Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

Autonomous navigation of an electric vehicle

Sarantinoudis Nikolaos

Full record


URI: http://purl.tuc.gr/dl/dias/E6BF0F08-E7F4-4E75-8F47-D982D67F5D0E
Year 2018
Type of Item Diploma Work
License
Details
Bibliographic Citation Nikolaos Sarantinoudis, "Autonomous navigation of an electric vehicle", Diploma Work, School of Electrical and Computer Engineering, Technical University of Crete, Chania, Greece, 2018 https://doi.org/10.26233/heallink.tuc.78897
Appears in Collections

Summary

Autonomous driving is one of the major areas of interest for the automotive industry. This constantly evolving field requires the involvement of a wide range of engineers with complementary skills. The education of these engineers is a key issue for the further development of the field. Currently in the engineering curricula, there is a lack of related platforms that can assist the engineers to train in and further develop the required dexterities. The current practice is to use either small robotic devices or full scale prototypes in order to understand and experiment in autonomous driving principles. Each approach has disadvantages ranging from the lack of realistic conditions to the cost of the platforms and sensors being used. In this thesis we present a low-cost and open-source modular electric vehicle platform, consisting from off-the-shelf components, which can be used for experimentation and research in the area of autonomous cars. This proposed platform, an urban concept vehicle, aims to tackle the problems of realistic conditions and cost respectively. Equipped with perception sensors, such as camera, lidar and ultrasonics, as well as navigation sensors such as GPS and IMU, provides the ideal foundation for anyone dealing with autonomy - from beginners to experts. The motivation for this work was to construct and provide a functioning platform for research purposes in the domain. The functionality of the suggested system is verified by extensive experimentation in very-close-to-real traffic conditions proving reliability, robustness and easy adaptability in diverse test cases.

Available Files

Services

Statistics