Suffolk Reporter

A team of researchers from Stony Brook University and the Massachusetts Institute of Technology (MIT) has made progress in developing home robots that learn on the job. Their work focuses on creating robots that become more intelligent and adaptable as they assist people over time.

The research, detailed in a paper titled "Embodied Lifelong Learning for Task and Motion Planning," was presented at the seventh Conference of Robotic Learning (CoRL). The study is led by Assistant Professor Jorge Mendez-Mendez from the Department of Electrical and Computer Engineering.

The project aims to design a system enabling robots to acquire both general skills, such as grabbing any object, and specialized skills, like handling fragile items. This approach allows robots to decide which skill to use in real-time situations.

"Part of our solution was to make sure the robot was learning new tasks more effectively," said Mendez-Mendez. "This is why instead of focusing solely on the final performance of a robot right after it was trained, we looked at how its capabilities were improving over time."

Further details can be found in Ankita Nagpal's article on the AI Innovation Institute website.