Inner Monologue: Embodied Reasoning through Planning with Language Models
This work addresses the challenge of enhancing robotic planning and control using LLMs, though it is incremental as it builds on existing methods for feedback integration.
The authors tackled the problem of enabling large language models (LLMs) to plan and interact in embodied robotic environments by incorporating natural language feedback, such as success detection and scene descriptions, without additional training. They found that this closed-loop feedback significantly improved high-level instruction completion in simulated and real-world tasks, including tabletop rearrangement and kitchen manipulation.
Recent works have shown how the reasoning capabilities of Large Language Models (LLMs) can be applied to domains beyond natural language processing, such as planning and interaction for robots. These embodied problems require an agent to understand many semantic aspects of the world: the repertoire of skills available, how these skills influence the world, and how changes to the world map back to the language. LLMs planning in embodied environments need to consider not just what skills to do, but also how and when to do them - answers that change over time in response to the agent's own choices. In this work, we investigate to what extent LLMs used in such embodied contexts can reason over sources of feedback provided through natural language, without any additional training. We propose that by leveraging environment feedback, LLMs are able to form an inner monologue that allows them to more richly process and plan in robotic control scenarios. We investigate a variety of sources of feedback, such as success detection, scene description, and human interaction. We find that closed-loop language feedback significantly improves high-level instruction completion on three domains, including simulated and real table top rearrangement tasks and long-horizon mobile manipulation tasks in a kitchen environment in the real world.