Self-Recovery Prompting: Promptable General Purpose Service Robot System with Foundation Models and Self-Recovery

Abstract

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 .

Mimo Shirasaka
Mimo Shirasaka
Undergraduate
Tatsuya Matsushima
Tatsuya Matsushima
Project Researcher

My research interests include robot learning, robot system, and XR.

Soshi Tsunashima
Soshi Tsunashima
Undergraduate
Yuya Ikeda
Yuya Ikeda
Master’s Student
Aoi Horo
Aoi Horo
Undergraduate
So Ikoma
So Ikoma
Undergraduate
Chikaha Tsuji
Chikaha Tsuji
Undergraduate
Hikaru Wada
Hikaru Wada
Undergraduate
Tsunekazu Omija
Tsunekazu Omija
Undergraduate
Dai Komukai
Dai Komukai
Undergraduate
Yutaka Matsuo
Yutaka Matsuo
Professor