Tutorial on Safe Vision-based Navigation of Autonomous Vehicles

Starting with the fundamentals of various camera setups such as monocular, stereo, and fisheye, Sriramya Bhamidipati, postdoctoral scholar in the Navigation and Autonomous Vehicles Lab, provides an overview of pose graph optimization and Simultaneous Localization and Mapping (SLAM). Sriramya also presents fault-resilient strategies in vision-based navigation that accounts for error sources caused by dynamic occlusions, harsh weather conditions, and repetitive features and the recent state-of-the-art on more advanced topics, such as providing certifiable guarantees for vision-based navigation and aiding vision measurements with neural networks and sensor fusion.