ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Conference Paper Deploying Imitation Learning Using VR Hand Tracking in Robot Manipulation Tasks
Cited - time in scopus Share share facebook twitter linkedin kakaostory
Authors
Jinchul Choi, Chan-Won Park, Jun Hee Park
Issue Date
2022-12
Citation
Conference on Neural Information Processing Systems (NeurIPS) 2022 : Workshop, pp.1-6
Language
English
Type
Conference Paper
Abstract
Imitation learning is emerging as one of the promising approaches for enabling robots to acquire abilities. Since imitation learning provides methods of learning policies through imitation of an expert’s behavior, it requires sophisticated and sufficient expert behavior trajectories. However, current interfaces for imitation such as kinesthetic teaching or remote operation considerably restrict the ability to efficiently collect diverse demonstration data. To address this challenge, this work proposes an alternative interface for imitation, which can easily transfer human motions to robots while simplifying the demo collection process using a VR-based hand tracking solution. In addition, a novel method that performs data augmentation on expert trajectories is proposed to improve imitation performance. Experimental results showed that the proposed method is effective in collecting expert demonstrations and augmenting the expert trajectories and successfully completing robot manipulation tasks.
KSP Keywords
Data Augmentation, Human motion, Imitation learning, Kinesthetic teaching, Remote Operation, Robot manipulation, hand tracking, novel method, tracking solution