- This event has passed.
Graduate Defense: Wankun Sirichotiyakul
May 17 @ 10:00 am - 12:00 pm MDT
Title: Data-Driven Passivity-Based Control of Underactuated Robotic Systems
Program: Doctor of Philosophy in Electrical and Computer Engineering
Advisor: Dr. Aykut Satici, Mechanical and Biomedical Engineering
Committee Members: Dr. Hao Chen, Electrical and Computer Engineering, and Dr. John Chiasson, Electrical and Computer Engineering
Classical control strategies for robotic systems are based on the idea that feedback control can be used to override the natural dynamics of the machines. Passivity-based control (PBC) is a branch of nonlinear control theory that follows such an approach. This method involves transforming a nonlinear control system, through a suitable control input, into another fictitious system that better facilitates the control design process. The majority of PBC techniques require some knowledge about a reasonable “storage function”, which represents the total energy in mechanical systems.
There are several challenges in the design of a suitable storage function, including: 1) what a reasonable choice for the function is for a given control system, and 2) control synthesis from the corresponding storage function requires a closed-form solution to a set of nonlinear partial differential equations. In general, the latter is often intractable. These challenges limit the applicability of PBC techniques.
A machine learning framework that automatically determines the storage function for underactuated robotic systems is introduced in this dissertation. This framework combines the expressive power of neural networks with the systematic methods of the PBC paradigm, bridging the gap between controllers derived from learning algorithms and stability properties. A series of simulated and physical experiments demonstrates the efficacy and applicability of this framework for a family of underactuated robots.