Formation-Aware Adaptive Conformalized Perception for Safe Leader-Follower Multi-Robot Systems

TL;DR

This paper introduces a formation-aware adaptive conformal prediction approach for multi-robot perception safety, improving visibility and tracking in leader-follower formations with probabilistic safety guarantees.

Contribution

It develops a novel distributed conformal prediction method that adapts uncertainty bounds based on formation risk, enhancing safety and performance in vision-based multi-robot systems.

Findings

Improved formation success rates in simulations.

Enhanced tracking accuracy over non-adaptive baselines.

Probabilistic safety guarantees maintained in varied configurations.

Abstract

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/}.