自己回復プロンプティング:基盤モデルと自己回復を備えた汎用サービスロボットシステム
Self-Recovery Prompting: Promptable General Purpose Service Robot System with Foundation Models and Self-Recovery
複数の基盤モデルを組み合わせた汎用サービスロボットシステムを構築し、失敗時に情報探索とプロンプト修正で自己回復する仕組みを提案・検証した。
著者: Mimo Shirasaka, Tatsuya Matsushima, Soshi Tsunashima, Yuya Ikeda, Aoi Horo, So Ikoma, Chikaha Tsuji, Hikaru Wada, Tsunekazu Omija, Dai Komukai, Yutaka Matsuo Yusuke Iwasawa
分類: cs.RO, cs.AI, cs.CV, cs.LG, cs.SY, eess.SY
原文アブストラクト
A general-purpose service robot (GPSR), which can execute diverse tasks in various environments, requires a system with high generalizability and adaptability to tasks and environments. In this paper, we first developed a top-level GPSR system for worldwide competition (RoboCup@Home 2023) based on multiple foundation models. This system is both generalizable to variations and adaptive by prompting each model. Then, by analyzing the performance of the developed system, we found three types of failure in more realistic GPSR application settings: insufficient information, incorrect plan generation, and plan execution failure. We then propose the self-recovery prompting pipeline, which explores the necessary information and modifies its prompts to recover from failure. We experimentally confirm that the system with the self-recovery mechanism can accomplish tasks by resolving various failure cases. Supplementary videos are available at https://sites.google.com/view/srgpsr .
