Vision & Robotics

Roboticist’s proposed framework to enable robots to learn on their own and adapt to new environments could revolutionize everything from home service robots to emergency response systems.

Researchers complete final step in a robotic ironing pipeline: removing wrinkles.

Song and her students won for their paper, Iterative Residual Policy for Goal-Conditioned Dynamic Manipulation of Deformable Objects.
About
The group studies the computational foundations for visual and robotic intelligence. They investigate machines that are able to perceive their surroundings and interact with them too.
The group of ten faculty often collaborate across the sciences and the arts. They leverage insights from both nature and math to advance the fundamentals of perception and interaction, and they also transfer their research to tackle practical challenges across disciplines. Several of the faculty are cross-listed with the Data Science Institute.