MIT Student Wants to Improve How Robots Interact with the World

Maria Bauza, a PhD candidate at MIT, wants to teach robots how to move objects better using machine learning and computer software. Working on a goal of automatous robots, the first step seems to be perfecting the way a robot will pick up an object, the way it might push the object around, and also the way it will set it down. Bauza believes that if a robot were able to make decisions regarding the object it is interacting with, it would be better equipped to interact with the world around it.

To create these robust autonomous systems, Bauza has been exploring the notion of uncertainty when robots pick up, grasp, or push an object. “If the robot could touch the object, have a notion of tactile information, and be able to react to that information, it will have much more success,” explains Bauza.

To learn more, read the complete article from MIT News here.