Game decision system and method for dynamic target cross-domain pursuit

By deeply coupling traffic data with target trajectory analysis and neural network modeling, the problem of insufficient reliability of path planning results in existing technologies is solved, realizing accurate path planning and dynamic adjustment of pursuit paths in complex traffic environments, thereby improving the success rate and execution efficiency of pursuit missions.

CN121281271BActive Publication Date: 2026-06-26XIDIAN UNIV
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
XIDIAN UNIV
Filing Date
2025-10-22
Publication Date
2026-06-26

AI Technical Summary

Technical Problem

Existing technologies fail to adequately consider the real-time impact of traffic environment on target behavior in path planning, resulting in insufficient reliability of path planning results, especially in complex traffic environments where pursuit paths frequently fail.

Method used

By deeply coupling traffic data with target trajectories, neural networks are used to model the impact of the traffic environment on target behavior. Combined with dense area identification and cluster analysis, an environmentally adaptable pursuit path is generated.

Benefits of technology

It improves the accuracy and reliability of route planning, enables dynamic route adjustment to cope with changes in traffic environment, avoids route failure, and improves the success rate and execution efficiency of pursuit missions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121281271B_ABST
    Figure CN121281271B_ABST
Patent Text Reader

Abstract

The application discloses a game decision system and method for dynamic target cross-domain pursuit, relates to the technical field of intelligent traffic and multi-agent collaborative decision, and comprises the following steps: periodically acquiring first traffic data, first trajectory data of each target and first state data of each agent; performing spatial grid mapping processing on the first traffic data to obtain second traffic data representing traffic operation states; and preprocessing the second traffic data to generate fourth traffic data representing traffic loads. Through feature matching and correlation coefficient calculation, the application realizes deep coupling analysis of trajectory and traffic data, captures complex nonlinear relationships between the two through a deep neural network, and enables the influence of the traffic environment on target behavior to be accurately modeled. Through the technical scheme, the application can accurately quantify the real-time influence of the traffic environment on the target trajectory, and provide a dynamic adjustment basis for path planning of the agent pursuit.
Need to check novelty before this filing date? Find Prior Art