Leveraging Large Language Model for Heterogeneous Ad Hoc Teamwork Collaboration

TL;DR

This paper introduces a novel LLM-based framework for heterogeneous ad hoc teamwork, enabling robots with different capabilities to collaborate efficiently without prior coordination, demonstrated through benchmark tests and real-world experiments.

Contribution

It proposes a training-free hierarchical dynamic planner using LLM and introduces IRoT for adaptive cooperation in heterogeneous teams, addressing a challenging ad hoc teamwork problem.

Findings

Effective collaboration in heterogeneous teams demonstrated

Framework outperforms baseline methods in benchmark tests

Successful deployment on physical robots in real-world scenarios

Abstract

Compared with the widely investigated homogeneous multi-robot collaboration, heterogeneous robots with different capabilities can provide a more efficient and flexible collaboration for more complex tasks. In this paper, we consider a more challenging heterogeneous ad hoc teamwork collaboration problem where an ad hoc robot joins an existing heterogeneous team for a shared goal. Specifically, the ad hoc robot collaborates with unknown teammates without prior coordination, and it is expected to generate an appropriate cooperation policy to improve the efficiency of the whole team. To solve this challenging problem, we leverage the remarkable potential of the large language model (LLM) to establish a decentralized heterogeneous ad hoc teamwork collaboration framework that focuses on generating reasonable policy for an ad hoc robot to collaborate with original heterogeneous teammates. A training-free hierarchical dynamic planner is developed using the LLM together with the newly proposed Interactive Reflection of Thoughts (IRoT) method for the ad hoc agent to adapt to different teams. We also build a benchmark testing dataset to evaluate the proposed framework in the heterogeneous ad hoc multi-agent tidying-up task. Extensive comparison and ablation experiments are conducted in the benchmark to demonstrate the effectiveness of the proposed framework. We have also employed the proposed framework in physical robots in a real-world scenario. The experimental videos can be found at https://youtu.be/wHYP5T2WIp0.