TY - JOUR
T1 - Active robot-assisted feeding with a general-purpose mobile manipulator
T2 - Design, evaluation, and lessons learned
AU - Park, Daehyung
AU - Hoshi, Yuuna
AU - Mahajan, Harshal P.
AU - Kim, Ho Keun
AU - Erickson, Zackory
AU - Rogers, Wendy A.
AU - Kemp, Charles C.
N1 - Funding Information:
We thank Mark Killpack who provided the control library. This work was supported by NSF Award IIS-1150157 , NIDILRR grant 90RE5016-01-00 via RERC TechSAge, and a Google Faculty Research Award. Appendix A
Funding Information:
The following is the Supplementary material related to this article. Video S1 This video introduces a meal-assistance system using a general-purpose mobile manipulator, PR2. Our active-feeding system provides visually guided behaviors for autonomous food acquisition and delivery. The interview and evaluation processes with participants with motor impairments show the necessities and capabilities of our system. Daehyung Park is a Postdoctoral Associate in Computer Science and Artificial Intelligence Laboratory at Massachusetts Institute of Technology. He received a doctorate in the School of Interactive Computing at the Georgia Institute of Technology, USA (2018), where he worked on assistive manipulation and machine learning. He earned an M.S. from University of Southern California, USA, and B.E. from Osaka University, Japan. He also worked as a Robot Engineer with the Mechatronics Center, Samsung Electronics Inc. Suwon, Korea His research interests include manipulation, machine learning, and assistive devices. Yuuna Hoshi is an undergraduate student in the College of Computing at the Georgia Institute of Technology. She is majoring in Computer Science with concentrations in Systems/Architecture and Intelligence. She is planning to graduate in December, 2019. Her interests include machine learning, computer vision, and human computer interaction. Harshal P. Mahajan is a research scientist at Georgia Institute of Technology. He received his Ph.D. in Rehabilitation Science from the University of Pittsburgh, PA where he worked on human centered design of smart assistive technologies for people with physical disabilities and cognitive impairments. His research interests also include understanding person specific and environment specific barriers and facilitators that influence health and function in people with disabilities and validating smart rehabilitation intervention strategies. Ho Keun Kim is a software engineer working in Rubrik Inc. He received a Bachelor’s degree in Computer Science and Mathematics at Georgia Institute of Technology. His interests include artificial intelligence, data analysis, and machine learning. Zackory Erickson is a Ph.D. student at Georgia Institute of Technology, where he works in the Healthcare Robotics Lab and is advised by Professor Charlie Kemp. His research focuses on enable robots to more intelligently interact with and assist people through physics-based simulation, haptic perception, and data-driven learning. He received a B.S. at the University of Wisconsin-La Crosse with majors in both computer science and mathematics. Wendy A. Rogers is Professor of Psychology and Coordinator of the Engineering Psychology Program at the Georgia Institute of Technology. Her research interests include cognitive aging, automation, skill acquisition, human–robot interaction, and technology acceptance. She is Director of the Human Factors and Aging Laboratory ( www.hfaging.org ), funded by NIH (National Institute on Aging) through the Center for Research and Education on Aging and Technology Enhancement (CREATE www.create-center.org ). She is an active member of the Aware Home Research Initiative ( http://awarehome.imtc.gatech.edu ) and is Editor of the Journal of Experimental Psychology: Applied. Charles C. Kemp is an Associate Professor at the Georgia Institute of Technology in the Department of Biomedical Engineering. He also has adjunct appointments in the School of Interactive Computing and the School of Electrical and Computer Engineering. He earned a doctorate in Electrical Engineering and Computer Science (2005), an M.Eng., and B.S. from MIT. In 2007, he founded the Healthcare Robotics Lab at Georgia Tech ( http://healthcare-robotics.com ), which focuses on mobile manipulation and human–robot interaction. He is an active member of the Institute for Robotics and Intelligent Machines ([IRIM@GT]) and Georgia Tech’s multi-disciplinary Robotics Ph.D. program. He has received the 3M Non-tenured Faculty Award, the Georgia Tech Research Corporation Robotics Award, and the NSF CAREER award.
Publisher Copyright:
© 2019 Elsevier B.V.
PY - 2020/2
Y1 - 2020/2
N2 - Eating is an essential activity of daily living (ADL) for staying healthy and living at home independently. Although numerous assistive devices have been introduced, many people with disabilities are still restricted from independent eating due to the devices’ physical or perceptual limitations. In this work, we present a new meal-assistance system and evaluations of this system with people with motor impairments. We also discuss learned lessons and design insights based on the evaluations. The meal-assistance system uses a general-purpose mobile manipulator, a Willow Garage PR2, which has the potential to serve as a versatile form of assistive technology. Our active feeding framework enables the robot to autonomously deliver food to the user's mouth, reducing the need for head movement by the user. The user interface, visually-guided behaviors, and safety tools allow people with severe motor impairments to successfully use the system. We evaluated our system with a total of 10 able-bodied participants and 9 participants with motor impairments. Both groups of participants successfully ate various foods using the system and reported high rates of success for the system's autonomous behaviors. In general, participants who operated the system reported that it was comfortable, safe, and easy-to-use.
AB - Eating is an essential activity of daily living (ADL) for staying healthy and living at home independently. Although numerous assistive devices have been introduced, many people with disabilities are still restricted from independent eating due to the devices’ physical or perceptual limitations. In this work, we present a new meal-assistance system and evaluations of this system with people with motor impairments. We also discuss learned lessons and design insights based on the evaluations. The meal-assistance system uses a general-purpose mobile manipulator, a Willow Garage PR2, which has the potential to serve as a versatile form of assistive technology. Our active feeding framework enables the robot to autonomously deliver food to the user's mouth, reducing the need for head movement by the user. The user interface, visually-guided behaviors, and safety tools allow people with severe motor impairments to successfully use the system. We evaluated our system with a total of 10 able-bodied participants and 9 participants with motor impairments. Both groups of participants successfully ate various foods using the system and reported high rates of success for the system's autonomous behaviors. In general, participants who operated the system reported that it was comfortable, safe, and easy-to-use.
KW - Assistive feeding
KW - Assistive robots
KW - Manipulation
KW - Meal assistance
UR - http://www.scopus.com/inward/record.url?scp=85075266568&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85075266568&partnerID=8YFLogxK
U2 - 10.1016/j.robot.2019.103344
DO - 10.1016/j.robot.2019.103344
M3 - Article
AN - SCOPUS:85075266568
SN - 0921-8890
VL - 124
JO - Robotics and Autonomous Systems
JF - Robotics and Autonomous Systems
M1 - 103344
ER -