Locomotion Modes Classification
Next generation of tools for rehabilitation robotics will require advanced human-robot interfaces able to activate the device as soon as patient's motion intention is raised. Although great progress has been made in the century long effort to design and implement robotic exoskeletons and powered orthoses, many design challenges still remain. One of the factor limiting current exoskeletons and orthoses is the lack of direct information exchange between the human wearer's nervous system and the wearable device.
With respect to previous researches, we plan to develop more sophisticated sensor systems to capture a broader set of parameters and provide proper input for the orthosis control unit. We are currently investigating the possibility to use advanced machine learning techniques for the identification of locomotion intentions from surface electromyography (sEMG) data. Current implementations have already demonstrated good accuracy during preliminary experiments on healthy subjects.
Collaborators
- Elena Ceseracciu, Department of Management and Engineering, Univ. of Padua, Italy
- Massimo Sartori, , Department of Neurorehabilitaion Engineering, Georg-August University, Göttingen, Germany
- Zimi Sawacha, Department of Information Engineering, Univ. of Padua, Italy
Host
University of Padua, DTG and BEM Laboratory@DEI
References
- E. Ceseracciu, M. Reggiani, Z. Sawacha, M. Sartori, F. Spolaor, C. Cobelli and E. Pagello. SVM classification of locomotion modes using surface electromyography for applications in rehabilitation robotics. In Robot and Human Interactive Communication (RO-MAN). The 18th IEEE International Symposium on, pages 165 –170, September 2010.
- E. Ceseracciu, M. Reggiani, Z. Sawacha, F. Spolaor, M. Sartori, E. Pagello, C. Cobelli. SVM-based classification of EMG signals for enhanced interfaces in lower extremities exoskeletons. In Siamoc Conference 2010, October 2010.
- E. Ceseracciu, M. Reggiani, Z. Sawacha, M. Sartori, E. Pagello and C. Cobelli. SVM-based classification for myoelectric control applied to lower limb. In Workshop CORNER, December 2009.
Current Students
Silvia SpolaoreSecond-cycle degree course (MSc level) in BioEngineering
University of Padua
March 2011-
Fabio MolonSecond-cycle degree course (MSc level) in Mechatronic Engineering
University of Padua
June 2010-
