Autonomous Navigation, Part 3: Understanding SLAM Using Pose Graph Optimization

This video provides some intuition around Pose Graph Optimization—a popular framework for solving the simultaneous localization and mapping (SLAM) problem in autonomous navigation.

We’ll cover why uncertainty in a vehicle’s sensors and state estimation makes building a map of the environment difficult and how pose graph optimization can deal with it. We’ll also briefly cover occupancy grid maps as one way to represent the environment model.

Additional Resources:

- Implement Simultaneous Localization and Mapping (SLAM) with MATLAB: https://bit.ly/2Yk9agi - Download ebook: Sensor Fusion and Tracking for Autonomous Systems: An Overview: https://bit.ly/2YZxvXA - Download white paper: Sensor Fusion and Tracking for Autonomous Systems - https://bit.ly/3dsf2bA - SLAM Course - 15 - Least Squares SLAM - Cyrill Stachniss video: https://youtu.be/VRGOLRGwAjg - Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age. Paper by Cesar Cadena, Luca Carlone, Henry Carrillo, Yasir Latif, Davide Scaramuzza, Jose ́ Neira, Ian Reid, John J. Leonard. - https://arxiv.org/abs/1606.05830 - Simultaneous Localisation and Mapping (SLAM): Part I. Paper by H. F. Durrant-Whyte and T. Bailey. IEEE Robotics and Automation Magazine, 13(2):99–110, 2006. - https://ieeexplore.ieee.org/document/... - Simultaneous Localisation and Mapping (SLAM): Part II. Paper by T. Bailey and H. F. Durrant-Whyte. Robotics and Autonomous Systems (RAS), 13(3):108–117, 2006. - https://ieeexplore.ieee.org/document/...