The Toyota Research Institute (TRI) announced today that Princeton University has been selected to participate in the next five-year phase of its collaborative research program. Princeton's Anirudha Majumdar, assistant professor of mechanical and aerospace engineering, will receive support for research on robotics and machine learning.
Princeton is one of thirteen universities added in a major expansion of TRI's program, joining three ongoing participants.
Professor Majumdar's proposal was selected for potential contributions to breakthroughs around difficult technological challenges in TRI’s research areas: Automated Driving, Robotics and Machine Assisted Cognition (MAC). Majumdar's project aims to develop machine learning-based techniques for endowing robots with manipulation capabilities that can be generalized to novel environments, even when these environments are significantly different from the ones used to train the robot. A good example, according to Majumdar, is teaching a robot to load and unload a dishwasher in one home and then to transfer that skill to a significantly different home. Majumdar's research interests focus on "pushing agile robotic systems to the brink of their hardware limits while providing formal guarantees on their safety and performance."