Taming VR Teleoperation and Learning from Demonstration for Multi-Task Bimanual Table Service Manipulation

TL;DR

This paper presents a robust VR teleoperation and learning from demonstration approach for multi-task bimanual table service manipulation, achieving top performance in a competitive robotics challenge.

Contribution

It introduces a hybrid system combining high-fidelity teleoperation with learned policies for complex manipulation tasks, advancing autonomous capabilities in service robots.

Findings

Achieved first place in ICRA 2025 WBCD competition.

Demonstrated high efficiency and reliability in multi-task manipulation.

Trained a policy from 100 demonstrations for pizza placement.

Abstract

This technical report presents the champion solution of the Table Service Track in the ICRA 2025 What Bimanuals Can Do (WBCD) competition. We tackled a series of demanding tasks under strict requirements for speed, precision, and reliability: unfolding a tablecloth (deformable-object manipulation), placing a pizza into the container (pick-and-place), and opening and closing a food container with the lid. Our solution combines VR-based teleoperation and Learning from Demonstrations (LfD) to balance robustness and autonomy. Most subtasks were executed through high-fidelity remote teleoperation, while the pizza placement was handled by an ACT-based policy trained from 100 in-person teleoperated demonstrations with randomized initial configurations. By carefully integrating scoring rules, task characteristics, and current technical capabilities, our approach achieved both high efficiency and reliability, ultimately securing the first place in the competition.