Learning task constraints in operational space formulation

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review

15 Citations (Scopus)
364 Downloads (Pure)

Abstract

Many human skills can be described in terms of performing a set of prioritised tasks. While a number of tools have become available that recover the underlying control policy from constrained movements, few have explicitly considered learning how constraints should be imposed in order to perform the control policy. In this paper, a method for learning the self-imposed constraints present in movement observations is proposed. The problem is formulated into the operational space control framework, where the goal is to estimate the constraint matrix and its null space projection that decompose the task space and any redundant degrees of freedom. The proposed method requires no prior knowledge about either the dimensionality of the constraints nor the underlying control policies. The techniques are evaluated on a simulated three degree-of-freedom arm and on the AR10 humanoid hand.

Original languageEnglish
Title of host publication2017 IEEE International Conference on Robotics and Automation (ICRA)
PublisherIEEE
Pages309-315
Number of pages7
ISBN (Electronic)9781509046331
DOIs
Publication statusE-pub ahead of print - 24 Jul 2017
Event2017 IEEE International Conference on Robotics and Automation, ICRA 2017 - Singapore, Singapore
Duration: 29 May 20173 Jun 2017

Conference

Conference2017 IEEE International Conference on Robotics and Automation, ICRA 2017
Country/TerritorySingapore
CitySingapore
Period29/05/20173/06/2017

Fingerprint

Dive into the research topics of 'Learning task constraints in operational space formulation'. Together they form a unique fingerprint.

Cite this