Seeing, Saying, Solving: An LLM-to-TL Framework for Cooperative Robots

TL;DR

This paper introduces a decentralized framework enabling heterogeneous robots to collaboratively detect conflicts, request help via natural language, and reason over offers to optimize overall system efficiency using LLMs and formal logic grounded in MILP.

Contribution

It presents a novel decentralized approach combining vision, language, and formal logic for cooperative robot assistance, ensuring syntactic correctness and system-wide optimization.

Findings

Robots can effectively detect conflicts using VLM.

The framework enables natural language help requests and offers.

Considering multiple help offers improves overall system efficiency.

Abstract

Increased robot deployment, such as in warehousing, has revealed a need for seamless collaboration among heterogeneous robot teams to resolve unforeseen conflicts. To address this challenge, we propose a novel, decentralized framework for robots to request and provide help. The framework begins with robots detecting conflicts using a Vision Language Model (VLM), then reasoning over whether help is needed. If so, it crafts and broadcasts a natural language (NL) help request using a Large Language Model (LLM). Potential helper robots reason over the request and offer help (if able), along with information about impact to their current tasks. Helper reasoning is implemented via an LLM grounded in Signal Temporal Logic (STL) using a Backus-Naur Form (BNF) grammar to guarantee syntactically valid NL-to-STL translations, which are then solved as a Mixed Integer Linear Program (MILP). Finally, the requester robot chooses a helper by reasoning over impact on the overall system. We evaluate our system via experiments considering different strategies for choosing a helper, and find that a requester robot can minimize overall time impact on the system by considering multiple help offers versus simple heuristics (e.g., selecting the nearest robot to help).