Bookmark Saya

arXiv Open Access 2023

Learning Task Skills and Goals Simultaneously from Physical Interaction

Haonan Chen Ye-Ji Mun Zhe Huang Yilong Niu Yiqing Xie +2 lainnya
Lihat Sumber

Abstrak

In real-world human-robot systems, it is essential for a robot to comprehend human objectives and respond accordingly while performing an extended series of motor actions. Although human objective alignment has recently emerged as a promising paradigm in the realm of physical human-robot interaction, its application is typically confined to generating simple motions due to inherent theoretical limitations. In this work, our goal is to develop a general formulation to learn manipulation functional modules and long-term task goals simultaneously from physical human-robot interaction. We show the feasibility of our framework in enabling robots to align their behaviors with the long-term task objectives inferred from human interactions.

Topik & Kata Kunci

cs.RO

Penulis (7)

H

Haonan Chen

Y

Ye-Ji Mun

Z

Zhe Huang

Y

Yilong Niu

Y

Yiqing Xie

D

D. Livingston McPherson

K

Katherine Driggs-Campbell

Format Sitasi

APA MLA BibTeX
Chen, H., Mun, Y., Huang, Z., Niu, Y., Xie, Y., McPherson, D.L. et al. (2023). Learning Task Skills and Goals Simultaneously from Physical Interaction. https://arxiv.org/abs/2309.04596

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2023
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓