RobotFleet: An Open-Source Framework for Centralized Multi-Robot Task Planning
This addresses the problem of building scalable multi-robot systems for robotics researchers and developers, though it appears incremental as it builds on existing concepts with LLM integration.
The paper tackles the challenge of coordinating heterogeneous robot fleets for multiple tasks by introducing RobotFleet, an open-source framework that uses LLMs for centralized planning and scheduling, resulting in a modular system that simplifies scaling and management.
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.