Control of Human-Machine Collaborative Systems

 

Professor Allison Okamura

 

The Johns Hopkins University

Department of Mechanical Engineering

 

Abstract

We are designing systems that amplify or assist human physical capabilities for performing tasks that require learned skills, judgment and dexterity. We refer to these systems as Human-machine Collaborative Systems (HMCS), as they generally seek to combine human judgment and experience with physical and sensory augmentation using advanced display and robotic devices. A general family of control techniques for creating anisotropic compliances (generating a specific type of Òvirtual fixtureÓ') has been created that can be used to enhance the speed and accuracy of fine manipulation. Hidden Markov Models were used for online segmentation of human actions, generating appropriate assistance based on segmentation results. In addition, we have undertaken human machine performance studies to measure the effectiveness of different types and levels of augmentation on manipulation performance. This work has applications in robotic assistance for medical procedures such as microsurgical retinal vein cannulation and suturing during robot-assisted minimally invasive surgery.

 

Biosketch

 

Dr. Allison Okamura is an Assistant Professor of Mechanical Engineering at The Johns Hopkins University. She received her B.S. degree from UC Berkeley in 1994 and M.S. and Ph.D. degrees from Stanford University in 1996 and 2000, all in Mechanical Engineering. She has worked in the development of haptic technology at Immersion Corporation, and is now a faculty member of the NSF Engineering Research Center for Computer Integrated Surgical Systems and Technology. Her current research interests include the design and control of robotic fingers for haptic exploration, reality-based modeling of explored objects, tissue and task modeling for surgical procedure assistance and simulation, human-machine interaction, and haptics in education.

 

Friday, February 6, 2004

3:30 Ð 4:30 p.m.

1500 EECS