Site Search  

Resources » Publication Details

Publication Details

Reference TypeConference Proceedings
Author(s)Kalakrishnan, M.; Pastor, P.; Righetti, L.; Schaal, S.
TitleLearning Objective Functions for Manipulation
Journal/Conference/Book TitleIEEE International Conference on Robotics and Automation
Keywordslearning, inverse reinforcement learning, manipulation, grasping, inverse kinematics, motion planning, trajectory optimization
AbstractWe present an approach to learning objective func- tions for robotic manipulation based on inverse reinforcement learning. Our path integral inverse reinforcement learning al- gorithm can deal with high-dimensional continuous state-action spaces, and only requires local optimality of demonstrated trajectories. We use L1 regularization in order to achieve feature selection, and propose an efficient algorithm to minimize the re- sulting convex objective function. We demonstrate our approach by applying it to two core problems in robotic manipulation. First, we learn a cost function for redundancy resolution in inverse kinematics. Second, we use our method to learn a cost function over trajectories, which is then used in optimization- based motion planning for grasping and manipulation tasks. Experimental results show that our method outperforms previous algorithms in high-dimensional settings.
Link to PDF/publications/K/kalakrishnan-ICRA2013.pdf

Designed by: Nerses Ohanyan & Jan Peters
Page last modified on June 20, 2013, at 07:00 PM