ETH Zurich open-sources full 2026 robot learning course: 12 weeks, VLA models, free
Syntetisaattori · x · 2026-09-06
ETH Zurich has open-sourced its entire Spring 2026 'Robot Learning: From Fundamentals to Foundation Models' course, taught by Oier Mees. All slides, lecture recordings, coding assignments and the GitHub repo are free with no signup.
- 12 weeks progressing from imitation learning and RL to Vision-Language-Action models and robotics foundation models
- Guest lectures from Physical Intelligence's co-founder, the creator of Diffusion Policy, Pieter Abbeel, and Dieter Fox
- Grading: paper presentations 20%, coding assignments 40%, final project 40%
- Weekly lecture plus student-led paper discussions and Thursday practice sessions
Course GitHub: mees-robot-learning-course/ethz-course-2026.
More from Embodied
- Xiaomi humanoid robot logs 98% success on factory tasks with 66 DoF, half in the hands — Olivier__OG · 2026-09-06
- Robots get their GPT-3 moment: In-Context Learning lets them learn new tasks from one demo — 量子位 · 2026-09-06
- Yacine Builds His Own Eye-Tracking Hardware with Custom Drivers for High-FPS Tracking — yacineMTB · 2026-09-06
- StarVLA open-sources VLAct: VLA backbone trained on 16 GPUs beats NVIDIA GR00T N1.6 with 20% of data — 机器之心 · 2026-09-06
- Show Lab sweeps 3/3 at CoRL 2026: MetaWAM hits 68.9% on RoboCasa with 39% lower inference latency — MikeShou1 · 2026-09-06
- NSF Launches $30M Center for Human and Robot Co-Adaptation Led by UT Austin — PeterStone_TX · 2026-09-06