Title :
Concurrent Adaptation of Human and Machine Improves Simultaneous and Proportional Myoelectric Control
Author :
Hahne, Janne M. ; Dahne, Sven ; Han-Jeong Hwang ; Muller, Klaus-Robert ; Parra, Lucas C.
Author_Institution :
Machine Learning Lab., Berlin Inst. of Technol., Berlin, Germany
Abstract :
Myoelectric control of a prosthetic hand with more than one degree of freedom (DoF) is challenging, and clinically available techniques require a sequential actuation of the DoFs. Simultaneous and proportional control of multiple DoFs is possible with regression-based approaches allowing for fluent and natural movements. Conventionally, the regressor is calibrated in an open-loop with training based on recorded data and the performance is evaluated subsequently. For individuals with amputation or congenital limb-deficiency who need to (re)learn how to generate suitable muscle contractions, this open-loop process may not be effective. We present a closed-loop real-time learning scheme in which both the user and the machine learn simultaneously to follow a common target. Experiments with ten able-bodied individuals show that this co-adaptive closed-loop learning strategy leads to significant performance improvements compared to a conventional open-loop training paradigm. Importantly, co-adaptive learning allowed two individuals with congenital deficiencies to perform simultaneous 2-D proportional control at levels comparable to the able-bodied individuals, despite having to a learn completely new and unfamiliar mapping from muscle activity to movement trajectories. To our knowledge, this is the first study which investigates man-machine co-adaptation for regression-based myoelectric control. The proposed training strategy has the potential to improve myographic prosthetic control in clinically relevant settings.
Keywords :
biomechanics; calibration; closed loop systems; electromyography; human computer interaction; learning (artificial intelligence); motion control; prosthetics; regression analysis; 2D proportional control; able-bodied individuals; amputation; calibration; closed-loop real-time learning scheme; coadaptive closed-loop learning strategy; concurrent adaptation; congenital limb-deficiency; conventional open-loop training paradigm; degree-of-freedom; machine learning; muscle activity; muscle contractions; myographic prosthetic control; natural movements; proportional myoelectric control; prosthetic hand; regression-based approaches; regression-based myoelectric control; regressor; sequential actuation; simultaneous myoelectric control; Adaptation models; Calibration; Electrodes; Electromyography; Feature extraction; Real-time systems; Training; Closed-loop-control; Electromyography; co-adaptation; myoelectric control; prosthetic hand; real-time-learning; regression; simultaneous control;
Journal_Title :
Neural Systems and Rehabilitation Engineering, IEEE Transactions on
DOI :
10.1109/TNSRE.2015.2401134