Self-Recovery Prompting: Promptable General Purpose Service Robot System with Foundation Models and Self-Recovery
This work addresses the problem of improving reliability and adaptability in general-purpose service robots for real-world applications, representing an incremental advancement by adding a recovery mechanism to an existing framework.
The paper tackles the challenge of building a general-purpose service robot system that can handle diverse tasks and environments by developing a system based on multiple foundation models and introducing a self-recovery prompting pipeline to address failures like insufficient information, incorrect plan generation, and plan execution failure, with experimental confirmation that the system resolves various failure cases.
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 .