Sack Lunch Seminar (SLS)

This talk will give an overview of the problem of navigation for mobile robots, with applications ranging from self-driving cars to autonomous underwater vehicles (AUVs). We will focus on the capability of Simultaneous Localization and Mapping (SLAM), in which the goal is to enable a mobile robot to build a map of an unknown environment while concurrently using that map to navigate. We will review the history of SLAM research and define some of the major challenges in SLAM, including choosing a map representation, developing algorithms for efficient state estimation, and solving for data association and loop closure. We will describe applications of SLAM for a variety of AUV missions including performing mine countermeasures and ship hull inspection missions. We will also describe recent research at MIT to develop dense 3D mapping capabilities for mobile robots, integrating KinectFusion with pose graph optimization techniques for SLAM. We will conclude the talk with a discussion of current and future research topics, including object-based and lifelong mapping, long-term autonomy, and advanced physical interaction with the world.

Joint work with Tom Whelan, Michael Kaess, John McDonald, Hordur
Johannsson, Maurice Fallon, David Rosen, Mark VanMiddlesworth, Ross
Finman, Paul Huang, Liam Paull, Dehann Fourie, and Franz Hover.