The course covers essentials of Artificial Intelligence, Machine Learning and Deep Learning with a specific focus on Computer Vision and image-based applications for autonomous vehicles (AVs) across eight modules. Key application-focused topics include Image Classification, Object Detection, Image Segmentation and Modeling Car Behavior in AVs ensuring up-to date application ways in different scenarios for autonomous vehicles, through the Computer Vision perspective.
This course provides an overview of Autonomous Intelligent Vehicle (AIV) software technology and architecture. It covers the evolution of automotive architectures, the need for new software-defined vehicle (SDV) approaches, and the role of DevOps in modern automotive software development.
This course provides the necessary background to begin programming tasks for autonomous driving functions. To this end, the curriculum covers autonomous vehicle hardware, real-time system classifications (Hard, Soft, and Firm), and modular software architectures for self-driving vehicles. Practical applications are emphasized through Robot Operating System 2 (ROS2) in C++ and Python, featuring hands-on examples in image data processing, CAN communication, and object detection using YOLOv8.
This course covers path planning methods for autonomous vehicles, from basic task classification to practical simulation. Key topics include route and motion planning, road representations, path optimization, parametric curve techniques including Bézier curves and polynomials, with practical applications demonstrated using MATLAB and Simulink.
Course covers an introduction to different map types, map layers and map generation, along with the fundamental concepts of vehicle localization and navigation. The modules include specific localization methods using GNSS data with RTK, LiDAR point clouds with Normal Distribution Transform (NDT), and Simultaneous Localization and Mapping (SLAM).