Behaviorally Adaptive Multi-Robot Hazard Localization in Failure-Prone, Communication-Denied Environments

TL;DR

This paper introduces a behavior-adaptive planning framework for multi-robot hazard mapping in failure-prone, communication-denied environments, enhancing safety and efficiency through risk-sensitive strategies.

Contribution

It proposes a novel behavioral entropy-based planning framework with two algorithms, BAPP-TID and BAPP-SIG, for adaptive, risk-aware multi-robot exploration.

Findings

BAPP accelerates entropy reduction compared to Shannon-based methods.

BAPP-SIG enhances robot survivability with minimal information loss.

Framework scales effectively in multi-robot deployments through spatial and role-based strategies.

Abstract

We address the challenge of multi-robot autonomous hazard mapping in high-risk, failure-prone, communication-denied environments such as post-disaster zones, underground mines, caves, and planetary surfaces. In these missions, robots must explore and map hazards while minimizing the risk of failure due to environmental threats or hardware limitations. We introduce a behavior-adaptive, information-theoretic planning framework for multi-robot teams grounded in the concept of Behavioral Entropy (BE), that generalizes Shannon entropy (SE) to capture diverse human-like uncertainty evaluations. Building on this formulation, we propose the Behavior-Adaptive Path Planning (BAPP) framework, which modulates information gathering strategies via a tunable risk-sensitivity parameter, and present two planning algorithms: BAPP-TID for intelligent triggering of high-fidelity robots, and BAPP-SIG for safe deployment under high risk. We provide theoretical insights on the informativeness of the proposed BAPP framework and validate its effectiveness through both single-robot and multi-robot simulations. Our results show that the BAPP stack consistently outperforms Shannon-based and random strategies: BAPP-TID accelerates entropy reduction, while BAPP-SIG improves robot survivability with minimal loss in information gain. In multi-agent deployments, BAPP scales effectively through spatial partitioning, mobile base relocation, and role-aware heterogeneity. These findings underscore the value of behavior-adaptive planning for robust, risk-sensitive exploration in complex, failure-prone environments.