Calibration free myoelectric control matches calibrated control for cursor tasks
Is User Calibration Still Necessary for Continuous Myoelectric Control? A Closed-Loop Comparison of Calibration-Free Controllers
Human-Computer InteractionMachine Learning
Summary
Controlling devices with muscle signals usually needs a personal setup step called calibration, which can be a hassle. The authors compared muscle-control methods that need calibration with others that don’t, in a test where users moved a cursor to targets. Surprisingly, the methods that skipped calibration worked just as well in completing tasks and even gave smoother, steadier cursor movements. This means future muscle-controlled devices might not require that tricky setup, making them easier to use.
What this means in practice
- •For prosthetic device developers: Design myoelectric prostheses that operate well without needing time-consuming individual calibration for each user.$Commercial implications: This enables faster, more user-friendly fitting of prosthetic control systems for clients, improving product appeal and usability.
- •For assistive technology manufacturers: Implement muscle-controlled interfaces that do not require user calibration while maintaining effective and stable control.
Authors
Amir Reza Hariri, Kevin B. Englehart, Erik Scheme
Abstract
The need for user-specific calibration remains an often-cited barrier to widespread adoption of myoelectric control. Cross-user models trained on large multi-user datasets can now recognize gestures from unseen users without calibration, but they have been evaluated almost exclusively offline, leaving open whether calibration is still needed in closed-loop control. This study compared six calibration-free controllers, trained on 306 users of the EMG-EPN-612 dataset and used without any calibration data from the test participant, against three calibrated controllers in a closed-loop Fitts' law target-acquisition task with sixteen participants. The calibrated controllers achieved higher offline balanced accuracy (90.6% against 73.1% for the best controller of each paradigm), but completion rates did not differ significantly between paradigms, and the highest completion rate was achieved by a calibration-free controller. Calibrated controllers moved faster on successful acquisitions, partly because of their individually fitted speed mappings, though not significantly after correction for multiple comparisons. However, every calibration-free controller produced more direct and stable trajectories than every calibrated controller, even after adjusting for cursor speed. Offline accuracy did not predict completion rate across controllers or within participants, and across paradigms higher offline accuracy was associated with poorer trajectory quality in 15 of 16 participants. Without any calibration data from the end user, a model trained across a large population matched calibrated control in completion rate and exceeded it in trajectory quality. The offline accuracy gained through calibration should therefore not be taken as evidence of a closed-loop benefit.