Dmitry Berenson is an Associate Professor in the Robotics Department at the University of Michigan, Ann Arbor. Previously, he served as an Assistant Professor at Worcester Polytechnic Institute from 2012 to 2016, following a postdoctoral position at the University of California, Berkeley in 2011-2012. His educational background includes: B.S. in electrical engineering from Cornell University (2005) Ph.D. in robotics from the Robotics Institute, Carnegie Mellon University (2011) Dr. Berenson's research focuses on advancing robotic manipulation capabilities, particularly in challenging scenarios involving deformable objects and complex environments. His work bridges the gap between theoretical motion planning algorithms and practical robotic applications, with emphasis on developing methods that can handle uncertainty, occlusion, and complex physical interactions. He has made significant contributions to contact-rich manipulation, deformable object handling, and the integration of learning with classical planning approaches. His research has important applications in manufacturing, agriculture, surgery, and everyday human environments where robots need to interact with complex objects. His recent publications demonstrate a strong trend toward integrating machine learning techniques (particularly diffusion models and other deep learning approaches) with traditional motion planning and manipulation methods. This hybrid approach allows for more robust handling of complex scenarios like deformable object manipulation, occluded environments, and long-horizon tasks that have traditionally challenged robotics systems. Among his notable achievements, Dr. Berenson has received the prestigious IEEE RAS Early Career Award and the NSF CAREER award, recognizing his significant contributions to robotics research and education. As an academic advisor, Dr. Berenson has mentored numerous students who have gone on to contribute to the field of robotics. His research has been supported by various grants that have enabled his team to pursue innovative approaches at the intersection of motion planning, manipulation, and machine learning. His work often involves interdisciplinary collaboration across computer science, mechanical engineering, and applied mathematics. Dr. Berenson leads a research group at the University of Michigan focused on robotic manipulation and motion planning. His lab develops algorithms that enable robots to perform complex manipulation tasks in unstructured environments, with particular expertise in handling deformable objects and reasoning about physical interactions. The group maintains strong connections with industry partners and other academic institutions, fostering a collaborative environment for advancing the state of the art in robotics.
