Theoretical Foundations

Multi-Robot Mapping

We describe an exact incremental solution to the SLAM problem by solving a full nonlinear optimization problem in real-time (with iSAM. One key consideration in multi-robot mapping is how to relate the measurements from different robots which are in different and unknown relative coordinate frames. In this work we tackle that problem with a new concept termed "Anchor Nodes."

Incremental Smoothing and Mapping

The iSAM algorithm was originally developed by Michael Kaess and Frank Dellaert at Georgia Tech. During his time as a PostDoc and research scientist in the Marine Robotics Group, Michael developed several extensions and improvements.