Saved in:
Bibliographic Details
Main Authors: Chen, Sirui, Wang, Chen, Nguyen, Kaden, Fei-Fei, Li, Liu, C. Karen
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.08464
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913541801377792
author Chen, Sirui
Wang, Chen
Nguyen, Kaden
Fei-Fei, Li
Liu, C. Karen
author_facet Chen, Sirui
Wang, Chen
Nguyen, Kaden
Fei-Fei, Li
Liu, C. Karen
contents Recent progress in imitation learning from human demonstrations has shown promising results in teaching robots manipulation skills. To further scale up training datasets, recent works start to use portable data collection devices without the need for physical robot hardware. However, due to the absence of on-robot feedback during data collection, the data quality depends heavily on user expertise, and many devices are limited to specific robot embodiments. We propose ARCap, a portable data collection system that provides visual feedback through augmented reality (AR) and haptic warnings to guide users in collecting high-quality demonstrations. Through extensive user studies, we show that ARCap enables novice users to collect robot-executable data that matches robot kinematics and avoids collisions with the scenes. With data collected from ARCap, robots can perform challenging tasks, such as manipulation in cluttered environments and long-horizon cross-embodiment manipulation. ARCap is fully open-source and easy to calibrate; all components are built from off-the-shelf products. More details and results can be found on our website: https://stanford-tml.github.io/ARCap
format Preprint
id arxiv_https___arxiv_org_abs_2410_08464
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ARCap: Collecting High-quality Human Demonstrations for Robot Learning with Augmented Reality Feedback
Chen, Sirui
Wang, Chen
Nguyen, Kaden
Fei-Fei, Li
Liu, C. Karen
Robotics
Artificial Intelligence
Recent progress in imitation learning from human demonstrations has shown promising results in teaching robots manipulation skills. To further scale up training datasets, recent works start to use portable data collection devices without the need for physical robot hardware. However, due to the absence of on-robot feedback during data collection, the data quality depends heavily on user expertise, and many devices are limited to specific robot embodiments. We propose ARCap, a portable data collection system that provides visual feedback through augmented reality (AR) and haptic warnings to guide users in collecting high-quality demonstrations. Through extensive user studies, we show that ARCap enables novice users to collect robot-executable data that matches robot kinematics and avoids collisions with the scenes. With data collected from ARCap, robots can perform challenging tasks, such as manipulation in cluttered environments and long-horizon cross-embodiment manipulation. ARCap is fully open-source and easy to calibrate; all components are built from off-the-shelf products. More details and results can be found on our website: https://stanford-tml.github.io/ARCap
title ARCap: Collecting High-quality Human Demonstrations for Robot Learning with Augmented Reality Feedback
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2410.08464