ROB 498/ROB 599: Robot Learning for Planning and Control
Winter 2025



Instructor:
Dmitry Berenson
Office Hours: After class
Email: dmitryb [at] umich.edu

GSIs:
Zixuan Huang and Mark Van Der Merwe
Email: zixuanh, markvdm [at] umich.edu
Office Hours:

Zixuan: Monday and Thursday 1:30pm - 2:30pm

Mark: Tuesday and Wednesday 11am-12pm

Location: FRB 2320


We will use Piazza for questions and discussion. Access Piazza through the class Canvas page.

We will use autograder.io for homework submission.

Time: Lectures: Monday, Wednesday 3:00pm - 4:30pm in FXB 1012. 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 reinforcement learning. Students will implement the above learning algorithms on robots in simulation.

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

Syllabus: Please see here.

Tentative Course Schedule: