Home /Research /A Multidisciplinary Course and the Corresponding Laboratory Platform Development for Teaching the Fundamentals of Advanced Autonomous Vehicles
PERCEPTION

A Multidisciplinary Course and the Corresponding Laboratory Platform Development for Teaching the Fundamentals of Advanced Autonomous Vehicles

Nima Lotfi, Jacob Novosad, Huan Phan-Van

Year
2020
Citations
3

Abstract

Abstract In the past few decades, autonomous features have been gradually augmented to traditional ground transportation systems. These features can range from simple cruise control, blind spot detection, and lane departure control, all the way to autopilot systems. Aiming to train the next generation of engineers in this field and to fill the skill gap among students in traditional engineering disciplines, a multi-purpose and multidisciplinary course, named “Autonomous Ground Vehicles”, along with an open-source laboratory platform was developed by the author. The proposed laboratory platform can be used to study a wide range of topics regarding autonomous vehicles, ranging from low-level data acquisition and control to higher-level concepts such as sensor fusion and SLAM. This paper discusses the pedagogical considerations in the syllabus and experimental laboratory platform design for this unique course. The course was offered as a cross-listed elective course among Mechanical Engineering, Mechatronics and Robotics Engineering, and Computer Science majors. Therefore, the challenges faced during the course offering, especially ensuring that the course is appropriate for ME, MRE, and CS students while complex enough to cover the essential fundamentals of autonomous vehicles are also discussed. Finally, the outcomes of offering this course in terms of student feedback, the lessons learned, and the future directions will be presented and discussed in the paper.

Keywords

Course (navigation)MechatronicsMultidisciplinary approachSyllabusAutopilotRoboticsEngineeringSystems engineeringComputer scienceEngineering management

Related papers

Browse all PERCEPTION papers