Approximate policy transfer applied to simulated Bongo Board balance

Developing global policies for humanoid robots using dynamic programming is difficult because they have many degrees of freedom. We present a formalism whereby a value function for a humanoid robot can be approximated using the known value functions of similar systems. These similar systems can incl...

Full description

Saved in:
Bibliographic Details
Main Authors: Anderson, S.O., Hodgins, J.K., Atkeson, C.G.
Format: Conference Proceeding
Language:English
Subjects:
Animation
Computational modeling
Control systems
Dynamic programming
Function approximation
Humanoid robots
Humans
Motion control
Orbital robotics
State-space methods
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Developing global policies for humanoid robots using dynamic programming is difficult because they have many degrees of freedom. We present a formalism whereby a value function for a humanoid robot can be approximated using the known value functions of similar systems. These similar systems can include approximate models of the robot with reduced dimensionality or trajectories derived from human motion capture data. Once an approximate value function is known, a local controller is used to compute control signals. The approximate value function provides information about the global strategies that should be used to solve the task. The local controller provides complementary information about the robots dynamics. We present an implementation of this strategy and simulation results generated by this implementation.
ISSN:2164-0572
DOI:10.1109/ICHR.2007.4813915