Machine Learning in Autonomous Driving

Machine Learning Seminar by Dr. Faezeh Tafazzoli, Machine Learning Engineer, Mercedes-Benz R&D

Abstract: Self-driving cars are rapidly evolving as we can see unimaginable innovation in hardware, software, and computing capabilities. However, as we progress towards advanced automobiles, an essential component in driving the development of level-4 and level-5 autonomous vehicles is Artificial Intelligence and Machine Learning. The full driving task is too complex an activity to be fully formalized as a sensing-acting robotics system that can be explicitly solved through model-based and learning-based approaches in order to achieve full unconstrained vehicle autonomy. Localization, mapping, scene perception, vehicle control, trajectory optimization, and higher-level planning decisions associated with autonomous vehicle development are still full of open challenges. This is especially true for unconstrained, real-world operation where the margin of allowable error is extremely small and the number of edge-cases is extremely large. This talk will go over some potential ML applications in this field with their corresponding challenges.

Bio: Faezeh Tafazzoli is a Machine Learning Engineer at Mercedes-Benz R&D, focusing on Sensor Fusion techniques in Autonomous Driving. She received her PhD in Computer Science from University of Louisville in 2017, working on Vehicle Make and Model Recognition with potential applications such as road traffic monitoring, driver assistance and intelligent parking. She has Master degrees from University of Nevada, Reno, and Amirkabir University of Technology, Iran. Her current research is focused on Computer Vision and Applied Machine Learning. In particular, she is interested in fine- grained classification, object detection and tracking, content-based image retrieval, and deep vision. Previously, Faezeh was employed as a research scientist intern at the Xerox Innovation Group (XRCW), PARC, and Eye-Com Corporation, working in the areas of Human Gait Analysis, Medical Remote Assessment, and Gaze Tracking.