Constraint-aware learning of policies by demonstration. (December 2018)

• Record Type: Journal Article
• Authors: Armesto, Leopoldo; Moura, João; Ivan, Vladimir; Erden, Mustafa Suphi; Sala, Antonio; Vijayakumar, Sethu
• Is Part Of: International journal of robotics research. Volume 37:Number 13/14(2018)
• Page Start: 1673
• Page End: 1689
• Publication Date: 2018-12
• Subjects: Direct policy learning -- constrained motion -- null-space policy -- force/torque application; Robots -- Periodicals; Robots, Industrial -- Periodicals; 629.89205
• DOI: 10.1177/0278364918784354
• Languages: English
• ISSNs: 0278-3649

Abstract

Many practical tasks in robotic systems, such as cleaning windows, writing, or grasping, are inherently constrained. Learning policies subject to constraints is a challenging problem. In this paper, we propose a method of constraint-aware learning that solves the policy learning problem using redundant robots that execute a policy that is acting in the null space of a constraint. In particular, we are interested in generalizing learned null-space policies across constraints that were not known during the training. We split the combined problem of learning constraints and policies into two: first estimating the constraint, and then estimating a null-space policy using the remaining degrees of freedom. For a linear parametrization, we provide a closed-form solution of the problem. We also define a metric for comparing the similarity of estimated constraints, which is useful to pre-process the trajectories recorded in the demonstrations. We have validated our method by learning a wiping task from human demonstration on flat surfaces and reproducing it on an unknown curved surface using a force- or torque-based controller to achieve tool alignment. We show that, despite the differences between the training and validation scenarios, we learn a policy that still provides the desired wiping motion.