University of Michigan runs a free course on deep learning for robot perception:
It's called DeepRob. And it's built like a practitioner's course, not a lecture series.
Students implement and train their own neural networks for object detection, pose estimation, and physical manipulation. Then they reproduce and extend state-of-the-art papers as a final project.
The entire thing (syllabus, paper list, coding projects, datasets, student final reports) is public.
It's the applied complement to the more theoretical courses you've probably already seen. Less "understand the math", more "make the robot see and act."
The course traces its lineage directly to Stanford CS231n and Andrej Karpathy's computer vision work... just aimed at robots.
Free. No login.
📌 [https://t.co/qcR4rYup4w]
Follow for more resources like this!
——-
Weekly robotics and AI insights.
Subscribe free: https://t.co/9Nm01QUcw3
ETH Zurich just open-sourced their entire 2026 robot learning course.
Not a MOOC. The actual course. Slides, lecture recordings, coding assignments, GitHub repo.
The curriculum goes from imitation learning and RL all the way to Vision-Language-Action models and foundation models for robotics.
Guest lectures from the co-founder of Physical Intelligence. The creator of Diffusion Policy. Pieter Abbeel. Dieter Fox.
12 weeks. Free. No signup.
If you want to understand where robot intelligence is actually heading… this is the reading list the field is using right now.
📍[https://t.co/eKsIjILi60]
——
Weekly robotics and AI insights.
Subscribe free: https://t.co/9Nm01QUcw3