Project

Back to overview

Non-Invasive Adaptive Hand Prosthetics (NINAPRO)

English title Non-Invasive Adaptive Hand Prosthetics (NINAPRO)
Applicant Caputo Barbara
Number 132700
Funding scheme Sinergia
Research institution IDIAP Institut de Recherche
Institution of higher education Idiap Research Institute - IDIAP
Main discipline Information Technology
Start/End 01.01.2011 - 28.02.2015
Approved amount 931'838.00
Show all

Keywords (10)

prosthetics; electromyography; brain-computer interfaces; pattern recognition; learning systems; adaptive signal processing; artificial intelligence; machine learning; adaptive prosthetics; bimedical signal processing

Lay Summary (English)

Lead
Lay summary
Daily life of hand amputees can be poor compared to what it was before the amputation. The state of the art in hand prosthetics, at the time of writing, does not offer more than 2-3 degrees of freedom and a very coarse control of the force, as there is no haptic feedback. Patients interface with the prothesis via surface electromyography (sEMG), recorded using surface electrodes. Learning how to control the device through many input sEMG channels is a long and difficult process for most patients, that therefore settles for limited and very simplified movements (open/close). This contrasts with recent advances in mechatronics, thanks to which mechanical hands gifted with many degrees-of-freedom and force control are being built. There is a need for prosthetic hands able to naturally reproduce a wide amount of movements and forces, while at the same time requiring a lower effort in learning how to control hand postures. This goes beyond mechatronic dexterity: the real challenge is how to provide patients with a cheap, easy and natural way of controlling the prosthesis.The goal of this project is to develop a family of algorithms able to significantly augment the dexterity, and reduce the training time, for sEMG controlled prosthesis. By testing our findings on a very large collection of data, this project will pave the way for a new generation of prosthetic hands.
Direct link to Lay Summary Last update: 21.02.2013

Responsible applicant and co-applicants

Employees

Publications

Publication
Stable myoelectric control of a hand prosthesis using non-linear incremental learning
Gijsberts Arjan, Bohra Ronan, Sierra González Daniel, Werner Anton, Nowak Maria, Caputo Barbara, Roa Manuel, Castellini Claudio (2014), Stable myoelectric control of a hand prosthesis using non-linear incremental learning, in Frontiers in Neurorobotics , 8(8), 8.
The movement error rate for evaluation of machine learning methods for sEMG-based hand movement classification
Gijsberts Arjan, Atzori Manfredo, Castellini Claudio, Müller Henning, Caputo Barbara (2014), The movement error rate for evaluation of machine learning methods for sEMG-based hand movement classification, in IEEE Transactions on Neural Systems and Rehabilitation Engineering , 22(4), 735-744.
Dexterous Control of Prosthetic Hands
Atzori Manfredo, Caputo Barbara, Castellini Claudio, Gijsberts Arjan, International Conference on Advanced Robotics (2013), Dexterous Control of Prosthetic Hands, in International Conference on Advanced Robotics, IEEE Press, Uruguay.
Evaluating subsampling strategies for sEMG-based prediction of voluntary muscle contractions
Kõiva Risto, Hilsenbeck Bastian, Castellini Claudio (2013), Evaluating subsampling strategies for sEMG-based prediction of voluntary muscle contractions, in International Conference on Rehabilitation Robotics, IEEE Press, USA.
Evidence of muscle synergies during human grasping
Castellini Claudio, van der Smagt Patrick (2013), Evidence of muscle synergies during human grasping, in Biological Cybernetics , 107(2), 233-245.
From N to N+1: Multiclass Transfer Incremental Learning
Kuzborskij Ilja, Orabona Francesco, Caputo Barbara (2013), From N to N+1: Multiclass Transfer Incremental Learning, in IEEE Conference on Computer Vision and Pattern Recognition, IEEE Press, Columbus, USA.
Recognition of hand movements in a transradial amputated subject by sEMG
Atzori Manfredo, Baechler Michael, Muller Henning (2013), Recognition of hand movements in a transradial amputated subject by sEMG, in International Conference on Rehabilitation Robotics, IEEE Press, Uruguay.
Stability and Hypothesis Transfer Learning
Kuzborskij Ilja, Orabona Francesco (2013), Stability and Hypothesis Transfer Learning, in International Conference on Machine Learning, IEEE Press, Atlanta, USA.
Building the NINAPRO Database: A Resource for the Biorobotics Community
Atzori Manfredo, Gijsberts Arjan, Heynen Simone, Mittaz Hager Anne-Gabrielle, Deriaz Olivier, Van der Smagt Patrick, Castellini Claudio, Caputo Barbara, Muller Henning (2012), Building the NINAPRO Database: A Resource for the Biorobotics Community, in Proceedings of the IEEE International Conference on Biomedical Robotics and Biomechatronics, IEEE Press, USA.
Experiences in the Creation of an Electromyography Database to Help Hand Amputated Persons
Atzori Manfredo, Gijsberts Arjan, Heynen Simone, Mittaz Hager Anne-Gabrielle, Castellini Claudio, Caputo Barbara, Muller Henning (2012), Experiences in the Creation of an Electromyography Database to Help Hand Amputated Persons, in Proceedings of the 24th European Medical Informatics Conference - MIE2012, MIE Press, Germany.
Experimental evaluation of human grasps using a sensorized object
Roa Miguel Angel, Kõiva Risto, Castellini Claudio (2012), Experimental evaluation of human grasps using a sensorized object, in IEEE International Conference on Biomedical Robotics and Biomechatronics, IEEE Press, USA.
FFLS: An accurate linear device for measuring synergistic finger contractions
Koiva Risto, Hilsenback Barbara, Castellini Claudio (2012), FFLS: An accurate linear device for measuring synergistic finger contractions, in Proceedings of the IEEE International Conference on Biomedical Robotics and Biomechatronics, IEEE Press, USA.
On the Challenge of Classifying 52 Hand Movements from Surface Electromyography
Kuzborskij Ilja, Gijsberts Arjan, Caputo Barbara (2012), On the Challenge of Classifying 52 Hand Movements from Surface Electromyography, in Proceeding ofAnnual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE Press, USA.
Spatial Registration of Hand Muscle Electromyography Signals
Atzori Manfredo, Castellini Claudio, Muller Henning (2012), Spatial Registration of Hand Muscle Electromyography Signals, in 7th International Workshop on Biosignal Interpretation, IEEE Press, Italy.
Using surface electromyography to predict single finger forces
Castellini Claudio, Koiva Risto (2012), Using surface electromyography to predict single finger forces, in Proceedings of IEEE International Conference on Biomedical Robotics and Biomechatronics, IEEE Press, USA.
Using surface electromyography to predict single finger forces
Castellini Claudio, Koiva Risto (2012), Using surface electromyography to predict single finger forces, in IEEE International Conference on Biomedical Robotics and Biomechatronics, IEEE Press, USA.
Preliminary evidence of dynamic muscular synergies in human grasping
Castellini Claudio, van der Smagt Patrick (2011), Preliminary evidence of dynamic muscular synergies in human grasping, in International Conference on Advanced Robotics, IEEE Press, USA.
Characterization of a Benchmark Database for Myoelectric Movement Classification
Atzori Manfredo, Gijsberts Arjan, Kuzborskij Ilja, Heynen Simone, Mittaz Hager Anna-Gabrielle, Deriaz Olivier, Castellini Claudio, Müller Henning, Caputo Barbara, Characterization of a Benchmark Database for Myoelectric Movement Classification, in IEEE Transactions on Neural Systems and Rehabilitation Engineering.
Electromyography Low Pass Filtering Effects on the Classifica- tion of Hand Movements in Amputated Subjects
Atzori Manfredo, Muller Henning, Electromyography Low Pass Filtering Effects on the Classifica- tion of Hand Movements in Amputated Subjects, in SCIEI International Conference on Digital Signal Processing (ICDSP), SCIEI, Milan, Italy.
EMG-based prediction of multi-DOF activations using single-DOF training: a preliminary result
Castellini Claudio, Nowak Maria, EMG-based prediction of multi-DOF activations using single-DOF training: a preliminary result, in Myoelectric Control Symposium, UNB Press, Canada.
Improving Control of Dexterous Hand Prostheses Using Adaptive Learning
Tommasi Tatiana, Orabona Francesco, Castellini Claudio, Caputo Barbara, Improving Control of Dexterous Hand Prostheses Using Adaptive Learning, in IEEE Transaction on Robotics.
Multi-Souce Adaptive Learning for Fast Control of Prothetics Hand
Patricia Novi, Tommasi Tatiana, Caputo Barbara, Multi-Souce Adaptive Learning for Fast Control of Prothetics Hand, in International Conference on Pattern Recognition, IEEE Press, Stockholm.
Natural Control Capabilities of Robotic Hands by Hand Amputated Subjects
Atzori Manfredo, Gijsberts Arjan, Muller Henning, Caputo Barbara, Natural Control Capabilities of Robotic Hands by Hand Amputated Subjects, in Annual International Conference of the IEEE Engineering in Medicine and Biology Society , IEEE Press, USA.
Proceedings of the first workshop on Peripheral Machine Interfaces: Going beyond traditional surface electromyography
1. Castellini Claudio, Artemiadis Pagiotis, Wininger Mark, Ajoudani Antonis, Bicchi Antonio, Caputo Barbara, Scheme Erik, Proceedings of the first workshop on Peripheral Machine Interfaces: Going beyond traditional surface electromyography, in Frontiers in Neurobotics.

Scientific events



Self-organised

Title Date Place
International Symposium on Control interface in upper extremity prosthetics: State of the art and beyond the state of the art! 16.05.2014 Leipzig, Germany
Non-Invasive Adaptive Prosthetics (Ninapro) Workshop 22.11.2013 Montevideo, Uruguay
1st PNS-MI Workshop – Peripheral Neural Interfaces 14.06.2013 Seattle, United States of America

Associated projects

Number Title Start Funding scheme
160837 Myo-Electricity, Gaze and Artificial Intelligence for Neurocognitive Examination and Prosthetics 01.02.2016 Sinergia

Abstract

Daily life of hand amputees can be poor compared to what it was before the amputation. The state of the art in hand prosthetics, at the time of writing, does not offer more than 2-3 degrees of freedom and a very coarse control of the force, as there is no haptic feedback. Patients interface with the prosthesis via surface electromyography (sEMG), recorded using surface electrodes. Learning how to control the device through many input sEMG channels is a long and difficult process for most patients, that therefore settles for limited and very simplified movements (open/close). This contrasts with recent advances in mechatronics, thanks to which mechanical hands gifted with many degrees-of-freedom and force control are being built. There is a need for prosthetic hands able to naturally reproduce a wide amount of movements and forces, while at the same time requiring a lower effort in learning how to control hand postures. This goes beyond mechatronic dexterity: the real challenge is how to provide patients with a cheap, easy and natural way of controlling the prosthesis. The goal of this project is to develop a family of algorithms able to significantly augment the dexterity, and reduce the training time, for sEMG controlled prosthesis. By testing our findings on a very large collection of data, this project will pave the way for a new generation of prosthetic hands. The work will be organized along the following four themes.Theme 1: Data Acquisition.The goal of this theme is to develop a reproducible protocol to acquire large data sets for healthy patients performing certain movements and amputated patients also making complex movements, while analyzing and assessing the data as they become available. The data acquisition includes the acquisition of signal data and the calibration of the sensors to limit the noise in the data. Relevant clinical data will be acquired at the same time such as age, gender, height, weight and for amputated patients also the exact place of the amputation and the time between amputation and tests performed. The data acquisition and analysis will proceed in close connection with the other themes.Theme 2: Augmented Dexterity: Posture ClassificationThe objective of this theme is to push the current state of the art in prosthetic hand posture classification from handling a maximum of 12 postures up to 40-50. We will design and implement state of the art machine learning algorithms within the multi kernel learning framework, using the sEMG signals separated instead of concatenated, as it is the mainstream practice today. We will then proceed to extend the algorithm so to exploit the intrinsic hierarchical structure of hand postures. The outcome of this theme will offer patients a much wider dexterity compared to the current state of the art.Theme 3: Augmented Dexterity: Natural ControlThis research theme is about pushing the envelope of sEMG control: extending it to a quasi-perfect prediction of force, by independently modeling and controlling single degrees-of-motion. The overall aim is then to augment the dexterity that an sEMG-controlled prosthesis could potentially achieve mimicking the way a human hand works. Results in this theme will be periodically benchmarked against those achieved in Theme 2.Theme 4: Adaptive LearningThe goal of this theme is to develop learning algorithms to better interpret the sEMG signals acquired from the patients, with the ultimate goal of boosting the learning process necessary for the patient to effectively use the prosthesis. We will build pre-trained models of various data postures, on the data acquired in theme 1, and we will adapt these general models to the needs of individual users as new data will became available using adaptive online learning methods.
-