DoReMi: Grounding Language Model by Detecting and Recovering from Plan-Execution Misalignment
This work addresses the challenge of improving reliability and efficiency in robotic task execution by enabling real-time correction of plan-execution deviations, representing an incremental advancement in language model grounding for robotics.
The paper tackles the problem of grounding language models in robotic tasks by detecting and recovering from misalignments between high-level textual plans and low-level execution due to environmental perturbations or imperfect controllers, resulting in higher task success rates and shorter completion times in experiments with robot arms and humanoid robots.
Large language models (LLMs) encode a vast amount of semantic knowledge and possess remarkable understanding and reasoning capabilities. Previous work has explored how to ground LLMs in robotic tasks to generate feasible and executable textual plans. However, low-level execution in the physical world may deviate from the high-level textual plan due to environmental perturbations or imperfect controller design. In this paper, we propose \textbf{DoReMi}, a novel language model grounding framework that enables immediate Detection and Recovery from Misalignments between plan and execution. Specifically, we leverage LLMs to play a dual role, aiding not only in high-level planning but also generating constraints that can indicate misalignment during execution. Then vision language models (VLMs) are utilized to detect constraint violations continuously. Our pipeline can monitor the low-level execution and enable timely recovery if certain plan-execution misalignment occurs. Experiments on various complex tasks including robot arms and humanoid robots demonstrate that our method can lead to higher task success rates and shorter task completion times. Videos of DoReMi are available at \url{https://sites.google.com/view/doremi-paper}.