Computer Science Colloquium - Sandra Liu, MIT

Computer Science Colloquium

Friday, May 05 @ 2:35pm

Wege Auditorium, TCL 123

Tactile Soft, Compliant Robotic Manipulators

When we look to the future of soft robotics and manipulation, we begin to look towards sensory-rich and compliant grasping mechanisms. Not only do we want to capitalize on the significant advantages in safety and adaptability that soft robots have, we also want to incorporate high-resolution tactile sensors, which will allow soft robots to perform more tasks. One such system is the GelSight sensor, which is low-cost, effective, and high-resolution. However, the integration of these camera-based sensors into compliant manipulators is difficult due to their rigidity. In this talk, I will present my work on the design of 3.5 different compliant tactile manipulators, along with some examples of their real-world uses. The incorporation of high-resolution tactile sensors into soft, compliant robots enables us to develop new manipulators that could eventually perform at the level of human hands.


Sandra Q. Liu is a Mechanical Engineering PhD candidate in the Perceptual Science Group at MIT CSAIL. She received her MS and BS in Mechanical Engineering from MIT and Caltech, respectively. Her current work is on the integration of the GelSight sensor into soft, compliant robots and manipulators to give them a better sense of touch.​ Recently, she and her co-authors received the Best Student Paper Award at the IEEE Conference on Soft Robotics (RoboSoft 2023) for their work on continuous, high-resolution tactile sensing integration into a human-inspired hand.