Bridging the gap between classical control theory and modern AI, Control for Robotics offers a comprehensive journey from the foundations of Optimal Control to modern Deep Reinforcement Learning. We have designed this course to combine rigorous derivations with practical programming exercises to help you build controllers that can handle the complexity of real-world robot decision-making. Whether you are a student or a practitioner, these resources will empower you to design intelligent, adaptive robotic systems.
The course is structured into eight main chapters:
- Introduction to Optimal Control
- Linear Quadratic Optimal Control
- Optimization Fundamentals
- Iterative Optimal Control Algorithms
- Model Predictive Control
- Model Learning and Learning-Based Control
- Introduction to Reinforcement Learning
- Deep Reinforcement Learning
The sequence of three courses follows from the book:
Feedback
We welcome feedback — please submit suggestions or issues through our feedback form.
Citation
If you use this handbook in your research, please cite it using the BibTeX entry below:
@book{cfr-handbook,
title = {{Control for Robotics:} From Optimal Control to Reinforcement Learning},
authors = {Angela P. Schoellig and SiQi Zhou},
year = {2025}
}
Authors
This course has been a collaborative effort over multiple years involving many people. The main authors are:| Angela P. Schoellig | Technical University of Munich |
| SiQi Zhou | Simon Fraser University |
- Lukas Brunke
- Martin Schuck
- Ralf Römer
- Oliver Hausdörfer
- Adam Hall
- Haocheng Zhao
- Luca Worbis
- Barry Yeh
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License .
Social
Acknowledgement
Many thanks to the great group of TAs that made this course possible!......