Towards a Real-Time, Interactive, Incremental Learning Algorithm for Prosthetic Myocontrol

Canepa M, Marucchi L, Boccardo N, Marinelli A, Di Domenico D, Gandolla M, Laffranchi M, Castellini C (2025)

Publication Language: English

Publication Type: Conference contribution

Publication year: 2025

Journal

IEEE ... International Conference on Rehabilitation Robotics : [proceedings] Institute of Electrical and Electronics Engineers Inc.

Publisher: IEEE Computer Society

Pages Range: 95-100

Conference Proceedings Title: 2025 International Conference On Rehabilitation Robotics (ICORR)

Event location: Chicago, IL US

ISBN: 979-8-3503-8069-9

DOI: 10.1109/ICORR66766.2025.11063044

Abstract

Myocontrol based upon machine learning usually requires a large initial labeled dataset to build its model and prescribes that said model will never change in the course of time. This approach has several limitations, e.g., the difficulty of building such a proper dataset and the low generalization power of the obtained model against the variety of situations encountered by the user in daily life. In this work we introduce an interactive, incremental learning method for intention detection in real-time, along with some optimization techniques. The method enables users to quickly update the myocontrol system on demand, reducing the impact of the non-stationarity of input signals, improving the generalization power and providing an interactive experience to the user.

Authors with CRIS profile

Claudio Castellini Assistive Intelligent Robotics Lab

Involved external institutions

Italian Institute of Technology / Istituto Italiano di Tecnologia (IIT) IT Italy (IT) Politecnico di Milano IT Italy (IT)

How to cite

APA:

Canepa, M., Marucchi, L., Boccardo, N., Marinelli, A., Di Domenico, D., Gandolla, M.,... Castellini, C. (2025). Towards a Real-Time, Interactive, Incremental Learning Algorithm for Prosthetic Myocontrol. In 2025 International Conference On Rehabilitation Robotics (ICORR) (pp. 95-100). Chicago, IL, US: IEEE Computer Society.

MLA:

Canepa, Michele, et al. "Towards a Real-Time, Interactive, Incremental Learning Algorithm for Prosthetic Myocontrol." Proceedings of the 2025 International Conference on Rehabilitation Robotics, ICORR 2025, Chicago, IL IEEE Computer Society, 2025. 95-100.

BibTeX: Download