Title: HD Map, Localization and Self-Driving Car
Speaker: Shiyu Song, PhD is the senior research scientist and the technical lead of the mapping and localization team at Baidu Autonomous Driving Business Unit. Before joined Baidu, he was a research scientist at NEC Labs America working on visual SLAM, vision based vehicle localization system for autonomous driving. He joined Baidu in 2014. He is one of the founding team members of the Baidu autonomous driving car project. His research interests include map reconstruction, structure from motion (SFM), SLAM and localization, etc.
Abstract: We make brief introduction of the development history of Baidu self-driving car, Baidu Apollo platform for developers, the techniques behind the Baidu HD Map and our multi-sensor fusion based localization system. We present a robust and precise localization system that achieves centimeter-level localization accuracy in varied city scenes. Our system adaptively uses information from complementary sensors such as GNSS, LiDAR, and IMU to achieve high localization accuracy and robustness in various challenging scenes, including urban downtown, highway, tunnel and so on. Both our HD Map products and localization system have been deployed in a large autonomous driving fleet, and make our vehicles fully autonomous in crowded city streets every day.