Multi-traffic participant modeling method and system fusing intention reasoning and density gradient

By integrating intent reasoning and density gradient multi-traffic participant modeling methods, this approach addresses the problem of existing technologies failing to consider traffic density and specific behaviors, achieving more realistic traffic participant simulation and improving the accuracy and safety of autonomous driving simulation testing.

CN121920248BActive Publication Date: 2026-06-26SUZHOU GUANRUI AUTOMOBILE TECH CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
SUZHOU GUANRUI AUTOMOBILE TECH CO LTD
Filing Date
2026-03-26
Publication Date
2026-06-26

AI Technical Summary

Technical Problem

Existing traffic participant models fail to effectively consider specific behaviors and real-time traffic density in different scenarios during autonomous driving simulation testing, thus affecting simulation results.

Method used

This paper proposes a multi-traffic participant modeling method that integrates intention reasoning and density gradient. By acquiring dynamic data of multiple traffic participants, it constructs behavioral models of motor vehicles, non-motor vehicles, and pedestrians. It uses Bayesian inference and deep Q-networks to optimize decision-making and combines social force models to simulate the interactions between traffic participants.

Benefits of technology

It improves the realism and effectiveness of traffic participant simulation, naturally simulating congestion, exclusion, and following behaviors in complex scenarios, thereby enhancing the accuracy and safety of simulation testing.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121920248B_ABST
    Figure CN121920248B_ABST
Patent Text Reader

Abstract

The application relates to the technical field of traffic scene simulation, and discloses a multi-traffic-participant modeling method and system fusing intention reasoning and density gradient, which comprises the following steps: acquiring dynamic data of multi-traffic-participants in a complex traffic scene, wherein the multi-traffic-participants comprise motor vehicles, non-motor vehicles and pedestrians; constructing a motor vehicle behavior model according to the dynamic data of the motor vehicles, wherein the motor vehicle behavior model predicts overall behavior intention and specific behavior intention of the motor vehicles; and constructing non-motor vehicle behavior models and pedestrian behavior models based on behaviors of the non-motor vehicles, behaviors of the pedestrians and traffic density according to the dynamic data of the non-motor vehicles and the dynamic data of the pedestrians. The application can model behaviors of traffic participants and improve simulation effects of pedestrians and vehicles.
Need to check novelty before this filing date? Find Prior Art