大規模言語モデルと構造化世界表現によるスケーラブルなタスクプランニング
Scalable Task Planning via Large Language Models and Structured World Representations
LLMの常識知識を活用して計画問題の状態空間から無関係な要素を刈り込み、大規模環境でのタスク計画を効率化する手法を提案し、家庭シミュレーションと7自由度マニピュレータで検証した。
著者: Rodrigo Pérez-Dattari, Zhaoting Li, Robert Babuška, Jens Kober, Cosimo Della Santina
分類: cs.RO, cs.AI
原文アブストラクト
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).
