimensional simulations of energy consumption, time consumption, and stability for various obstacle avoidance schemes. Finally, an improved non-dominated sorting genetic algorithm is used to select the optimal obstacle avoidance strategy, incorporating operator preferences.
Need to check novelty before this filing date? Find Prior Art