A novel method for learning policies from constrained motion

M. Howard, S. Klanke, M. Gienger, C. Goerick, S. Vijayakumar

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Many everyday human skills can be framed in terms of performing some task subject to constraints imposed by the environment. Constraints are usually unobservable and frequently change between contexts. In this paper, we present a novel approach for learning (unconstrained) control policies from movement data, where observations come from movements under different constraints. As a key ingredient, we introduce a small but highly effective modification to the standard risk functional, allowing us to make a meaningful comparison between the estimated policy and constrained observations. We demonstrate our approach on systems of varying complexity, including kinematic data from the ASIMO humanoid robot with 27 degrees of freedom.
Original languageEnglish
Title of host publicationRobotics and Automation, 2009. ICRA'09. IEEE International Conference on
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages7
ISBN (Electronic)978-1-4244-2789-5
ISBN (Print)978-1-4244-2788-8
Publication statusPublished - 2009

Keywords / Materials (for Non-textual outputs)

  • actuators
  • fingers
  • humanoid robots
  • humans
  • kinematics
  • motion control
  • page description languages
  • robotics and automation
  • solids
  • torso


Dive into the research topics of 'A novel method for learning policies from constrained motion'. Together they form a unique fingerprint.

Cite this