@misc{Awasthi, type = {Master Thesis}, author = {Awasthi, Sudarshan}, title = {Pepper ChatGPT System as a Study Programme Guide for Students}, school = {Hochschule Rhein-Waal}, abstract = {This thesis centers on enhancing the humanoid Pepper robot with Artificial Intelligence-driven information delivery capabilities in an educational setting using Large Language Model at student service centers. In this work, Pepper was connected to GPT-Engine to act as a voice assistant robot. With the help of GPT-Engine Pepper can answer questions about the University and its study programmes. The enhancement involves a client-server architecture, where the client-side application enables students to interact with Pepper via speech, and the server-side, equipped with AI functionalities, processes these interactions and generates appropriate responses. This setup significantly augments Pepper's capabilities, allowing for more accurate and efficient information delivery. An experiment was conducted with nine student participants of Hochschule-Rhein Waal, where they asked questions about the University and study Programmes to inform themselves about the University and Study Programmes. During the interaction, they evaluated the robot's clarity of communication, accuracy of responses, and overall user experience. The findings indicate that while the AI enhancements generally improved Pepper's ability to communicate and provide information, areas such as voice recognition and response accuracy require further improvement. This research contributes to the field of human-robot interaction by illustrating a practical approach to augmenting existing service robots with AI capabilities. It underscores the importance of advanced AI integration in enhancing the functionality of service robots in educational environments. The study provides valuable insights into the broader application of AI-enhanced robots in the Information Guide role, highlighting the ongoing need for technological advancements in AI integration and humanrobot interaction.}, language = {en} } @masterthesis{Schink, type = {Bachelor Thesis}, author = {Schink, Lukas}, title = {Pepper: Der halbautonome, humanoide Service-Roboter}, school = {Hochschule Rhein-Waal}, abstract = {Die vorliegende Arbeit untersucht die Integration großer Sprachmodelle in die Steuerung humanoider Roboter, am Beispiel der Anbindung von ChatGPT an den Service-Roboter Pepper. Motivation der Arbeit ist die Frage, wie moderne Sprachmodelle die Interaktionsf{\"a}higkeit {\"a}lterer Roboterplattformen verbessern k{\"o}nnen, sodass Roboter wie Pepper trotz ihres Alters und begrenzter physischer F{\"a}higkeiten in sozialen und bildungsbezogenen Anwendungen relevant bleiben. Ziel der Forschung ist es, Peppers Kommunikations- und Interaktionsm{\"o}glichkeiten durch die Kombination seiner bestehenden und m{\"o}glichen Funktionen mit den Sprachverarbeitungsf{\"a}higkeiten von ChatGPT zu erweitern. Hierzu wurde ein System entwickelt, das kontextbasierte Codes (Actioncodes) verwendet, die es dem Sprachmodell erm{\"o}glichen, Peppers Verhalten dynamisch zu steuern und flexibel auf Situationen zu reagieren. Dazu geh{\"o}rt die technische Anbindung von ChatGPT an die QiSDK, die Implementierung spezifischer Actioncodes sowie die Definition einer Pers{\"o}nlichkeit und kontextuellen Wissensbasis f{\"u}r den Roboter. Das System wurde auf Basis vorangegangener Feldversuche im Labor getestet und evaluiert. Die Ergebnisse zeigen, dass die Integration von ChatGPT Peppers Interaktionsf{\"a}higkeit signifikant verbessert, indem die Kommunikation nat{\"u}rlicher und die Reaktionen des Roboters flexibler werden. Diese Arbeit demonstriert, wie moderne Sprachmodelle dazu beitragen k{\"o}nnen, {\"a}ltere Robotersysteme zu modernisieren und ihre Einsatzm{\"o}glichkeiten erheblich zu erweitern.}, language = {de} } @masterthesis{Elmessiry2025, type = {Bachelor Thesis}, author = {Elmessiry, Abdalrahman}, title = {implementation and investigation of a distributed robotic chess system}, school = {Hochschule Rhein-Waal}, year = {2025}, abstract = {This thesis presents and evaluates a distributed robotic system that successfully integrates a native Windows chess engine (Fritz 19) with a containerized ROS2-based robot control system, operating on a single host computer. The architecture is designed to solve the common challenge of bridging disparate operating systems in real-time robotics. Performance analysis over 35 moves demonstrates the architecture's high reliability, achieving a 100\% success rate in the software pipeline from command generation to execution planning. The study quantifies the system's primary performance bottleneck, showing that the physical robot movement averaged 22.6 seconds, while the underlying communication latency was negligible at 2.89 ms. This highlights a crucial distinction between computational speed and the challenges of physical manipulation. Compared to existing human-robot chess systems, which typically operate within a single OS or rely heavily on computer vision, this work contributes a validated architectural alternative. Its primary contribution is a single-host framework that integrates a native Windows application with a containerized ROS2 system. This provides a robust solution for developers needing to bridge disparate software ecosystems in real-time robotics and establishes a performance baseline demonstrating that such integration is highly efficient.}, language = {en} }