Search papers, labs, and topics across Lattice.
The paper introduces a distributed, formation-aware adaptive conformal prediction method for multi-robot leader-follower systems, addressing the challenge of perception safety under heteroscedastic errors and visibility constraints. It uses Risk-Aware Mondrian Conformal Prediction to generate formation-conditioned uncertainty quantiles, tightening bounds near field-of-view limits and relaxing them in safer regions. These bounds are integrated into a Conformal Control Barrier Function Quadratic Program (CBF-QP) to enforce visibility while maintaining tracking performance and feasibility.
Multi-robot systems can now better handle perception uncertainty and visibility constraints by adapting safety bounds based on formation risk, leading to improved success rates and tracking accuracy.
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/}.
