Multi-robot Mission Planning in Dynamic Semantic Environments

TL;DR

This paper introduces a novel sampling-based multi-robot planning method for dynamic, uncertain environments with semantic targets, enabling adaptive, collaborative missions expressed in Linear Temporal Logic.

Contribution

It presents the first approach to semantic multi-robot planning in uncertain, dynamic environments, integrating online path revision based on perceptual feedback.

Findings

Efficient planning in uncertain, dynamic environments demonstrated.

Online path revision improves mission success.

Method outperforms existing approaches in experiments.

Abstract

This paper addresses a new semantic multi-robot planning problem in uncertain and dynamic environments. Particularly, the environment is occupied with non-cooperative, mobile, uncertain labeled targets. These targets are governed by stochastic dynamics while their current and future positions as well as their semantic labels are uncertain. Our goal is to control mobile sensing robots so that they can accomplish collaborative semantic tasks defined over the uncertain current/future positions and labels of these targets. We express these tasks using Linear Temporal Logic (LTL). We propose a sampling-based approach that explores the robot motion space, the mission specification space, as well as the future configurations of the labeled targets to design optimal paths. These paths are revised online to adapt to uncertain perceptual feedback. To the best of our knowledge, this is the first work that addresses semantic mission planning problems in uncertain and dynamic semantic environments. We provide extensive experiments that demonstrate the efficiency of the proposed method