Scalable Task Planning via Large Language Models and Structured World Representations
This addresses planning challenges for robotics and AI systems in complex environments, though it appears incremental as it builds on existing LLM and planning methods.
The paper tackles the computational intractability of task planning in large-scale environments by using LLMs to prune irrelevant components from the state space, simplifying complexity and demonstrating efficacy in a household simulation and real-world validation with a 7-DoF manipulator.
Planning methods struggle with computational intractability in solving task-level problems in large-scale environments. This work explores leveraging the commonsense knowledge encoded in LLMs to empower planning techniques to deal with these complex scenarios. We achieve this by efficiently using LLMs to prune irrelevant components from the planning problem's state space, substantially simplifying its complexity. We demonstrate the efficacy of this system through extensive experiments within a household simulation environment, alongside real-world validation using a 7-DoF manipulator (video https://youtu.be/6ro2UOtOQS4).