In general, my research focuses on how advanced control schemes and machine learning can be integrated in order solve problems that would be otherwise intractable using one or the other.

 

One example involves the management and optimization of multiple tasks for highly redundant robots (humanoids specifically). Often, when a robot is directed to perform multiple tasks simultaneously, as in whole-body control, one or more tasks may interfere and prevent the robot from accomplishing the ensemble. By applying various artificial intelligence and machine learning tools on top of a whole-body controller, these conflicts can be managed and in many cases eliminated.