Optimizing Walking Controllers for Uncertain Inputs and Environments
We introduce methods for optimizing physics-based walking controllers for
robustness to uncertainty. Many unknown factors, such as external forces,
control torques, and user control inputs, cannot be known in advance
and must be treated as uncertain.
These variables are represented with probability distributions,
and a return function scores the desirability of a single motion.
Controller optimization entails maximizing the expected value of the
return, which is computed by Monte Carlo methods.
We demonstrate examples with different sources of uncertainty and
Optimizing control strategies under uncertainty increases robustness
and produces natural variations in style.
Thanks to Zoran Popović for early discussions, and
the reviewers for their suggestions.
This research is supported in part by the Natural Sciences and Engineering Research Council of Canada (NSERC), Canada Foundation for Innovation (CFI),
the Ontario Ministry of Research and Innovation, and
the Canadian Institute for Advanced Research (CIFAR).
Part of this work was done while Aaron Hertzmann was on a
sabbatical visit to Pixar Animation Studios.