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 .

翻译：通用服务机器人（GPSR）需在多样环境中执行各类任务，这要求系统具备高度通用性与任务/环境适应性。本文首先基于多个基础模型，为全球性竞赛（RoboCup@Home 2023）开发了顶层GPSR系统。该系统通过各模型的可提示机制，既保持了对变体的泛化能力，又实现了环境适应性。通过分析系统性能，我们发现在更真实的GPSR应用场景中存在三类失效：信息不足、规划生成错误及规划执行失败。据此提出自我恢复提示流水线，通过探索必要信息并修正提示词实现故障恢复。实验证实，具备自我恢复机制的系统能解决各类失效案例并完成任务。补充视频见 https://sites.google.com/view/srgpsr。