Sha Yi
University of California, San Diego
shayi@ucsd.edu
Bio
Sha Yi is a Postdoctoral Scholar at the University of California San Diego, co-advised by Professors Xiaolong Wang and Michael T. Tolley. She received her Ph.D. in Robotics from Carnegie Mellon University, where she was advised by Professors Katia Sycara and Zeynep Temel. Her research interests include using computational methods to design and control novel robotic systems. She is a recipient of CMU Presidential Fellowship and has industry experience with Amazon Robotics, Microsoft, and early-stage startups.
Areas of Research
- Robotics
Learning to Design Robots
Robots are starting to integrate into manufacturing, healthcare, and our daily lives. However, their development remains largely an iterative and intuition-driven process. Robot structures are typically designed, fabricated, and tested manually, followed by the tuning of control policies to achieve desired behaviors. This separation between design and control often leads to suboptimal performance and repeated manufacturing iterations. I aim to overcome these challenges with a unified, data-driven co-design framework for robots. Such a framework integrates simulation, optimization, and learning to automatically generate and evaluate robot designs, along with their corresponding control policies. By coupling material, geometry, and actuation design with control objectives, this approach enables the creation of task-specific and customizable robot manipulators. Furthermore, this computational approach can potentially uncover novel robot morphologies and control policies beyond human intuition, enabling capabilities previously thought to be infeasible.