Seminal
The magazine and atlas of EU-funded researchA new publication from the web and AI team at Scott Charnley

Atlas / Germany

European Research Council grant · Running

AUTO-FES Clinical Evaluation of Automatic FES Calibration

Coordinator
Technische Universitaet Muenchen, Germany
Runs
1 October 2026 to 31 March 2028
Status
Running
EU funding
€150k
Total cost
—
Partners
2 organisations in 1 countries
Type
European Research Council grant
Grant agreement
101335511

What the project is doing

In the project's own words, from its summary on CORDIS.

Clinical evidence has shown that functional electrical stimulation (FES) improves hand movements in patients with motor disabilities, helping stroke or spinal cord injury patients regain limb function. Multi-array FES uses a high-density electrode array that can selectively activate specific muscle groups and enable selective hand movements. However, user-specific neuromuscular behavior and unknown electrode positions require calibration at each use.

This process is time-consuming, error-prone, and dependent on clinical expertise, making manual calibration a major bottleneck to clinical and commercial adoption. Automating calibration reduces setup time, leaving more time for therapy and enabling unsupervised use in rehabilitation and activities of daily living (ADL). We developed and validated a robust Bayesian optimisation for reliable automatic FES calibration, showing strong performance in healthy participants.

However, translation to clinical populations requires patient data because pathological muscle physiology (nonlinear neuromuscular dynamics, altered muscle tone and spasticity, and abnormal muscle synergy) introduces patient-specific behaviors that must be explicitly modelled and cannot be reliably inferred from healthy participants. To address this gap and increase TRL, this project collects and analyses clinical data from post-stroke patients and defines clinical constraints, performance requirements, and usability specifications for high-TRL system validation.

Clinical data allows identification of patient-specific neuromuscular characteristics needed for individualised modeling and the derivation of performance metrics assessing calibration efficiency, stimulation selectivity, functional task performance, and system usability and robustness. These evaluations aim to establish automatic multi-array FES calibration (Auto-FES) as a practical, robust, easy-to-operate assistive technology suitable for unsupervised use in clinical and home settings.

Topics

Who is involved

OrganisationCityCountryRole
Technische Universitaet MuenchenMuenchenGermanyCoordinator
Schon Klinik Bad Aibling Se & Co KgMunchenGermanyParticipant

Source: CORDIS, European Commission. Data of 5 Nov 2026, reused under the Commission's reuse policy. View on CORDIS