Heterogeneous Robot Collaboration in Unstructured Environments with Grounded Generative Intelligence

TL;DR

This paper introduces SPINE-HT, a framework enabling heterogeneous robot teams to perform complex, unstructured environment missions by grounding language-based planning in real-time capabilities and feedback, significantly improving success rates.

Contribution

The paper presents SPINE-HT, a novel three-stage framework that grounds LLM reasoning in robot capabilities and online feedback for unstructured environments, advancing multi-robot collaboration.

Findings

Nearly doubled success rate in simulation compared to prior methods.

Achieved 87% success rate in real-world heterogeneous robot missions.

Effective online subtask refinement based on real-time feedback.

Abstract

Heterogeneous robot teams operating in realistic settings often must accomplish complex missions requiring collaboration and adaptation to information acquired online. Because robot teams frequently operate in unstructured environments -- uncertain, open-world settings without prior maps -- subtasks must be grounded in robot capabilities and the physical world. While heterogeneous teams have typically been designed for fixed specifications, generative intelligence opens the possibility of teams that can accomplish a wide range of missions described in natural language. However, current large language model (LLM)-enabled teaming methods typically assume well-structured and known environments, limiting deployment in unstructured environments. We present SPINE-HT, a framework that addresses these limitations by grounding the reasoning abilities of LLMs in the context of a heterogeneous robot team through a three-stage process. Given language specifications describing mission goals and team capabilities, an LLM generates grounded subtasks which are validated for feasibility. Subtasks are then assigned to robots based on capabilities such as traversability or perception and refined given feedback collected during online operation. In simulation experiments with closed-loop perception and control, our framework achieves nearly twice the success rate compared to prior LLM-enabled heterogeneous teaming approaches. In real-world experiments with a Clearpath Jackal, a Clearpath Husky, a Boston Dynamics Spot, and a high-altitude UAV, our method achieves an 87\% success rate in missions requiring reasoning about robot capabilities and refining subtasks with online feedback. More information is provided at https://zacravichandran.github.io/SPINE-HT.