ReSPIRe: Informative and Reusable Belief Tree Search for Robot Probabilistic Search and Tracking in Unknown Environments

TL;DR

ReSPIRe is a novel belief tree search method for robot target search and tracking in unknown environments, combining efficient mutual information estimation, adaptive particle management, and reusable policy trees to improve accuracy and computational efficiency.

Contribution

The paper introduces ReSPIRe, a new approach that integrates sigma point-based MI estimation, hierarchical particle structures, and reusable belief trees for improved robot search and tracking.

Findings

ReSPIRe achieves higher tracking accuracy than benchmarks.

ReSPIRe demonstrates superior computational efficiency.

ReSPIRe maintains stable performance in real-world tests.

Abstract

Target search and tracking (SAT) is a fundamental problem for various robotic applications such as search and rescue and environmental exploration. This paper proposes an informative trajectory planning approach, namely ReSPIRe, for SAT in unknown cluttered environments under considerably inaccurate prior target information and limited sensing field of view. We first develop a novel sigma point-based approximation approach to fast and accurately estimate mutual information reward under non-Gaussian belief distributions, utilizing informative sampling in state and observation spaces to mitigate the computational intractability of integral calculation. To tackle significant uncertainty associated with inadequate prior target information, we propose the hierarchical particle structure in ReSPIRe, which not only extracts critical particles for global route guidance, but also adjusts the particle number adaptively for planning efficiency. Building upon the hierarchical structure, we develop the reusable belief tree search approach to build a policy tree for online trajectory planning under uncertainty, which reuses rollout evaluation to improve planning efficiency. Extensive simulations and real-world experiments demonstrate that ReSPIRe outperforms representative benchmark methods with smaller MI approximation error, higher search efficiency, and more stable tracking performance, while maintaining outstanding computational efficiency.