Michele Barsotti

Michele Barsotti

Auto-generated profile, based on publicly available information

Michele Barsotti

PERCRO Laboratory, TeCIP Institute, Scuola Superiore Sant'Anna, Pisa, Italy

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 December 2012 in IEEE Transactions on Systems, Man and Cybernetics, Part C (Applications and Reviews)
Verified
Journal Article
Closed access
AFAntonio Frisoli
Antonio Frisoli
Claudio LoconsoleClaudio Loconsole
Claudio Loconsole
DLDaniele Leonardis
Daniele Leonardis
FBFilippo Banno
Filippo Banno
MBMichele Barsotti
Michele Barsotti
MBMassimo Bergamasco
Massimo Bergamasco
This paper proposes a new multimodal architecture for gaze-independent brain-computer interface (BCI)-driven control of a robotic upper limb exoskeleton for stroke rehabilitation to provide active assistance in the execution of reaching tasks in a real setting scenario. At the level of action plan, the patient's intention is decoded by means of an active vision system, through the combination of a Kinect-based vision system, which can online robustly identify and track 3-D objects, and an eye-tracking system for objects selection. At the level of action generation, a BCI is used to control the patient's intention to move his/her own arm, on the basis of brain activity analyzed during motor imagery. The main kinematic parameters of the reaching movement (i.e., speed, acceleration, and jerk) assisted by the robot are modulated by the output of the BCI classifier so that the robot-assisted movement is performed under a continuous control of patient's brain activity. The system was experimentally evaluated in a group of three healthy volunteers and four chronic stroke patients. Experimental results show that all subjects were able to operate the exoskeleton movement by BCI with a classification error rate of 89.4±5.0% in the robot-assisted condition, with no difference of the performance observed in stroke patients compared with healthy subjects. This indicates the high potential of the proposed gaze-BCI-driven robotic assistance for neurorehabilitation of patients with motor impairments after stroke since the earliest phase of recovery.

1 October 2014 in PRESENCE: Virtual and Augmented Reality
Verified
Journal Article
Closed access
DLDaniele Leonardis
Daniele Leonardis
AFAntonio Frisoli
Antonio Frisoli
MBMichele Barsotti
Michele Barsotti
MCMarcello Carrozzino
Marcello Carrozzino
MBMassimo Bergamasco
Massimo Bergamasco
This study investigates how the sense of embodiment in virtual environments can be enhanced by multisensory feedback related to body movements. In particular, we analyze the effect of combined vestibular and proprioceptive afferent signals on the perceived embodiment within an immersive walking scenario. These feedback signals were applied by means of a motion platform and by tendon vibration of lower limbs, evoking illusory leg movements. Vestibular and proprioceptive feedback were provided congruently with a rich virtual scenario reconstructing a real city, rendered on a head-mounted display (HMD). The sense of embodiment was evaluated through both self-reported questionnaires and physiological measurements in two experimental conditions: with all active sensory feedback (highly embodied condition), and with visual feedback only. Participants' self-reports show that the addition of both vestibular and proprioceptive feedback increases the sense of embodiment and the individual's feeling of presence associated with the walking experience. Furthermore, the embodiment condition significantly increased the measured galvanic skin response and respiration rate. The obtained results suggest that vestibular and proprioceptive feedback can improve the participant's sense of embodiment in the virtual experience.

13 November 2018 in Frontiers in Neurorobotics
Verified
Journal Article
Open access
PDF file
Domenico BuongiornoDomenico Buongiorno
Domenico Buongiorno
MBMichele Barsotti
Michele Barsotti
FBFrancesco Barone
Francesco Barone
VBVitoantonio Bevilacqua
Vitoantonio Bevilacqua
AFAntonio Frisoli
Antonio Frisoli
The growing interest of the industry production in wearable robots for assistance and rehabilitation purposes opens the challenge for developing intuitive and natural control strategies. Myoelectric control, or myo-control, which consists in decoding the human motor intent from muscular activity and its mapping into control outputs, represents a natural way to establish an intimate human-machine connection. In this field, model based myo-control schemes (e.g., EMG-driven neuromusculoskeletal models, NMS) represent a valid solution for estimating the moments of the human joints. However, a model optimization is needed to adjust the model's parameters to a specific subject and most of the optimization approaches presented in literature consider complex NMS models that are unsuitable for being used in a control paradigm since they suffer from long-lasting setup and optimization phases. In this work we present a minimal NMS model for predicting the elbow and shoulder torques and we compare two optimization approaches: a linear optimization method (LO) and a non-linear method based on a genetic algorithm (GA). The LO optimizes only one parameter per muscle, whereas the GA-based approach performs a deep customization of the muscle model, adjusting 12 parameters per muscle. EMG and force data have been collected from 7 healthy subjects performing a set of exercises with an arm exoskeleton. Although both optimization methods substantially improved the performance of the raw model, the findings of the study suggest that the LO might be beneficial with respect to GA as the latter is much more computationally heavy and leads to minimal improvements with respect to the former. From the comparison between the two considered joints, it emerged also that the more accurate the NMS model is, the more effective a complex optimization procedure could be. Overall, the two optimized NMS models were able to predict the shoulder and elbow moments with a low error, thus demonstrating the potentiality for being used in an admittance-based myo-control scheme. Thanks to the low computational cost and to the short setup phase required for wearing and calibrating the system, obtained results are promising for being introduced in industrial or rehabilitation real time scenarios.

1 August 2015
Verified
Conference Paper
Closed access
MBM. Barsotti
M. Barsotti
DLD. Leonardis
D. Leonardis
Claudio LoconsoleClaudio Loconsole
Claudio Loconsole
MSM. Solazzi
M. Solazzi
Edoardo SotgiuEdoardo Sotgiu
Edoardo Sotgiu
AFA. Frisoli
A. Frisoli
In this paper we propose a full upper limb exoskeleton for motor rehabilitation of reaching, grasping and releasing in post-stroke patients. The presented system takes into account the hand pre-shaping for object affordability and it is driven by patient's intentional control through a self-paced asynchronous Motor Imagery based Brain Computer Interface (MI-BCI). The developed antropomorphic eight DoFs exoskeleton (two DoFs for the hand, two for the wrist and four for the arm) allows full support of the manipulation activity at the level of single upper limb joint. In this study, we show the feasibility of the proposed system through experimental rehabilitation sessions conducted with three chronic post-stroke patients. Results show the potential of the proposed system for being introduced in a rehabilitation protocol.

14 August 2017 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Verified
Journal Article
Closed access
MBMichele Barsotti
Michele Barsotti
DLDaniele Leonardis
Daniele Leonardis
NVNicola Vanello
Nicola Vanello
MBMassimo Bergamasco
Massimo Bergamasco
Antonio FrisoliAntonio Frisoli
Antonio Frisoli
Background and objectives: Feedback plays a crucial role for using brain computer interface systems. This paper proposes the use of vibration-evoked kinaesthetic illusions as part of a novel multisensory feedback for a motor imagery (MI)-based BCI and investigates its contributions in terms of BCI performance and electroencephalographic (EEG) correlates. Methods: sixteen subjects performed two different right arm MI-BCI sessions: with the visual feedback only and with both visual and vibration-evoked kinaesthetic feedback, conveyed by the stimulation of the biceps brachi tendon. In both conditions, the sensory feedback was driven by the MI-BCI. The rich and more natural multisensory feedback was expected to facilitate the execution of MI, and thus to improve the performance of the BCI. The EEG correlates of the proposed feedback were also investigated with and without the performing of MI. Results and Conclusions: the contribution of vibration-evoked kinaesthetic feedback led to statistically higher BCI performance (Anova, F (1,14) = 18.1, p <; .01) and more stable EEG event-related-desynchronization. Obtained results suggest promising application of the proposed method in neuro-rehabilitation scenarios: the advantage of an improved usability could make the MI-BCIs more applicable for those patients having difficulties in performing kinaesthetic imagery.

10 December 2018 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
MBMichele Barsotti
Michele Barsotti
SDSigrid Dupan
Sigrid Dupan
IVIvan Vujaklija
Ivan Vujaklija
Strahinja DosenStrahinja Dosen
Strahinja Dosen
Antonio FrisoliAntonio Frisoli
Antonio Frisoli
DFDario Farina
Dario Farina
A hand impairment can have a profound impact on the quality of life. This has motivated the development of dexterous prosthetic and orthotic devices. However, their control with neuromuscular interfacing remains challenging. Moreover, existing myocontrol interfaces typically require an extensive calibration. We propose a minimally supervised, online myocontrol system for proportional and simultaneous finger force estimation based on ridge regression using only individual finger tasks for training. We compare the performance of this system when using two feature sets extracted from high-density EMG recordings: EMG linear envelope (ENV) and non-linear EMG to Muscle Activation mapping (ACT). Eight intact-limb participants were tested using online target reaching tasks. On average, the subjects hit 85 × 9% and 91 × 11% of single finger targets with ENV and ACT features respectively. The hit rate for combined finger targets decreased to 29 × 16% (ENV) and 53 × 23% (ACT). The non-linear transformation (ACT) therefore improved the performance, leading to higher completion rate and more stable control, especially for the non-trained movement classes (better generalization). These results demonstrate the feasibility of proportional multiple finger control by regression on non-linear EMG features with a minimal training set of single finger tasks.