Control of Human-Machine Collaborative
Systems
Professor Allison
Okamura
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.
3:30 Ð 4:30 p.m.