JIVKO SINAPOV, TUFTS UNIVERSITY - Talk Abstract

Abstract: 

Robots are transforming the way we live and are increasingly deployed in applications such as assistive care, environmental monitoring, agriculture and collaborative manufacturing. Enabling such robots to adapt in real time when facing novel situations, and problems, however, remains a challenge. In this talk I will provide a brief overview of the research conducted in the MuLIP lab and highlight some key results in the areas of multisensory perception and robot learning that address key challenges in robot deployment. Specifically, I will discuss findings related to transfer learning for both perception and control, as well as highlight novel mechanisms that enable robots to adapt to novel situations that may be unforeseen by the designers and engineers prior to deployment. I will end with open questions and problems, along with our ongoing efforts to address them.