2018-10-23-subramani18a.md

title	abstract	keywords	layout	series	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	publisher	container-title	volume	genre	issued	pdf	extras
Inferring geometric constraints in human demonstrations	This paper presents an approach for inferring geometric constraints in human demonstrations. In our method, geometric constraint models are built to create representations of kinematic constraints such as fixed point, axial rotation, prismatic motion, planar motion and others across multiple degrees of freedom. Our method infers geometric constraints using both kinematic and force/torque information. The approach first fits all the constraint models using kinematic information and evaluates them individually using position, force and moment criteria. Our approach does not require information about the constraint type or contact geometry; it can determine both simultaneously. We present experimental evaluations using instrumented tongs that show how constraints can be robustly inferred in recordings of human demonstrations.	Learning by Demonstration, LbD, Constraints, Geometric Constraints	inproceedings	Proceedings of Machine Learning Research	subramani18a	0	Inferring geometric constraints in human demonstrations	223	236	223-236	223	false	Subramani, Guru and Zinn, Michael and Gleicher, Michael	given family Guru Subramani given family Michael Zinn given family Michael Gleicher	2018-10-23		PMLR	Proceedings of The 2nd Conference on Robot Learning	87	inproceedings	date-parts 2018 10 23	http://proceedings.mlr.press/v87/subramani18a/subramani18a.pdf	label link Supplementary video https://youtu.be/-rra2QA51Is label link Source code https://github.com/uwgraphics/CoRL2018Constraint