Abstract
Learning sequential force interaction tasks from kinesthetic demonstrations is a promising approach to transfer human manipulation abilities to a robot. In this paper we propose a novel concept to decompose such demonstrations into a set of Movement Primitives (MPs). The decomposition is based on a probability distribution we call Directional Normal Distribution (DND). To capture the sequential properties of the manipulation task, we model the demonstrations with a Hidden Markov Model (HMM). Here, we employ mixtures of DNDs as the HMM's output emissions. The combination of HMMs and mixtures of DNDs allows to infer the MP's composition, i.e., its coordinate frames, control variables and target coordinates from the demonstration data. In addition, it permits to determine an appropriate number of MPs that explains the demonstrations best. We evaluate the approach on kinesthetic demonstrations of a light bulb unscrewing task. Decomposing the task leads to intuitive and meaningful MPs that reflect the natural structure of the task.
Original language | English |
---|---|
Title of host publication | Proceedings of the 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems |
Subtitle of host publication | IROS 2016 |
Editors | Dong-Soo Kwon, Chul-Goo Kang, Il Hong Suh |
Place of Publication | Piscataway, NJ, USA |
Publisher | IEEE |
Pages | 3920-3927 |
ISBN (Electronic) | 978-1-5090-3762-9 |
DOIs | |
Publication status | Published - 2016 |
Event | 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2016 - Daejeon, Korea, Republic of Duration: 9 Oct 2016 → 14 Oct 2016 http://www.iros2016.org/ |
Conference
Conference | 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2016 |
---|---|
Abbreviated title | IROS 2016 |
Country/Territory | Korea, Republic of |
City | Daejeon |
Period | 9/10/16 → 14/10/16 |
Internet address |
Keywords
- Hidden Markov models
- Force
- Robot kinematics
- Gaussian distribution
- Force measurement
- Probabilistic logic