FCRF: 大規模言語モデルによる長期的ロボットタスク計画のための柔軟な構成主義的自己反省
FCRF: Flexible Constructivism Reflection for Long-Horizon Robotic Task Planning with Large Language Models
家庭内ロボットの長期的タスク計画において、タスク難易度に応じて柔軟に自己反省し、過去の成功・失敗経験を統合するMentor-Actor型フレームワークFCRFを提案し、シミュレーションと実機で性能向上を示した。
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: Yufan Song, Jiatao Zhang, Zeng Gu, Qingmiao Liang, Tuocheng Hu, Wei Song, Shiqiang Zhu
分類: cs.RO, cs.AI
原文アブストラクト
Autonomous error correction is critical for domestic robots to achieve reliable execution of complex long-horizon tasks. Prior work has explored self-reflection in Large Language Models (LLMs) for task planning error correction; however, existing methods are constrained by inflexible self-reflection mechanisms that limit their effectiveness. Motivated by these limitations and inspired by human cognitive adaptation, we propose the Flexible Constructivism Reflection Framework (FCRF), a novel Mentor-Actor architecture that enables LLMs to perform flexible self-reflection based on task difficulty, while constructively integrating historical valuable experience with failure lessons. We evaluated FCRF on diverse domestic tasks through simulation in AlfWorld and physical deployment in the real-world environment. Experimental results demonstrate that FCRF significantly improves overall performance and self-reflection flexibility in complex long-horizon robotic tasks.
