Portia Gaitskell

Portia  Gaitskell
Advisor: Wojciech Matusik
Department: EECS
Years: 2021-2022
Research Project Title:

Robots and Learning

abstract:Natural creatures have evolved to optimize their body shape to be most suitable for survival. The innate body shape and the acquired control ability together determine skill level on different tasks. Modern reinforcement learning algorithms have been successful in finding optimal control for robots on many challenging tasks. However, less attention is paid to optimizing robot design and developing a comprehensive benchmark for it. In this project, we will propose a large-scale benchmark for co-evolving design and control of soft robots. Our benchmark environments will span across multiple tasks, including locomotion, morphing, and manipulation on varying terrains. We will implement state-of-the-art techniques for design optimization along with deep reinforcement learning for robot control.
About:

I am participating in SuperUROP because I want to explore the intersections of my two interests, robotics and machine learning, through an advanced research project. I was initially exposed to these fields through ML and optimization coursework, as well as hands-on projects in the NEET Autonomous Machines thread. I am excited to be joining this group and look forward to being challenged and to furthering my knowledge in these areas.