Proportional Myoelectric Control of Robots: Muscle Synergy Development Drives Performance Enhancement, Retainment, and Generalization

• Published in: IEEE transactions on robotics Vol. 31; no. 2; pp. 259 - 268
• Main Authors: Ison, Mark, Artemiadis, Panagiotis
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.04.2015; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Aerospace electronics; Control equipment; Control systems; Decoders; Decoding; Electromyography; Emergence; Helicopters; Human; Human-computer interaction; human-robot interaction; motor learning; Muscles; Myoelectric control; Principal component analysis; Prostheses; real-time systems; Robot control; Robotics; Robots; Tasks; User interface; Electromyography; motor learning; human–robot interaction; real-time systems; myoelectric control
• ISSN: 1552-3098; 1941-0468
• DOI: 10.1109/TRO.2015.2395731

Proportional myoelectric control has been proposed for user-friendly interaction with prostheses, orthoses, and new human-machine interfaces. Recent research has stressed intuitive controls that mimic human intentions. However, these controls have limited accuracy and functionality, resulting in user-specific decoders with upper-bound constraints on performance. Thus, myoelectric controls have yet to realize their potential as a natural interface between humans and multifunctional robotic controls. This study supports a shift in myoelectric control schemes toward proportional simultaneous controls learned through the development of unique muscle synergies. A multiple day study reveals natural emergence of a new muscle synergy space as subjects identify the system dynamics of a myoelectric interface. These synergies correlate with long-term learning, increasing performance over consecutive days. Synergies are maintained after one week, helping subjects retain efficient control and generalize performance to new tasks. The extension to robot control is also demonstrated with a robot arm performing reach-to-grasp tasks in a plane. The ability to enhance, retain, and generalize control, without needing to recalibrate or retrain the system, supports control schemes promoting synergy development, not necessarily user-specific decoders trained on a subset of existing synergies, for efficient myoelectric interfaces designed for long-term use.