Rehabilitation robotics is an emerging field of application that could introduce great improvements in the medical care of post-injury impairment minimization and motor recovery. The Fit for Medical Robotics (Fit4MedRob) project, funded by the Italian Ministry of University and Research, aims at identifying unmet needs of both patients and health-care workers and at tackling them with new technologies and protocols. In this context, the thesis proposes a new automated rehabilitation system involving a collaborative robot manipulator. The developed software program allows to set up customizable shoulder exercises by means of an intuitive graphical user interface. The exercises are then implemented on the robot manipulator, that serves as a reference to the patient. The patient replicates the movement, which is captured by sensors, and a real-time exercise evaluation system assesses the quality of the performance. The results of the evaluation are used to propose modifications to the exercise by exploiting a performance-based adaptation algorithm. The advantages introduced by the system reside mainly in the accurate evaluation of the movement, the user-friendly display of the results and the possibility to generalize the exercises to different parts of the body. Other important features are the modularity of the system structure, the technological benefits of using a general purpose manipulator and the quick set up. Future developments will include the extension of the system to exercises involving more complex movements, different body parts and contact between the robot and the patient.
Progetto ed Implementazione di un Sistema Automatico di Riabilitazione usando un Robot Collaborativo. La robotica riabilitativa è una tecnologia in espansione, che potrebbe apportare grandi miglioramenti nella pratica medica che affronta disabilità e recupero di funzionalità. Il progetto Fit For Medical Robotics (Fit4MedRob), finanziato dal Ministero dell’ Università e della Ricerca, mira a identificare i bisogni non corrisposti di pazienti e operatori sanitari e a soddisfarli con lo sviluppo di nuove tecnologie e protocolli. In questo contesto, la tesi propone un nuovo sistema automatico di riabilitazione che coinvolge un robot collaborativo. Il software sviluppato permette di impostare esercizi della spalla personalizzati tramite un’intuitiva interfaccia grafica. Gli esercizi sono quindi implementati sul manipolatore robotico, che opera come riferimento per il paziente. Il paziente replica il movimento, acquisito da sensori, e un sistema di valutazione dell’esercizio determina la qualità della performance. I risultati della valutazione vengono usati per proporre modifiche all’esercizio in maniera adattiva. I vantaggi introdotti dal sistema risiedono principalmente nella precisione della valutazione, nell’usabilità dell’interfaccia e nella possibilità di generalizzare gli esercizi a altre parti del corpo. Altre caratteristiche importanti sono la modularità della struttura, la comodità tecnologica di usare un manipolatore general purpose e l’immediatezza dell’installazione. Sviluppi futuri includeranno l’estensione del sistema a esercizi costituiti da movimenti più complessi, che coinvolgono anche altre parti del corpo e il contatto tra robot e paziente.
Design and Implementation of an Automated Rehabilitation System using a Collaborative Robot
DEL PIO, LUIGI ZACCARIA
2022/2023
Abstract
Rehabilitation robotics is an emerging field of application that could introduce great improvements in the medical care of post-injury impairment minimization and motor recovery. The Fit for Medical Robotics (Fit4MedRob) project, funded by the Italian Ministry of University and Research, aims at identifying unmet needs of both patients and health-care workers and at tackling them with new technologies and protocols. In this context, the thesis proposes a new automated rehabilitation system involving a collaborative robot manipulator. The developed software program allows to set up customizable shoulder exercises by means of an intuitive graphical user interface. The exercises are then implemented on the robot manipulator, that serves as a reference to the patient. The patient replicates the movement, which is captured by sensors, and a real-time exercise evaluation system assesses the quality of the performance. The results of the evaluation are used to propose modifications to the exercise by exploiting a performance-based adaptation algorithm. The advantages introduced by the system reside mainly in the accurate evaluation of the movement, the user-friendly display of the results and the possibility to generalize the exercises to different parts of the body. Other important features are the modularity of the system structure, the technological benefits of using a general purpose manipulator and the quick set up. Future developments will include the extension of the system to exercises involving more complex movements, different body parts and contact between the robot and the patient.È consentito all'utente scaricare e condividere i documenti disponibili a testo pieno in UNITESI UNIPV nel rispetto della licenza Creative Commons del tipo CC BY NC ND.
Per maggiori informazioni e per verifiche sull'eventuale disponibilità del file scrivere a: unitesi@unipv.it.
https://hdl.handle.net/20.500.14239/16632