Feb. 17, 11:45, Wei Ji Ma. Optimality and Probabilistic Computation in Visual Categorization

Katherine Kuchenbecker

University of Pennsylvania

The value of tactile sensations in haptics and robotics

Although physical interaction with the world is at the core of human experience, few computer and machine interfaces provide the operator with high-fidelity touch feedback, limiting their usability.  Similarly, autonomous robots rarely take advantage of touch perception and thus struggle to match the manipulation capabilities of humans.  My long-term research goal is to leverage scientific knowledge about the sense of touch to engineer haptic interfaces and robotic systems that increase the range and quality of tasks humans can accomplish.  This talk will describe my group's three main research thrusts, covering the third one in the closest detail: haptic texture rendering, touch feedback for robotic surgery, and touch perception for autonomous robots.  First, we pioneered a data-driven method of simulating the feel of textured surfaces using an augmented stylus and a tablet computer.  Second, we have invented, refined, and studied a practical method for giving the surgeon realistic tactile feedback of instrument vibrations during robotic surgery.  Third, household robots will need to know how to grasp and manipulate a wide variety of objects, as well as communicate with humans about such items.  We have invented a set of methods that enable a PR2 robot equipped with commercial tactile sensors to delicately and firmly grasp real-world objects.  We then extended this work to enable the same robot to perceive the haptic properties of objects and describe them using adjectives in much the same way as humans.  Our work in all three of these areas has been principally enabled by a single insight: although less studied than kinesthetic cues, tactile sensations convey much of the richness of physical interactions. 

Katherine J. Kuchenbecker is an Associate Professor of Mechanical Engineering and Applied Mechanics at the University of Pennsylvania. She is Undergraduate Curriculum Chair in her department, has a secondary appointment in Computer and Information Science, and is a member of the Bioengineering Graduate Group.  Her research centers on the design and control of haptic interfaces for applications such as robot-assisted surgery, medical simulation, stroke rehabilitation, and personal computing.  She directs the Penn Haptics Group, which is part of the General Robotics, Automation, Sensing, and Perception (GRASP) Laboratory.  She has won several awards for her research, including an NSF CAREER Award in 2009, Popular Science Brilliant 10 in 2010, and the IEEE Robotics and Automation Society Academic Early Career Award in 2012.  Prior to becoming a professor, she completed a postdoctoral fellowship at the Johns Hopkins University, and she earned her Ph.D. in Mechanical Engineering at Stanford University in 2006.