Spring 2020 GRASP Seminar Series: Bing Song, Columbia University "Toward an Integration of Learning and Iterative Control Algorithms"

ABSTRACT

Can we make robots learn motor skills in the real world safely and efficiently? 
Based on mathematical descriptions of real-world problems, i.e., models, iterative control algorithms can provide safe and efficient solutions to those problems in simulations. Learning from data can handle unmodeled dynamics and unstructured situations. The integration of learning and iterative control algorithms will lead to intelligent robots learning motor skills in practice, toward becoming extensions of both the human body and the human brain. 

In this talk, I will discuss my work on integrating learning into control to teach robots motor skills. I will focus on two types of control algorithms, model predictive control with iterative linear-quadratic-regulator for trajectory planning and iterative learning control for trajectory tracking, and how they can be applied for snake robot locomotion. I am interested in how to learn motor skills in a way that is generalizable across individual robots, and how to use models and data under different circumstances.  
 

Presenter's biography

Bing Song is currently a postdoctoral scientist in Prof. Matei Ciocarlie’s Robotic Manipulation and Mobility Lab at Columbia University. She earned her PhD degree in control theory at Columbia University under the direction of Prof. Richard Longman and Prof. Minh Phan (Dartmouth College). Her thesis is “From Model-Based to Data-Driven Discrete Iterative Learning Control”. Her research interests include iterative learning control, optimal control, repetitive control, and reinforcement learning for robotics.

Location

University of Pennsylvania- GRASP Lab
3330 Walnut Street
Wu & Chen Auditorium Levine 101
Philadelphia, PA 19104
United States

Presenter

Bing Song