Ιδρυματικό Αποθετήριο
Πολυτεχνείο Κρήτης
EN  |  EL

Αναζήτηση

Πλοήγηση

Ο Χώρος μου

Gesture recognition using artificial intelligence and application to an unmanned ground vehicle (UGV)

Tsiftsi Christina

Πλήρης Εγγραφή


URI: http://purl.tuc.gr/dl/dias/5E790FB2-F16C-469D-A131-DED925820D0A
Έτος 2024
Τύπος Μεταπτυχιακή Διατριβή
Άδεια Χρήσης
Λεπτομέρειες
Βιβλιογραφική Αναφορά Christina Tsiftsi, "Gesture recognition using artificial intelligence and application to an unmanned ground vehicle (UGV)", Master Thesis, School of Production Engineering and Management, Technical University of Crete, Hellenic Army Academy, Chania, Greece, 2024 https://doi.org/10.26233/heallink.tuc.100541
Εμφανίζεται στις Συλλογές

Περίληψη

This thesis explores the integration of advanced gesture recognition technologies into the control systems of unmanned ground vehicles (UGVs), aiming to enhance their operability and user interaction. The research leverages a comprehensive approach, combining Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) methodologies to develop a robust and efficient gesture recognition system. The study begins with the theoretical foundations of AI, ML, and DL, establishing a framework for the subsequent development of gesture recognition algorithms, then delves into a thorough review of existing UGV control interfaces and identifies the limitations of traditional input methods. The core of the research involves the creation of a tailored gesture recognition system utilizing ML and DL techniques. This system is trained on diverse datasets to ensure adaptability to various user gestures and environmental conditions. The integration of real-time processing ensures swift and accurate interpretation of gestures, facilitating seamless communication between the operator and the UGV.Furthermore, the thesis investigates the practical implementation of the gesture recognition system on an unmanned ground vehicle prototype. Through a series of experiments and simulations, the effectiveness of the developed system is evaluated in terms of responsiveness, accuracy, and overall usability in diverse operational scenarios. The findings of this research contribute to the field of UGV control interfaces by providing a novel, AI-driven solution that significantly improves the human-UGV interaction paradigm. The study not only advances the theoretical understanding of gesture recognition within the context of unmanned systems but also offers practical insights into the integration of such technologies for real-world applications.In conclusion, the thesis establishes the potential of combining AI, ML, and DL in the realm of gesture recognition for unmanned ground vehicles, paving the way for more intuitive and efficient control interfaces in the evolving landscape of autonomous systems.

Διαθέσιμα αρχεία

Υπηρεσίες

Στατιστικά