arXiv 2604.279352026-04-30cs.ROcs.SYeess.SPeess.SY

通过推断飞行：用于自适应无人机群的主动推断世界模型

Flying by Inference: Active Inference World Models for Adaptive UAV Swarms

Department of Engineering and Naval Architecture (DITEN), University of Genoa（工程与 naval 架构系（DITEN），热那亚大学）；Intelligent Systems Laboratory, Department of Systems Engineering and Automation, Carlos III University of Madrid（智能系统实验室，系统工程与自动化系，马德里卡洛斯三世大学）

Kaleem Arshid, Ali Krayani, Lucio Marcenaro, David Martin Gomez, Carlo Regazzoni

备注：: Submitted to IEEE journal

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出了一种专家引导的主动推断框架，用于自适应无人机群轨迹规划。该方法将多无人机轨迹设计转化为分层概率推断问题，通过遗传算法生成专家示范并学习世界模型，实现高效的轨迹规划与动态调整。

摘要：

本文提出了一种专家引导的主动推断框架，用于自适应无人机群轨迹规划。该方法将多无人机轨迹设计转化为分层概率推断问题。在离线阶段，遗传算法结合排斥力避障（GA--RF）生成专家示范，这些示范被抽象为任务、路线和动作字典。这些字典用于学习一个概率世界模型，该模型捕捉专家任务分配如何诱导路线顺序，以及路线顺序如何诱导动作层面的行为。在在线操作中，无人机群通过形成对符号状态的后验信念，并最小化基于KL散度的异常指标，与专家推导的参考分布相关，从而实现任务分配、路线插入、动作适应和避障重计划，而无需重新运行离线优化器。在动作层面集成贝叶斯状态估计器，包括EKF和PF模块，以提高在不确定性下的轨迹修正能力。仿真结果表明，所提框架在保持专家式规划结构的同时，产生比改进的Q学习更平滑和稳定的性能。此外，使用真实飞行无人机轨迹数据的进一步验证表明，所学世界模型能够在噪声和非光滑观测下修正符号预测，支持其在自适应无人机群自主性中的应用。

英文摘要：

This paper presents an expert-guided active-inference-inspired framework for adaptive UAV swarm trajectory planning. The proposed method converts multi-UAV trajectory design from a repeated combinatorial optimization problem into a hierarchical probabilistic inference problem. In the offline phase, a genetic-algorithm planner with repulsive-force collision avoidance (GA--RF) generates expert demonstrations, which are abstracted into Mission, Route, and Motion dictionaries. These dictionaries are used to learn a probabilistic world model that captures how expert mission allocations induce route orders and how route orders induce motion-level behaviors. During online operation, the UAV swarm evaluates candidate actions by forming posterior beliefs over symbolic states and minimizing KL-divergence-based abnormality indicators with respect to expert-derived reference distributions. This enables mission allocation, route insertion, motion adaptation, and collision-aware replanning without rerunning the offline optimizer. Bayesian state estimators, including EKF and PF modules, are integrated at the motion level to improve trajectory correction under uncertainty. Simulation results show that the proposed framework preserves expert-like planning structure while producing smoother and more stable behavior than modified Q-learning. Additional validation using real-flight UAV trajectory data demonstrates that the learned world model can correct symbolic predictions under noisy and non-smooth observations, supporting its applicability to adaptive UAV swarm autonomy.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。