料理レシピからロボットのタスクツリーへ：知識ネットワークとLLMを活用した計画の正確性とタスク効率の改善
From Cooking Recipes to Robot Task Trees -- Improving Planning Correctness and Task Efficiency by Leveraging LLMs with a Knowledge Network
LLMで料理レシピをタスクツリーに変換し、複数の出力をグラフ化して検索することで、ロボット調理計画の正確性と実行効率を高める手法を提案。
著者: Md Sadman Sakib, Yu Sun
分類: cs.RO, cs.AI
原文アブストラクト
Task planning for robotic cooking involves generating a sequence of actions for a robot to prepare a meal successfully. This paper introduces a novel task tree generation pipeline producing correct planning and efficient execution for cooking tasks. Our method first uses a large language model (LLM) to retrieve recipe instructions and then utilizes a fine-tuned GPT-3 to convert them into a task tree, capturing sequential and parallel dependencies among subtasks. The pipeline then mitigates the uncertainty and unreliable features of LLM outputs using task tree retrieval. We combine multiple LLM task tree outputs into a graph and perform a task tree retrieval to avoid questionable nodes and high-cost nodes to improve planning correctness and improve execution efficiency. Our evaluation results show its superior performance compared to previous works in task planning accuracy and efficiency.
