Abstract:
We propose a model-based reinforcement learning algorithm for biped walking in which the robot learns to appropriately modulate an observed walking pattern. Via-points are detected from the observed walking trajectories using the minimum jerk criterion. The learning algorithm modulates the via-points as control actions to improve walking trajectories. This decision is based on a learned model of the Poincare map of the periodic walking pattern. The model maps from a state in the single support phase and the control actions to a state in the next single support phase. We applied this approach to both a simulated robot model and an actual biped robot. We show that successful walking policies are acquired.
copied = false, 2000);
">
@conference{Morimoto-2005-9165,
author = {Jun Morimoto And Jun Nakanishi And Gen Endo And Gordon Cheng And Chris Atkeson And Garth Zeglin},
title = {Poincare-Map-Based Reinforcement Learning for Biped Walking},
booktitle = {Proceedings of (ICRA) International Conference on Robotics and Automation},
year = {2005},
month = {April},
pages = {2381 - 2386},
}
author = {Jun Morimoto And Jun Nakanishi And Gen Endo And Gordon Cheng And Chris Atkeson And Garth Zeglin},
title = {Poincare-Map-Based Reinforcement Learning for Biped Walking},
booktitle = {Proceedings of (ICRA) International Conference on Robotics and Automation},
year = {2005},
month = {April},
pages = {2381 - 2386},
}