PATO: Policy Assisted TeleOperation for Scalable Robot Data Collection

TL;DR

PATO introduces an assistive system that automates parts of robotic data collection, reducing human effort and enabling one operator to control multiple robots simultaneously, thus making large-scale robotic data collection more scalable and efficient.

Contribution

The paper presents PATO, a novel assistive teleoperation system that automates repetitive tasks and allows a single operator to manage multiple robots, enhancing scalability and efficiency in robotic data collection.

Findings

Reduces human mental load during data collection

Increases data collection efficiency with assistive policies

Enables control of multiple robots by one operator

Abstract

Large-scale data is an essential component of machine learning as demonstrated in recent advances in natural language processing and computer vision research. However, collecting large-scale robotic data is much more expensive and slower as each operator can control only a single robot at a time. To make this costly data collection process efficient and scalable, we propose Policy Assisted TeleOperation (PATO), a system which automates part of the demonstration collection process using a learned assistive policy. PATO 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. For code and video results, see https://clvrai.com/pato