TRAIL Team Description Paper for RoboCup@Home 2023

TL;DR

The TRAIL team from The University of Tokyo developed a versatile, data-driven in-home robot system for RoboCup@Home 2023, integrating recent deep learning technologies and a global data platform to enhance robot adaptability and community research.

Contribution

They unified three recent deep learning and robot learning technologies into a real household robot system and created a global data platform for RoboCup@Home community research.

Findings

Effective data-driven approach for in-home tasks

Integration of three recent deep learning technologies

Global data platform for community research

Abstract

Our team, TRAIL, consists of AI/ML laboratory members from The University of Tokyo. We leverage our extensive research experience in state-of-the-art machine learning to build general-purpose in-home service robots. We previously participated in two competitions using Human Support Robot (HSR): RoboCup@Home Japan Open 2020 (DSPL) and World Robot Summit 2020, equivalent to RoboCup World Tournament. Throughout the competitions, we showed that a data-driven approach is effective for performing in-home tasks. Aiming for further development of building a versatile and fast-adaptable system, in RoboCup @Home 2023, we unify three technologies that have recently been evaluated as components in the fields of deep learning and robot learning into a real household robot system. In addition, to stimulate research all over the RoboCup@Home community, we build a platform that manages data collected from each site belonging to the community around the world, taking advantage of the characteristics of the community.