Learning movement primitive libraries through probabilistic segmentation

Lioutikov, Rudolf and Neumann, Gerhard and Maeda, Guilherme and Peters, Jan (2017) Learning movement primitive libraries through probabilistic segmentation. International Journal of Robotics Research (IJRR), 36 (8). pp. 879-894. ISSN 0278-3649

Full content URL: https://doi.org/10.1177/0278364917713116

Documents
lioutikov_probs_ijrr2017.pdf

Request a copy
[img] PDF
lioutikov_probs_ijrr2017.pdf - Whole Document
Restricted to Registered users only

12MB
Item Type:Article
Item Status:Live Archive

Abstract

Movement primitives are a well established approach for encoding and executing movements. While the primitives
themselves have been extensively researched, the concept of movement primitive libraries has not received similar
attention. Libraries of movement primitives represent the skill set of an agent. Primitives can be queried and sequenced
in order to solve specific tasks. The goal of this work is to segment unlabeled demonstrations into a representative
set of primitives. Our proposed method differs from current approaches by taking advantage of the often neglected,
mutual dependencies between the segments contained in the demonstrations and the primitives to be encoded. By
exploiting this mutual dependency, we show that we can improve both the segmentation and the movement primitive
library. Based on probabilistic inference our novel approach segments the demonstrations while learning a probabilistic
representation of movement primitives. We demonstrate our method on two real robot applications. First, the robot
segments sequences of different letters into a library, explaining the observed trajectories. Second, the robot segments
demonstrations of a chair assembly task into a movement primitive library. The library is subsequently used to assemble the chair in an order not present in the demonstrations.

Keywords:Movement Segmentation, Movement Primitives, Skill Libraries
Subjects:H Engineering > H671 Robotics
Divisions:College of Science > School of Computer Science
Related URLs:
ID Code:28021
Deposited On:26 Jul 2017 13:49

Repository Staff Only: item control page