Adaptive Iterative Feedback Prompting for Obstacle-Aware Path Planning via LLMs
Keywords: Path Planning, Large Language Models for Planning, Large Language Models, Iterative Prompting, Few-shot Prompting
TL;DR: The paper proposes AIFP, enabling LLMs to iteratively plan paths with environmental feedback to avoid collisions and re-plan as needed.
Abstract: Planning is essential for agents operating in complex decision-making tasks, particularly in Human-Robot Interaction (HRI) scenarios, which often require adaptability and the ability to navigate dynamic environments. Large Language Models (LLMs), known for their exceptional natural language understanding capabilities, hold promise for enhancing planning in HRI by processing contextual and linguistic cues. However, their effectiveness is limited by inherent shortcomings in spatial reasoning. Existing LLM-based planning frameworks often depend on combining with classical planning methods or struggle to adapt to dynamic environments, limiting their practical applicability. This paper examines whether the incorporation of an environmental feedback mechanism and iterative planning can enhance the planning capabilities of LLMs. Specifically, we propose the “Adaptive Iterative Feedback Prompting” (AIFP) framework for path planning. In AIFP, an LLM generates partial trajectories iteratively, which are evaluated for potential collisions using environmental feedback. Based on the evaluation, AIFP executes the trajectory or re-plans. Our preliminary results show that AIFP increases the success rate of the baseline by $33.3%$ and generates efficient, appropriately complex paths, making it a promising approach for dynamic HRI scenarios.
Submission Number: 33
Loading