University of Cambridge > Talks.cam > Machine Learning @ CUED > Discovery of Complex Behaviors through Contact-Invariant Optimization

Discovery of Complex Behaviors through Contact-Invariant Optimization

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Zoubin Ghahramani.

I will present a recent motion behavior synthesis framework capable of producing a wide variety of important human behaviours, including locomotion, getting up, crawling, climbing, carrying objects, acrobatics, and various cooperative actions involving two characters and their manipulation of the environment. The framework can also be applied to synthesis of dexterous hand manipulation tasks, including grasping and picking up objects, twirling them between the ļ¬ngers, tossing and catching, and drawing.

At the core of the framework is the contact-invariant optimization (CIO) method, which enables simultaneous optimization of motion trajectory and contact states. This is done by augmenting the search space with scalar auxiliary variables that indicate whether a potential contact (such as contact between foot and ground) should be active in a given phase of the motion. These auxiliary variables affect not only the cost function but also the dynamics (by enabling and disabling contact forces), and are optimized together with the motion trajectory.

This is joint work with Zoran Popovic and Emanuel Todorov.

This talk is part of the Machine Learning @ CUED series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2019 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity