Ask, Reason, Assist: Decentralized Robot Collaboration via Language and Logic

2025-09-27

AI Summary

In dynamic warehouse environments, heterogeneous robot teams suffer from inefficient collaboration due to task conflicts. Method: This paper proposes a decentralized coordination framework that integrates large language models (LLMs) with signal temporal logic (STL) to automatically parse and reason over natural-language requests into formal, executable constraints. It introduces a BNF-grammar–compliant natural-language interface and tightly couples STL semantics with mixed-integer linear programming (MILP) for distributed decision optimization. Contribution/Results: Experiments demonstrate that the approach significantly reduces total task completion time, outperforms conventional heuristic strategies, and approaches the performance of a centralized Oracle upper bound. The framework ensures syntactic correctness, logical verifiability, and real-time collaborative efficiency—establishing a comprehensive advantage in practical multi-robot coordination under dynamic constraints.

Technology Category

• Intelligent Robots: Multi-Robot Systems
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Multiagent Systems: Coordination and Collaboration

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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 that enables robots to request and provide help. The process begins when a robot detects a conflict and uses a Large Language Model (LLM) to decide whether external assistance is required. If so, it crafts and broadcasts a natural language (NL) help request. Potential helper robots reason over the request and respond with offers of assistance, including information about the effect on their ongoing tasks. Helper reasoning is implemented via an LLM grounded in Signal Temporal Logic (STL) using a Backus-Naur Form (BNF) grammar, ensuring syntactically valid NL-to-STL translations, which are then solved as a Mixed Integer Linear Program (MILP). Finally, the requester robot selects a helper by reasoning over the expected increase in system-level total task completion time. We evaluated our framework through experiments comparing different helper-selection strategies and found that considering multiple offers allows the requester to minimize added makespan. Our approach significantly outperforms heuristics such as selecting the nearest available candidate helper robot, and achieves performance comparable to a centralized "Oracle" baseline but without heavy information demands.

Problem

• Enabling decentralized collaboration among heterogeneous robot teams
• Resolving unforeseen conflicts through language-based help requests
• Optimizing helper selection to minimize system task completion time

Innovation

• Decentralized framework for robot help requests
• LLM and STL logic for helper reasoning
• MILP optimization for task completion time