ゼロ知識タスクプランニングへの言語ベースアプローチ
Towards Zero-Knowledge Task Planning via a Language-based Approach
タスク固有の知識なしに目標達成の行動列を生成する「ゼロ知識タスクプランニング」を定式化し、LLMで自然言語指示をサブタスクに分解してビヘイビアツリーを生成・実行中に修正する手法を提案した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Liam Merz Hoffmeister, Brian Scassellati, Daniel Rakita
分類: cs.RO
原文アブストラクト
In this work, we introduce and formalize the Zero-Knowledge Task Planning (ZKTP) problem, i.e., formulating a sequence of actions to achieve some goal without task-specific knowledge. Additionally, we present a first investigation and approach for ZKTP that leverages a large language model (LLM) to decompose natural language instructions into subtasks and generate behavior trees (BTs) for execution. If errors arise during task execution, the approach also uses an LLM to adjust the BTs on-the-fly in a refinement loop. Experimental validation in the AI2-THOR simulator demonstrate our approach's effectiveness in improving overall task performance compared to alternative approaches that leverage task-specific knowledge. Our work demonstrates the potential of LLMs to effectively address several aspects of the ZKTP problem, providing a robust framework for automated behavior generation with no task-specific setup.
