Robot Localization and Navigation

Catalog description

This course presents the concepts, techniques, algorithms, and state-of-the-art approaches for robot perception, localization, and mapping. The course will show the theoretical foundations and will also have a substantial experimental component based on Matlab/ROS. The course will start from basic concepts in probability and then introduce probabilistic approaches for data fusion such as Bayes Filters, Kalman Filter, Extended Kalman Filter, Unscented Kalman Filter, and Particle Filter. Then, the course will introduce the SLAM problem showing how this has recently been solved using batch optimization and graph methods. Finally, mapping algorithms will also be briefly discussed.| Prerequisites: ECE-GY 6253 or ME-GY 6703 or ME-GY 6923 or department approval