A laboratory course on 3D vision for robotic applications

3D vision has recently become particularly relevant for industrial robots operating in real-world unstructured environments. However, the complexity of robotic 3D vision systems poses novel and exciting challenges in academia, as teaching their design requires the students to understand how to develop the 3D measuring algorithms of the vision system, and how to integrate the precise vision measurements into the robot applications. This paper presents a practical, teaching framework composed of a sequence of laboratory assignments, which help instructors teach students how to integrate 3D vision algorithms into real-world robotic applications, and how to evaluate their design parameters using real-time data acquisition from 3D sensors. The proposed teaching framework has been integrated as part of an existing undergraduate course on Embedded Systems Design at the University of Cyprus, and early evaluation provided by students is also included.