Systems and Algorithms for Autonomous Vehicles

The course provides an in-depth introduction to autonomous vehicles, addressing both the algorithms aspect and the systems aspect. The course consists of two parts. Part 1: Theory (5.5 hp). History and background of autonomous driving; perception-planning-control pipeline of autonomous vehicles; fundamentals of Machine Learning, Deep Learning and Reinforcement Learning; Convolutional Neural Networks for perception, including object classification, object detection, and segmentation; classic planning and control algorithms; Reinforcement Learning-based planning and control algorithms; safety and security issues; hardware and software platforms. Part 2: Lab Assignments (2.0 hp). Training and deployment of Deep Learning models for autonomous driving with a framework such as Tensorflow or PyTorch; implementation of part of the perception-planning-control pipeline in a simulation environment.