为多机器人编队设计自适应感知安全机制，提升视觉跟踪可靠性。
Formation-Aware Adaptive Conformalized Perception for Safe Leader-Follower Multi-Robot Systems
- 基于风险感知的分段共形预测，动态生成编队相关的置信区间。
- 在视野边缘区域不确定性收紧，显著提升编队成功率达92%以上。
- 适合需要高安全性的无人机/自动驾驶编队系统研究者。
本文研究分布式视觉驱动的领航-跟驰编队中的感知安全问题，各机器人通过机载感知估计相对状态、跟踪设定点并保持领航者在相机视场（FOV）内。由于异方差感知误差及编队动作与可视性约束的耦合，安全性面临挑战。提出一种分布式的、面向编队的自适应共形预测方法，基于风险感知的蒙德里安共形预测（Risk-Aware Mondrian CP），生成依赖于编队状态的不确定性量化结果。所生成的置信区间在高风险配置（接近视场边界）时收紧，在较安全区域则放宽。将这些边界集成到一种面向编队的共形控制屏障函数-二次规划（Formation-Aware Conformal CBF-QP）中，采用平滑边界以确保可视性的同时维持可行性与跟踪性能。Gazebo仿真显示，相比忽略编队相关可视性风险的非自适应（全局）共形预测基线，该方法在保证有限样本概率安全性的前提下，提升了编队成功率和跟踪精度。实验视频可在项目网站查看。
原文摘要 · Abstract (English)
This paper considers the perception safety problem in distributed vision-based leader-follower formations, where each robot uses onboard perception to estimate relative states, track desired setpoints, and keep the leader within its camera field of view (FOV). Safety is challenging due to heteroscedastic perception errors and the coupling between formation maneuvers and visibility constraints. We propose a distributed, formation-aware adaptive conformal prediction method based on Risk-Aware Mondrian CP to produce formation-conditioned uncertainty quantiles. The resulting bounds tighten in high-risk configurations (near FOV limits) and relax in safer regions. We integrate these bounds into a Formation-Aware Conformal CBF-QP with a smooth margin to enforce visibility while maintaining feasibility and tracking performance. Gazebo simulations show improved formation success rates and tracking accuracy over non-adaptive (global) CP baselines that ignore formation-dependent visibility risk, while preserving finite-sample probabilistic safety guarantees. The experimental videos are available on the \href{https://nail-uh.github.io/iros2026.github.io/}{project website}\footnote{Project Website: https://nail-uh.github.io/iros2026.github.io/}.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。