ROB 498: Robot Learning for Planning and Control
Winter 2023

Nima Fazeli
Office Hours: After class
Email: nfz [at]
Dmitry Berenson
Office Hours: After class
Email: dmitryb [at]

Miquel Oller and Tom Power
Email: oller, tpower [at]
Office Hours:
Tues 4-5pm, room FRB3320 (Tom)
Weds 4:45-5:45pm, room FRB3200 (Tom and Miquel)
Fri 2-3pm room, FRB3320 (Miquel)

We will use Piazza for questions and discussion. Access the class discussion site here.

We will use for homework submission.

Time: Lectures: Monday, Wednesday 3:00pm - 4:30pm in G906 COOL. All lectures will be recorded and posted on Canvas.

Overview: An introduction to modern machine learning methods for control and planning in robotics. Topics include function approximation, learning dynamics, using learned dynamics in control and planning, handling uncertainty in learned models, learning from demonstration, and model-based and model-free reinforcement learning. Students will implement the above learning algorithms on robots in simulation.

Linear Algebra (ROB 101 or Math 214 or Math 217) and EECS 281

Syllabus: Please see here.

Tentative Course Schedule: