Next Article in Journal
Rock Material Recycling in Tunnel Engineering
Previous Article in Journal
Optical and Galvanomagnetic Properties of Bi1-xSbx Thin Films in the Terahertz Frequency Range
Open AccessArticle

Learning, Improving, and Generalizing Motor Skills for the Peg-in-Hole Tasks Based on Imitation Learning and Self-Learning

1
Department of Electronics and Computer Engineering, Hanyang University, Seoul 04763, Korea
2
Department of Innovative Smart Manufacturing R&D, Korea Institute of Industrial Technology, Cheonan-si 31056, Korea
*
Authors to whom correspondence should be addressed.
Appl. Sci. 2020, 10(8), 2719; https://doi.org/10.3390/app10082719
Received: 27 February 2020 / Revised: 7 April 2020 / Accepted: 7 April 2020 / Published: 15 April 2020
(This article belongs to the Section Electrical, Electronics and Communications Engineering)
We propose a framework based on imitation learning and self-learning to enable robots to learn, improve, and generalize motor skills. The peg-in-hole task is important in manufacturing assembly work. Two motor skills for the peg-in-hole task are targeted: “hole search” and “peg insertion”. The robots learn initial motor skills from human demonstrations and then improve and/or generalize them through reinforcement learning (RL). An initial motor skill is represented as a concatenation of the parameters of a hidden Markov model (HMM) and a dynamic movement primitive (DMP) to classify input signals and generate motion trajectories. Reactions are classified as familiar or unfamiliar (i.e., modeled or not modeled), and initial motor skills are improved to solve familiar reactions and generalized to solve unfamiliar reactions. The proposed framework includes processes, algorithms, and reward functions that can be used for various motor skill types. To evaluate our framework, the motor skills were performed using an actual robotic arm and two reward functions for RL. To verify the learning and improving/generalizing processes, we successfully applied our framework to different shapes of pegs and holes. Moreover, the execution time steps and path optimization of RL were evaluated experimentally.
View Full-Text
Keywords: peg-in-hole task; reinforcement learning; hidden Markov model; dynamic movement primitive; robot; motor skill peg-in-hole task; reinforcement learning; hidden Markov model; dynamic movement primitive; robot; motor skill
Show Figures

Figure 1

MDPI and ACS Style

Cho, N.J.; Lee, S.H.; Kim, J.B.; Suh, I.H. Learning, Improving, and Generalizing Motor Skills for the Peg-in-Hole Tasks Based on Imitation Learning and Self-Learning. Appl. Sci. 2020, 10, 2719.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop