Assisted Teleoperation for Scalable Robot Data Collection

shivin dass, Karl Pertsch, Hejia Zhang, Youngwoon Lee, Joseph J Lim, Stefanos Nikolaidis

Keywords: Teleoperation, Shared Autonomy, Scalable Data Collection

TL;DR: We propose an assisted teleoperation method that enables scalable collection of diverse robot datasets.

Abstract: Large-scale robotic datasets are essential for effective robot pre-training. However, collecting large-scale robotic data is expensive and slow as each operator can control only a single robot at a time. To make this costly data collection process efficient and scalable, we propose a novel assisted teleoperation system, which automates part of the demonstration collection process using a learned assistive policy. The assistive policy autonomously executes repetitive behaviors in data collection and asks for human input only when it is uncertain about which subtask or behavior to execute. We conduct teleoperation user studies both with a real robot and a simulated robot fleet and demonstrate that our assisted teleoperation system reduces human operators' mental load while improving data collection efficiency. Further, it enables a single operator to control multiple robots in parallel, which is a first step towards scalable robotic data collection.