Connection: Zoom Link
Phone Dial-in: +1 650 724 9799 (US Toll) or +1 833 302 1536 (US Toll Free)
Meeting ID: 931 9963 2737, Password: 531513 Attendees: CARS Affiliates (please forward invitation wiithin your organization)
Abstract: Merging into traffic is one of the most common day-to-day maneuvers we perform as drivers, yet still poses a major problem for self-driving vehicles. The reason that humans can naturally navigate through such social interaction scenarios is that we have an intrinsic capacity to reason about other people’s intents, beliefs, and desires, using this reasoning to predict what might happen in the future and make corresponding decisions. In this webinar, computational techniques for enabling self-driving cars to make predictions of the social world around them will be discussed, focusing on the rapidly-evolving field of trajectory forecasting. The webinar will feature three segments, beginning with a discussion about the problem of trajectory forecasting and methods for solving it. The second part of the webinar will discuss how, even with the ability to predict the future, it is still unclear how best to integrate such trajectory forecasting models within the autonomy stack. For instance, what information is required from upstream perception modules? How can future predictions be efficiently incorporated in downstream planning and control algorithms? The webinar will conclude with a view towards the future, discussing potential advancements in trajectory forecasting in the presence of fleets of networked autonomous vehicles in diverse geographies. Bio: Boris Ivanovic is a Ph.D. Candidate in Aeronautics and Astronautics at Stanford University. His research interests center around trajectory forecasting and its exciting applications within autonomous driving, combining techniques from machine learning with principled methods in robotics such as motion planning and optimization-based model predictive control. He received an M.S. in Computer Science from Stanford as well as a B.A.Sc. in Engineering Science from the University of Toronto.