Jeffrey Hawke Seminar at the Department of Engineering Science, University of Oxford

Abstract: Creating a vehicle which is able to intelligently drive itself is one of the hardest (and most interesting) technical problems we have today, which the potential for wide ranging societal shifts. The industry has made many advances toward getting autonomous vehicles on the road, but we still have many hurdles remaining. In this talk, we will share some of the technical challenges facing the self-driving industry currently, and how we at Wayve are working towards a solution. Machine learning has enabled many breakthroughs in autonomous driving over the last few years, though typically is constrained to problems of perception. At Wayve, it has enabled us to learn driving policies for autonomous vehicles without relying on high definition maps or hand-coded, rule-based planners.

Bio:  Jeff has worked in R&D for autonomous robots in both industry and academia: highlights include creating software for autonomous forklifts deployed in factory production lines and warehouses, motion planning for grasping in cluttered spaces with personal robots, force control for collaborative robots for manufacturing, and perception for self-driving cars during his DPhil at Oxford with the mobile robotics group (now ORI A2I lab). At Wayve he works across tech and business strategy, developing machine learning approaches to autonomous driving.