News Archives

RSS Feed

Learning to Walk and Swim with Shaped Manifold Control

January 24, 2008

  • Date: Thursday, January 24th, 2008 
  • Time: 11 am — 12:15 pm 
  • Place: ME 218

Bill Smart
Department of Computer Science and Engineering
Washington University in St. Louis.

Abstract: Learning to control high-dimensional, non-linear dynamical systems is hard, in part because of the Curse of Dimensionality. The volume of the state space increases exponentially with the number of state variables used to describe the system. Learning a controller over this space often requires an exponential amount of training data, limiting us to relatively low-dimensional systems.

Many robotic systems, however, do not inhabit the entire volume of the state space. In fact, any system with a periodic gait lives on a 1-dimensional manifold embedded in the full state space of the system. In this talk, we introduce Shaped Manifold Control (SMC), which simultaneously estimates the manifold over which the system operates and learns an effective controller over this manifold. SMC sidesteps the curse of dimensionality because is learns over a 1-dimensional manifold, regardless of the dimensionality of the full state space. We have successfully applied SMC to a number of simulated high-dimensional continuous dynamical systems, including swimming and walking robots, and will demonstrate the resulting learned controllers.

Bio: Bill Smart holds a B.Sc. (Hons) in computer science from the University of Dundee (1991), an M.Sc. in Intelligent robotics from the University of Edinburgh (1992), and both an M.S. (1996) and Ph.D. (2002) in computer science from Brown University. He is currently an assistant professor of computer science and engineering at Washington University in St. Louis. He co-directs the Media and Machines Laboratory, a multi-disciplinary laboratory performing research in the areas of robotics, computer vision, machine learning, and computer graphics. His current research focuses on learning robust controllers for high-dimensional robot systems, human-robot interaction, and direct brain-computer interfaces.

Watch Colloquium: