TY - JOUR
T1 - Building an adaptive interface via unsupervised tracking of latent manifolds
AU - Rizzoglio, Fabio
AU - Casadio, Maura
AU - De Santis, Dalia
AU - Mussa-Ivaldi, Ferdinando A.
N1 - Funding Information:
This work was supported by the Marie Curie Integration [Grant FP7- PEOPLE-2012-CIG-334201 ], the Ministry of Science and Technology , Israel (Joint Israel–Italy lab in Biorobotics Artificial somatosensorial for humans and humanoids), the National Science Foundation [Grant 1632259 ], the NIDILRR [Grant 90REGE0005-01 ], the NICHHD [Grant 5R01HD072080 ], NIBIB, USA (Grant No. R01 EB024058-03 ) and the European Union Horizon 2020 research and innovation program under the Marie Sklodowska-Curie, project REBoT, [G.A. No 750464 ].
Publisher Copyright:
© 2021 The Authors
PY - 2021/5
Y1 - 2021/5
N2 - In human–machine interfaces, decoder calibration is critical to enable an effective and seamless interaction with the machine. However, recalibration is often necessary as the decoder off-line predictive power does not generally imply ease-of-use, due to closed loop dynamics and user adaptation that cannot be accounted for during the calibration procedure. Here, we propose an adaptive interface that makes use of a non-linear autoencoder trained iteratively to perform online manifold identification and tracking, with the dual goal of reducing the need for interface recalibration and enhancing human–machine joint performance. Importantly, the proposed approach avoids interrupting the operation of the device and it neither relies on information about the state of the task, nor on the existence of a stable neural or movement manifold, allowing it to be applied in the earliest stages of interface operation, when the formation of new neural strategies is still on-going. In order to more directly test the performance of our algorithm, we defined the autoencoder latent space as the control space of a body–machine interface. After an initial offline parameter tuning, we evaluated the performance of the adaptive interface versus that of a static decoder in approximating the evolving low-dimensional manifold of users simultaneously learning to perform reaching movements within the latent space. Results show that the adaptive approach increased the representational efficiency of the interface decoder. Concurrently, it significantly improved users’ task-related performance, indicating that the development of a more accurate internal model is encouraged by the online co-adaptation process.
AB - In human–machine interfaces, decoder calibration is critical to enable an effective and seamless interaction with the machine. However, recalibration is often necessary as the decoder off-line predictive power does not generally imply ease-of-use, due to closed loop dynamics and user adaptation that cannot be accounted for during the calibration procedure. Here, we propose an adaptive interface that makes use of a non-linear autoencoder trained iteratively to perform online manifold identification and tracking, with the dual goal of reducing the need for interface recalibration and enhancing human–machine joint performance. Importantly, the proposed approach avoids interrupting the operation of the device and it neither relies on information about the state of the task, nor on the existence of a stable neural or movement manifold, allowing it to be applied in the earliest stages of interface operation, when the formation of new neural strategies is still on-going. In order to more directly test the performance of our algorithm, we defined the autoencoder latent space as the control space of a body–machine interface. After an initial offline parameter tuning, we evaluated the performance of the adaptive interface versus that of a static decoder in approximating the evolving low-dimensional manifold of users simultaneously learning to perform reaching movements within the latent space. Results show that the adaptive approach increased the representational efficiency of the interface decoder. Concurrently, it significantly improved users’ task-related performance, indicating that the development of a more accurate internal model is encouraged by the online co-adaptation process.
KW - Autoencoder networks
KW - Body–machine interface
KW - Decoder adaptation
KW - Human–machine interaction
KW - Motor learning
UR - http://www.scopus.com/inward/record.url?scp=85101339977&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85101339977&partnerID=8YFLogxK
U2 - 10.1016/j.neunet.2021.01.009
DO - 10.1016/j.neunet.2021.01.009
M3 - Article
C2 - 33636657
AN - SCOPUS:85101339977
VL - 137
SP - 174
EP - 187
JO - Neural Networks
JF - Neural Networks
SN - 0893-6080
ER -