ESE 650 - Learning in Robotics

They will be expected to have a good mathematical background with knowledge of machine learning techniques at the level of CIS 520, signal processing techniques at the level of ESE 531, as weill as have some robotics experience. This course will cover the mathematical fundamentals and applications of machine learning algorithms to mobile robotics. Possible topics that will be discussed include probabalistic generative models for sensory feature learning. Bayesian filtering for localization and mapping, dimensionality reduction techniques formotor control, and reinforcement learning of behaviors. Students are expected to have a solid mathematical background in machine learning and signal processing, and will be expected to implement algorithms on a mobile robot platform for their course projects. Grading will be based upon course project assignments as well as class participation
Recent Professors
Schedule Planner
Recent Semesters
Spring 2016
Avg. Class Size
Avg. Sections