Motion capture and reinforcement learning of dynamically stable humanoid movement primitives
- 1 May 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10504729,p. 5284-5290
Abstract
Direct transfer of human motion trajectories to humanoid robots does not result in dynamically stable robot movements due to the differences in human and humanoid robot kinematics and dynamics. We developed a system that converts human movements captured by a low-cost RGB-D camera into dynamically stable humanoid movements. The transfer of human movements occurs in real-time. As need arises, the developed system can smoothly transition between unconstrained movement imitation and imitation with balance control, where movement reproduction occurs in the null space of the balance controller. The developed balance controller is based on an approximate model of the robot dynamics, which is sufficient to stabilize the robot during on-line imitation. However, the resulting movements cannot be guaranteed to be optimal because the model of the robot dynamics is not exact. The initially acquired movement is therefore subsequently improved by model-free reinforcement learning, both with respect to the accuracy of reproduction and balance control. We present experimental results in simulation and on a real humanoid robot.Keywords
This publication has 20 references indexed in Scilit:
- Dynamic motion capture and edition using a stack of tasks2011
- Real-time human pose recognition in parts from single depth images2011
- Reinforcement learning of full-body humanoid motor skills2010
- Compliant Control of Multicontact and Center-of-Mass Behaviors in Humanoid RobotsIEEE Transactions on Robotics, 2010
- Simultaneous tracking and balancing of humanoid robots for imitating human motion capture data2009
- Dynamics systems vs. optimal control — a unifying view2007
- Towards a unified understanding of basic notions and terms in humanoid roboticsRobotica, 2006
- Forces Acting on a Biped Robot. Center of Pressure—Zero Moment PointIEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans, 2004
- Planning of joint trajectories for humanoid robots using B-spline wavelets2002
- Euler Angle Conversion1994