Location: PGSC 105

Zoom Link: https://purdue-edu.zoom.us/j/98798335169

Coffee and snacks will be provide.

Robot Touch: What to Sense and Why for Reliable Manipulation

Abstract: 

We have little insight into the role of tactile sensing in robot manipulation, despite decades of research. Studies show that grasping reliability improves with the use of tactile sensors, but recent AI-based systems are able to perform complex tasks like laundry folding and dishwasher loading without touch sensors. We address the question of which sensors are needed and why through a model that captures the dominant mechanics of the grasping process. This model applies to precision fingertip grasps that are limited by friction at the gripper-object contact; this describes roughly half of human grasps. Combining physical equilibrium with a no-slip condition reveals which parameters determine grasp stability. To deal with each of these key parameters, there are three choices: directly sense them with sensors in the contact surfaces of the gripper; indirectly sense them, for example using vision to sense contact locations; or use strategies for grasping and manipulation that minimize dependence on the parameters. Finally, this raises the question of how to gauge the value of direct contact sensors, given that such sensors are expensive and fragile, and alternative methods of indirect sensing are available. We therefore assess a framework for evaluating the costs and benefits of various forms of contact parameter estimation in designing manipulation systems for the real world. One implication is that the absence of contact sensors places additional burdens on the rest of the manipulation system for selecting and executing control strategies that work reliably.

Speaker:

Robert D. Howe is the Abbott and James Lawrence Professor of Engineering at the Harvard Paulson School of Engineering and Applied Sciences, and Founding Co-Director of the Harvard MS/MBA Degree Program. Dr. Howe started the Harvard BioRobotics Laboratory in 1990, which investigates the roles of sensing and mechanical design and motor control, in both humans and robots. His research interests focus on manipulation, the sense of touch, and human-machine interfaces. Biomedical applications of this work include of robotic and image-guided surgery. Dr. Howe earned a bachelors degree in physics from Reed College, then worked as a design engineer in the electronics industry in Silicon Valley. He received a doctoral degree in mechanical engineering from Stanford University in 1990, and then joined the faculty at Harvard. Dr. Howe is a Fellow of the IEEE and the AIMBE, and has received Best Paper Awards at mechanical engineering, robotics, and surgery conferences. Lab web site: http://biorobotics.harvard.edu/

Organizers: Ziran Wang (ziran@purdue.edu), Yan Gu (yangu@purdue.edu), Yu She (shey@purdue.edu)