PhD Scientific Days 2022

Theoretical Medicine (Poster discussion will take place on the terrace of the room during the Coffee Break)

PlatypOUs—A Mobile Robot Platform and Demonstration Tool Supporting STEM Education

Text of the abstract

Introduction: in an interdisciplinary project, students at Semmelweis University and Óbuda University developed a mobile robot platform that uses electrophysiological signals as control instructions.
Aim: the aim of the project was to create a mobile robot system for educational purposes (to be featured in a robot operating system programming course at Óbuda University) and to facilitate interaction between different research fields (robotics and health sciences) and students from different levels of education (i.e. from bachelor’s to doctoral studies).
Methods: the hardware is based on an Intel mini-PC, has differentially driven wheels and is equipped with wheel encoders, a LIDAR, a depth camera and an inertial measurement unit (containing an accelerometer and a gyroscope). As signal acquisition device, a portable electroencephalography headset (a MindRove arc) is utilized. The robot can be controlled to make a 90° turn to the right, to go forward or stop. A graphical user interface collects sample sequences corresponding to each command and trains a support vector machine-based classifier to differentiate between the samples.
Results: regarding sample prediction accuracy, our system could achieve 86.67%; in a pattern following task, an average error of 12.39% was encountered.
Conclusion: The initial tests have deemed our proof-of-concept system useable but further validation is required to prove its real-world feasibility.
Funding: The research was supported by the Eötvös Loránd Research Network Secretariat under grant agreement no. ELKH KÖ-40/2020 (‘Development of cyber-medical systems based on AI and hybrid cloud methods’). Project no. 2019-1.3.1-KK-2019-00007 has been implemented with the support provided from the National Research, Development and Innovation Fund of Hungary, financed under the 2019-1.3.1-KK funding scheme. The publication of the original article has been supported by the Robotics Special College via the ’NTP-SZKOLL-21-0034 Talent management and professional community building at the ÓE ROSZ’ project. Project no. FK132823 has been implemented with the support provided by the Ministry of Innovation and Technology of Hungary from the National Research, Development and Innovation Fund, financed under the FK_19 funding scheme. Melinda Rácz is thankful for the SE 250+ Doctoral Scholarship for Excellence.