Multi-Camera Localization and Mapping for Autonomous Vehicles


Steve Waslander, University of Waterloo

Multi-Camera Localization and Mapping for Autonomous Vehicles

4-5 pm 240 Bechtel, 3:30 cookies and beverages in the ITS Library

Abrstract: Winter conditions provide a significant impediment to most existing autonomous driving perception and planning methods, due to the negative effects on sensor data and the significantly altered landscape and road conditions. Visual data tends to be light on reliable features and challenged by high contrast scenes, while both vision and lidar measurements are corrupted by precipitation. Road markings can be degraded or occluded, leading to significant challenges in lane detection. In this talk, I will present recent work in multi-camera localization in snow-covered environments and degraded lane marking detection currently being deployed on the Waterloo Autonomoose self-driving test vehicle.

Bio: Prof. Steven Waslander received his 1998 from Queen's University, his M.S. in 2002 and his Ph.D. in 2007, both from Stanford University in Aeronautics and Astronautics. He was a Control Systems Analyst for Pratt & Whitney Canada from 1998 to 2001. In 2008, he joined the Department of Mechanical and Mechatronics Engineering at the University of Waterloo in Waterloo, ON, Canada, where he is now an Associate Professor. He is the Director of the Waterloo Autonomous Vehicles Laboratory (WAVELab, His research interests lie in the areas of autonomous aerial and ground vehicles, simultaneous localization and mapping, nonlinear estimation and control, and multi-vehicle systems.