CS 6758 - [Robot Learning]

Spring. 4 credits. Student option grading.

Prerequisite: knowledge of basic computer science principles and skills at a level sufficient to write a reasonably non-trivial computer program (e.g., CS 2110 or CS 3110 or equivalent); any one of the following courses in probability/statistics or signal processing: CS 2800 or ECE 2200 or ECE 3100 or ENGRD 2700 (or equivalent). Co-meets with CS 4758.

Staff.

Studies the problem of how an agent can learn to perceive its world well enough to act in it, to make reliable plans, and to learn from its own experience. The focus is on algorithms and machine learning techniques for autonomous operation of robots. Topics include filtering and state estimation (Kalman filters, particle filters); Markov decision process; learning (reinforcement and supervised learning); planning and control; perception (vision, sensing). The course has a term project involving physical robots; no final exam.