Learning sequential motor tasks

Daniel, C. and Neumann, G. and Kroemer, O. and Peters, J. (2013) Learning sequential motor tasks. In: IEEE International Conference on Robotics and Automation, 6 - 10 May 2013, Karlsruhe, Germany.

Documents
Daniel_ICRA_2013.pdf
[img]
[Download]
[img]
Preview
PDF
Daniel_ICRA_2013.pdf - Whole Document

1MB
Item Type:Conference or Workshop contribution (Paper)
Item Status:Live Archive

Abstract

Many real robot applications require the sequential use of multiple distinct motor primitives. This requirement implies the need to learn the individual primitives as well as a strategy to select the primitives sequentially. Such hierarchical learning problems are commonly either treated as one complex monolithic problem which is hard to learn, or as separate tasks learned in isolation. However, there exists a strong link between the robots strategy and its motor primitives. Consequently, a consistent framework is needed that can learn jointly on the level of the individual primitives and the robots strategy. We present a hierarchical learning method which improves individual motor primitives and, simultaneously, learns how to combine these motor primitives sequentially to solve complex motor tasks. We evaluate our method on the game of robot hockey, which is both difficult to learn in terms of the required motor primitives as well as its strategic elements.

Additional Information:cited By 3
Keywords:Motor Skill Learning, Sequencing, Motor Primitiives
Subjects:G Mathematical and Computer Sciences > G760 Machine Learning
H Engineering > H671 Robotics
Divisions:College of Science > School of Computer Science
Related URLs:
ID Code:25781
Deposited On:07 Apr 2017 08:04

Repository Staff Only: item control page