MTU-LLM: LLM-based Multi-Robot Task Allocation and Path Planning for Heterogeneous Robots in Search and Rescue Operations

Abstract

Urban Search and Rescue operations after natural disasters involve locating and assisting victims in hazardous environments, which is challenging. Classical Multi-Robot Task Allocation (MRTA) and path planning approaches have been used to deploy heterogeneous robot teams in unsafe areas. However, existing methods often lack focus on workload balance and requirement fulfillment and struggle to generalize across different scenarios. To address these challenges, we propose Multi-robot Task allocation Utilizing LLMs (MTU-LLM), a framework designed to reduce the development time for task allocation and path planning approaches, enabling faster robot deployment. The framework uses an LLM-based “prompt engineering” approach that generates task allocation and path planning scripts for heterogeneous robot teams. This method is scalable, repeatable, and consistent across various environmental conditions, reducing lead time for MRTA algorithm development. The MTU-LLM approach is evaluated against classical MRTA and path planning methods using standard metrics. When tested on a standard environment map with varying robot teams and victim counts, the LLM-based approach demonstrates significantly higher computation time efficiency, better workload balance, and comparable requirement fulfillment percentage across numerous use cases compared to baseline methods.