TY - GEN
T1 - Learning Interactive Behaviors for Musculoskeletal Robots Using Bayesian Interaction Primitives
AU - Campbell, Joseph
AU - Hitzmann, Arne
AU - Stepputtis, Simon
AU - Ikemoto, Shuhei
AU - Hosoda, Koh
AU - Amor, Heni Ben
N1 - Funding Information:
ACKNOWLEDGMENT We would like to thank Masuda Hiroaki for his assistance. This work was supported by the National Science Foundation under Grant Nos. 1714060 and IIS-1749783, JSPS under KAKENHI Grant Number 18H01410, and the Honda Research Institute. J.C. is a JSPS International Research Fellow.
Publisher Copyright:
© 2019 IEEE.
PY - 2019/11
Y1 - 2019/11
N2 - Musculoskeletal robots that are based on pneumatic actuation have a variety of properties, such as compliance and back-drivability, that render them particularly appealing for human-robot collaboration. However, programming interactive and responsive behaviors for such systems is extremely challenging due to the nonlinearity and uncertainty inherent to their control. In this paper, we propose an approach for learning Bayesian Interaction Primitives for musculoskeletal robots given a limited set of example demonstrations. We show that this approach is capable of real-time state estimation and response generation for interaction with a robot for which no analytical model exists. Human-robot interaction experiments on a 'handshake' task show that the approach generalizes to new positions, interaction partners, and movement velocities.
AB - Musculoskeletal robots that are based on pneumatic actuation have a variety of properties, such as compliance and back-drivability, that render them particularly appealing for human-robot collaboration. However, programming interactive and responsive behaviors for such systems is extremely challenging due to the nonlinearity and uncertainty inherent to their control. In this paper, we propose an approach for learning Bayesian Interaction Primitives for musculoskeletal robots given a limited set of example demonstrations. We show that this approach is capable of real-time state estimation and response generation for interaction with a robot for which no analytical model exists. Human-robot interaction experiments on a 'handshake' task show that the approach generalizes to new positions, interaction partners, and movement velocities.
UR - http://www.scopus.com/inward/record.url?scp=85081156025&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85081156025&partnerID=8YFLogxK
U2 - 10.1109/IROS40897.2019.8967845
DO - 10.1109/IROS40897.2019.8967845
M3 - Conference contribution
AN - SCOPUS:85081156025
T3 - IEEE International Conference on Intelligent Robots and Systems
SP - 5071
EP - 5078
BT - 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2019
Y2 - 3 November 2019 through 8 November 2019
ER -