RobotFleet: An Open-Source Framework for Centralized Multi-Robot Task Planning

2025-10-11

AI Summary

To address the challenges of collaborative planning and dynamic scheduling for heterogeneous robot swarms in multi-task scenarios, this paper proposes a centralized closed-loop control framework. Methodologically, we design a modular autonomous stack that integrates large language models (LLMs) for open-world task decomposition and semantic reasoning; construct a shared declarative global state model enabling bidirectional communication and real-time re-planning; and adopt containerized deployment with a distributed communication architecture to ensure scalability. Our key contribution is the first deep integration of LLM-driven semantic reasoning and declarative world modeling into heterogeneous multi-robot coordination systems, significantly lowering development complexity. Experiments demonstrate substantial improvements in task allocation efficiency, system robustness, and re-planning response latency. The implementation is open-sourced to facilitate rapid integration and extensibility.

Technology Category

• Intelligent Robots: Multi-Robot Systems
• Planning, Routing, and Scheduling: Planning with Language Models
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Coordinating heterogeneous robot fleets to achieve multiple goals is challenging in multi-robot systems. We introduce an open-source and extensible framework for centralized multi-robot task planning and scheduling that leverages LLMs to enable fleets of heterogeneous robots to accomplish multiple tasks. RobotFleet provides abstractions for planning, scheduling, and execution across robots deployed as containerized services to simplify fleet scaling and management. The framework maintains a shared declarative world state and two-way communication for task execution and replanning. By modularizing each layer of the autonomy stack and using LLMs for open-world reasoning, RobotFleet lowers the barrier to building scalable multi-robot systems. The code can be found here: https://github.com/therohangupta/robot-fleet.

Problem

• Coordinating heterogeneous robot fleets to achieve multiple complex goals
• Simplifying fleet scaling and management through containerized robot services
• Lowering barriers for building scalable multi-robot systems with LLMs

Innovation

• Uses LLMs for open-world reasoning in robots
• Provides containerized services for fleet scaling
• Maintains shared declarative world state for coordination