Autonomous and Adaptive Role Selection for Multi-robot Collaborative Area Search Based on Deep Reinforcement Learning

TL;DR

This paper introduces a hierarchical deep reinforcement learning framework for multi-robot collaborative area search, enabling adaptive role selection and switching to improve exploration and coverage efficiency.

Contribution

It presents a novel hierarchical multi-agent reinforcement learning approach with role-based task planning and switching mechanisms for multi-robot search tasks.

Findings

Demonstrates scalability to larger robot teams

Shows improved exploration and coverage performance

Generalizes well across different scene complexities

Abstract

In the tasks of multi-robot collaborative area search, we propose the unified approach for simultaneous mapping for sensing more targets (exploration) while searching and locating the targets (coverage). Specifically, we implement a hierarchical multi-agent reinforcement learning algorithm to decouple task planning from task execution. The role concept is integrated into the upper-level task planning for role selection, which enables robots to learn the role based on the state status from the upper-view. Besides, an intelligent role switching mechanism enables the role selection module to function between two timesteps, promoting both exploration and coverage interchangeably. Then the primitive policy learns how to plan based on their assigned roles and local observation for sub-task execution. The well-designed experiments show the scalability and generalization of our method compared with state-of-the-art approaches in the scenes with varying complexity and number of robots.