ARCADE: Scalable Demonstration Collection and Generation via Augmented Reality for Imitation Learning

TL;DR

ARCADE introduces an augmented reality framework that simplifies demonstration collection and automatically generates synthetic data, enabling scalable robot imitation learning with minimal user effort across various tasks.

Contribution

The paper presents ARCADE, a novel AR-based system that streamlines demonstration collection and synthesizes additional data, significantly enhancing the scalability of robot imitation learning.

Findings

Successfully trained policies on multiple tasks using ARCADE

Achieved 80% success rate on household pouring task

Reduced demonstration collection time and effort

Abstract

Robot Imitation Learning (IL) is a crucial technique in robot learning, where agents learn by mimicking human demonstrations. However, IL encounters scalability challenges stemming from both non-user-friendly demonstration collection methods and the extensive time required to amass a sufficient number of demonstrations for effective training. In response, we introduce the Augmented Reality for Collection and generAtion of DEmonstrations (ARCADE) framework, designed to scale up demonstration collection for robot manipulation tasks. Our framework combines two key capabilities: 1) it leverages AR to make demonstration collection as simple as users performing daily tasks using their hands, and 2) it enables the automatic generation of additional synthetic demonstrations from a single human-derived demonstration, significantly reducing user effort and time. We assess ARCADE's performance on a real Fetch robot across three robotics tasks: 3-Waypoints-Reach, Push, and Pick-And-Place. Using our framework, we were able to rapidly train a policy using vanilla Behavioral Cloning (BC), a classic IL algorithm, which excelled across these three tasks. We also deploy ARCADE on a real household task, Pouring-Water, achieving an 80% success rate.