ROS-LLM: A ROS framework for embodied AI with task feedback and structured reasoning

TL;DR

ROS-LLM is a versatile framework enabling non-experts to program robots using natural language, integrating LLMs with ROS for intuitive task execution and structured reasoning.

Contribution

This work introduces a novel ROS-based framework that combines LLMs, behavior modes, imitation learning, and reflection for intuitive robot programming by non-experts.

Findings

Framework demonstrates robustness across diverse tasks.

Supports long-horizon and remote supervisory control scenarios.

Open-source code facilitates adoption and reproduction.

Abstract

We present a framework for intuitive robot programming by non-experts, leveraging natural language prompts and contextual information from the Robot Operating System (ROS). Our system integrates large language models (LLMs), enabling non-experts to articulate task requirements to the system through a chat interface. Key features of the framework include: integration of ROS with an AI agent connected to a plethora of open-source and commercial LLMs, automatic extraction of a behavior from the LLM output and execution of ROS actions/services, support for three behavior modes (sequence, behavior tree, state machine), imitation learning for adding new robot actions to the library of possible actions, and LLM reflection via human and environment feedback. Extensive experiments validate the framework, showcasing robustness, scalability, and versatility in diverse scenarios, including long-horizon tasks, tabletop rearrangements, and remote supervisory control. To facilitate the adoption of our framework and support the reproduction of our results, we have made our code open-source. You can access it at: https://github.com/huawei-noah/HEBO/tree/master/ROSLLM.