From assisted-living to the hospital ward and operating room, robotic assistants with manipulation capabilities have the potential to significantly reduce costs while increasing consistency and quality of care. To create algorithms for robot manipulation in this broad class of domains, we must address the fundamentals of interacting with the world and collaborating with people. Significant progress has been made in manipulating rigid objects, where algorithms exist for general-purpose pick-and-place tasks regardless of the size and shape of the object. However, no such methods exist for a similarly broad and practical class of deformable object manipulation tasks, such as making a bed or retracting tissue during surgery. The problem is indeed challenging, as these objects are not straightforward to model and have infinite-dimensional configuration spaces, making it difficult to apply established motion planning approaches. Our approach seeks to bypass these difficulties by representing deformable objects using simplified geometric models at both the global and local planning levels. Though we do not predict the state of the object precisely, we nevertheless can perform tasks such as cable-routing, cloth folding, and surgical probe insertion in geometrically-complex environments. Building on this work, our new projects in this area aim to blend exploration of the model space with goal-directed manipulation of deformable objects and to generalize our methods to motion planning for inherently safe soft robot arms, where we can exploit contact to mitigate actuation uncertainty.
Speaker Biography
Dmitry Berenson received a BS in Electrical Engineering from Cornell University in 2005 and received his Ph.D. degree from the Robotics Institute at Carnegie Mellon University in 2011, where he was supported by an Intel PhD Fellowship. He completed a post-doc at UC Berkeley in 2011 and started as an Assistant Professor in Robotics Engineering and Computer Science at WPI in 2012. He founded and directs the Autonomous Robotic Collaboration (ARC) Lab at WPI, which focuses on motion planning, manipulation, and human-robot collaboration.