Bayesian Decentralized Decision-making for Multi-Robot Systems: Sample-efficient Estimation of Event Rates

TL;DR

This paper introduces a decentralized Bayesian method enabling robot swarms to efficiently identify safer areas with unknown hazard rates, improving safety and convergence speed in risky environments.

Contribution

It presents a novel Bayesian framework for decentralized hazard rate estimation in multi-robot systems, enhancing decision accuracy and sample efficiency.

Findings

Swarm consistently identifies safer areas in simulations.

Method reduces hazardous exposure compared to heuristics.

Improves safety and convergence speed in decision-making.

Abstract

Effective collective decision-making in swarm robotics often requires balancing exploration, communication and individual uncertainty estimation, especially in hazardous environments where direct measurements are limited or costly. We propose a decentralized Bayesian framework that enables a swarm of simple robots to identify the safer of two areas, each characterized by an unknown rate of hazardous events governed by a Poisson process. Robots employ a conjugate prior to gradually predict the times between events and derive confidence estimates to adapt their behavior. Our simulation results show that the robot swarm consistently chooses the correct area while reducing exposure to hazardous events by being sample-efficient. Compared to baseline heuristics, our proposed approach shows better performance in terms of safety and speed of convergence. The proposed scenario has potential to extend the current set of benchmarks in collective decision-making and our method has applications in adaptive risk-aware sampling and exploration in hazardous, dynamic environments.