DocumentCode :
1984572
Title :
Real-time prediction learning for the simultaneous actuation of multiple prosthetic joints
Author :
Pilarski, Patrick M. ; Dick, Travis B. ; Sutton, Richard S.
Author_Institution :
Dept. of Comput. Sci., Univ. of Alberta, Edmonton, AB, Canada
fYear :
2013
fDate :
24-26 June 2013
Firstpage :
1
Lastpage :
8
Abstract :
Integrating learned predictions into a prosthetic control system promises to enhance multi-joint prosthesis use by amputees. In this article, we present a preliminary study of different cases where it may be beneficial to use a set of temporally extended predictions - learned and maintained in real time - within an engineered or learned prosthesis controller. Our study demonstrates the first successful combination of actor-critic reinforcement learning with real-time prediction learning. We evaluate this new approach to control learning during the myoelectric operation of a robot limb. Our results suggest that the integration of real-time prediction and control learning may speed control policy acquisition, allow unsupervised adaptation in myoelectric controllers, and facilitate synergies in highly actuated limbs. These experiments also show that temporally extended prediction learning enables anticipatory actuation, opening the way for coordinated motion in assistive robotic devices. Our work therefore provides initial evidence that realtime prediction learning is a practical way to support intuitive joint control in increasingly complex prosthetic systems.
Keywords :
assisted living; dexterous manipulators; electromyography; humanoid robots; medical robotics; prosthetics; unsupervised learning; velocity control; actor-critic reinforcement learning; amputees; anticipatory actuation; complex prosthetic systems; control learning approach; coordinated assistive robotic device motion; highly-actuated limbs; intuitive joint control; multijoint prosthesis enhancement; myoelectric controller operation; prosthetic control system; real-time prediction learning; robot limb; simultaneous multiple prosthetic joint actuation; speed control policy acquisition; temporally extended prediction learning; unsupervised adaptation; Actuators; Joints; Prosthetics; Real-time systems; Robot kinematics; Wrist;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Rehabilitation Robotics (ICORR), 2013 IEEE International Conference on
Conference_Location :
Seattle, WA
ISSN :
1945-7898
Print_ISBN :
978-1-4673-6022-7
Type :
conf
DOI :
10.1109/ICORR.2013.6650435
Filename :
6650435
Link To Document :
بازگشت