Real-time reinforcement for human-machine interface control
Abstract
A major challenge involved in human-machine interfaces is developing feedback strategies that improve control and benefit patients with motor disabilities. Here, we propose, validate, and mechanistically characterize a personalized, closed-loop strategy that delivers reinforcement feedback in real time during human-machine interface control. Across five experiments involving 106 participants and two control interfaces, fewer than 20 reinforcement trials produced immediate improvements in force control and lasting retention gains. These effects were strongest when visual and/or somatosensory feedback was limited, a finding that suggests translational relevance for tasks, technologies, and pathologies with limited sensory feedback. In chronic stroke patients, real-time reinforcement likewise improved online force control under limited visual feedback, although short training did not yield retention gains. Information-theoretic analyses further revealed that reinforcement compensates for reduced feedback control when sensory feedback is sparse and promotes motor exploitation of successful actions. Overall, these findings identify real-time reinforcement as a promising strategy for enhancing human-machine interface control.
Related
- Volitional control of a recurrent brain computer interface via covert reinforcement of endogenous reward networks
- Integrating Brain-Computer Interface and Neuromorphic Computing for Human Digital Twins
- A novel methodology for assessing reinforcement choice in primates under human care
- Hippocampal-cingulate dynamics in the human brain link reinforcement-learning and memory
- Multi-agent meta-reinforcement learning based on contrastive predictive coding—For rapid adaptive traffic control after emergencies
BibTeX
@article{vassiliadis2026realtime,
title = {{Real-time reinforcement for human-machine interface control}},
author = {Pierre Vassiliadis and Daniel Leal Pinheiro and Lisa Fleury and Zénon Alexandre and Martín Esparza-Iaizzo and Abigaïl Ingster and Silvestro Micera and Solaiman Shokur and Friedhelm C Hummel},
journal = {Neuron},
year = {2026},
month = oct,
doi = {10.1016/j.neuron.2026.05.009},
url = {https://hal.science/hal-05785351v1},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Real-time reinforcement for human-machine interface control
AU - Pierre Vassiliadis
AU - Daniel Leal Pinheiro
AU - Lisa Fleury
AU - Zénon Alexandre
AU - Martín Esparza-Iaizzo
AU - Abigaïl Ingster
AU - Silvestro Micera
AU - Solaiman Shokur
AU - Friedhelm C Hummel
PY - 2026
DA - 2026/10/08
JO - Neuron
DO - 10.1016/j.neuron.2026.05.009
UR - https://hal.science/hal-05785351v1
AB - A major challenge involved in human-machine interfaces is developing feedback strategies that improve control and benefit patients with motor disabilities. Here, we propose, validate, and mechanistically characterize a personalized, closed-loop strategy that delivers reinforcement feedback in real time during human-machine interface control. Across five experiments involving 106 participants and two control interfaces, fewer than 20 reinforcement trials produced immediate improvements in force control and lasting retention gains. These effects were strongest when visual and/or somatosensory feedback was limited, a finding that suggests translational relevance for tasks, technologies, and pathologies with limited sensory feedback. In chronic stroke patients, real-time reinforcement likewise improved online force control under limited visual feedback, although short training did not yield retention gains. Information-theoretic analyses further revealed that reinforcement compensates for reduced feedback control when sensory feedback is sparse and promotes motor exploitation of successful actions. Overall, these findings identify real-time reinforcement as a promising strategy for enhancing human-machine interface control.
SN - 0896-6273
ER -