基于BDI的地面无人体系多智能体仿真行为模型构建方法

By constructing a two-layer coupled architecture of BDI and Cousin models, the problem of the disconnect between cognition and behavior in ground-based unmanned systems is solved, enabling the natural movement and efficient task completion of intelligent agent clusters, and improving the realism of simulation scenarios and the robustness of task execution.

CN121959970BActive Publication Date: 2026-07-17HUNAN SHUOQI TECH CO LTD

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
HUNAN SHUOQI TECH CO LTD
Filing Date
2026-04-01
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

In existing multi-agent simulation behavior models of ground-based unmanned systems, cognition and behavior are disconnected, resulting in scattered formations and rigid trajectories during agent swarm maneuvers, as well as a lack of high-level task planning capabilities, making it difficult to efficiently complete dynamic tasks.

Method used

A multi-agent simulation behavior model of a ground-based unmanned system based on BDI is constructed. A cognitive-behavioral dual-layer coupling architecture is established within the intelligent body. Intentions are generated through the BDI decision function and mapped to the dynamic parameter set of the Cousin model. Combined with the perception feedback loop, a decision-action closed loop is formed to realize the quantitative mapping between intentions and behaviors.

Benefits of technology

It improves the naturalness of movement and task efficiency of intelligent agent clusters, enhances the controllability and trustworthiness of unmanned clusters, enables rapid response and adaptive adjustment in complex environments, and significantly improves the robustness of task completion and the realism of simulation scenarios.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121959970B_ABST
    Figure CN121959970B_ABST
Patent Text Reader

Abstract

本发明公开了基于BDI的地面无人体系多智能体仿真行为模型构建方法,涉及无人系统仿真技术领域,包括以下步骤:S1:构建智能体内部BDI认知层;S2:设置意图‑行为转换器;S3:构建Couzin模型层;S4:建立感知反馈回路。本发明,通过双向耦合架构,在保障任务效率的同时,显著提升运动自然度,通过量化映射链,建立从人类指令到集群行为的透明桥梁,增强人对无人集群的信任与可控性,有效解决了传统模型中认知与行为脱节的问题,既让智能体集群在执行任务时展现出流畅自然的自组织运动特性,又能高效完成既定任务目标,显著提升了仿真场景的真实感与智能体行为的自然协调性,使模拟结果更贴近实际地面无人集群的作业表现。
Need to check novelty before this filing date? Find Prior Art