Selective Exploration and Information Gathering in Search and Rescue Using Hierarchical Learning Guided by Natural Language Input

TL;DR

This paper presents a hierarchical reinforcement learning system guided by natural language input, enabling robots to efficiently explore disaster areas in search and rescue missions by integrating human-provided information.

Contribution

It introduces a novel framework combining large language models with hierarchical RL to incorporate human input and improve search efficiency in complex environments.

Findings

Enhanced learning efficiency in SAR tasks

Improved decision-making with human guidance

Effective integration of LLMs with RL

Abstract

In recent years, robots and autonomous systems have become increasingly integral to our daily lives, offering solutions to complex problems across various domains. Their application in search and rescue (SAR) operations, however, presents unique challenges. Comprehensively exploring the disaster-stricken area is often infeasible due to the vastness of the terrain, transformed environment, and the time constraints involved. Traditional robotic systems typically operate on predefined search patterns and lack the ability to incorporate and exploit ground truths provided by human stakeholders, which can be the key to speeding up the learning process and enhancing triage. Addressing this gap, we introduce a system that integrates social interaction via large language models (LLMs) with a hierarchical reinforcement learning (HRL) framework. The proposed system is designed to translate verbal inputs from human stakeholders into actionable RL insights and adjust its search strategy. By leveraging human-provided information through LLMs and structuring task execution through HRL, our approach not only bridges the gap between autonomous capabilities and human intelligence but also significantly improves the agent's learning efficiency and decision-making process in environments characterised by long horizons and sparse rewards.