BIOE Seminar Series: Associate Professor Wenzhen Yuan

Making sense of the physical world with high-resolution tactile sensing

Abstract: This talk will introduce the development of a high-resolution robotic tactile sensor GelSight, and how it can help robots understand and interact with the physical world. GelSight is a vision-based tactile sensor that measures the geometry of the contact surface with a spatial resolution of around 25 micrometers, and it also measures the shear forces and torques at the contact surface. With the help of high-resolution information, a robot could easily detect the precise shape and texture of the object surfaces and therefore recognize them. But it can help robots get more information from contact, such as understanding different physical properties of the objects and assisting with manipulation tasks. The talk will cover our work on using GelSight to detect slips while grasping and perceiving object properties such as hardness and viscosity of the liquid. I will also present our work on simulating the tactile sensor and using the simulated sensor input to boost the robot’s capability to perform perception and grasping tasks in reality. These simulation tools can also help us rethink the sensor design challenge and how tactile sensors can be used for various types of robots.

Biography: Wenzhen Yuan is an associate professor at the Siebel School of Computing and Data Science at the University of Illinois Urbana-Champaign and the director of the RoboTouch Lab. She is a pioneer in high-resolution tactile sensing for robots. Her research work spans tactile sensor design and modeling, simulation, signal processing, and tactile-based robot perception and manipulation. Her research interests also include dexterous robot hand manipulation, whole-body tactile sensing, social-physical human-robot interaction, and soft robotics. She is a recipient of the IEEE RAS Early Career Award and NSF CAREER Award. Her achievements have been acknowledged through the early-career spotlight talk at Robotics: Science and Systems (RSS) and the Conference on Robot Learning (CoRL), and as the keynote speaker at the International Conference on Robotics and Automation (ICRA).