Resources

In this course, we will not strictly follow predefined resources; instead, we will weekly provide slides, online assignments, and tutorials. We are aiming at presenting the topic for each week in a self-contained way. However, we believe that the resources provide on this page will enable students to explore more in the areas of human-robot interaction, machine learning and humanoid robotics.

Textbooks

There is no required textbook for this course. We recommend several freely available books to provide mathematical formalization and details.

• Modern Robotics by Lynch et al.
• Human-Robot Interaction by Bartneck et al.
• Deep learning book by Goodfellow et al.
• Reinforcement learning by Sutton et al.
• Computer Vision: Algorithms and Applications by R. Szeliski
• Mathematics for machine learning by Deisenroth al.
• Neural Networks and Deep Learning by Michael Nielsen.
• The elements of statistical learning by Hastie et al.

Python/Numpy/Jupyter Notebook/TensorFlow tutorials

In this course, we will use Python 3 to show code snippets and prepare tutorials. We will also introduce TensorFlow 2.x and Keras to build machine learning models. You can also use other machine learning libraries: PyTorch, Caffee, Jax, etc. If you have programming experience with different languages and would like to switch to Python, the below list can be helpful to shorten the transition period.

• Python Numpy tutorials by Justin Johnson
• TensorFlow 2.x tutorials
• Jupyter Notebook tutorials

Simulation environments for robotics

The main application area of this course is humanoid robotic. You can find free simulation environments for robotics in the following links:

• qiBullet: a simulation environement based on bullet physic engine.
• Gazebo: a multi-purpose robot simulator
• ROS: robot operating system
• The NRP: Neurorobotics platform

Miscellaneous reading list

• Distill and the gradient are online magazines to have visual understanding of machine learning concepts. The content of them will be helpful to develop and intuition on the behavior of the machine learning models.
• A Recipe for Training Neural Networks, a collection of advice to debug your models, by Andrei Karpathy.
• Machine learning methods visualizations by Christopher Olah.

Resources for the assignments

• Reading research papers by Andrew Ng
• How to read a paper
• Ten Simple Rules for Writing a Literature Review
• Ten Simple Rules for Writing Research Papers
• Ten Simple Rules for Better Figures
• Ten simple rules for short and swift presentations
• Ten Simple Rules for Making Good Oral Presentations

Acknowledegments

The content of this course was inspired from various online courses on deep learning, computer vision and robotics including cs231, CSCI 1430, STAT 453, and EECS 498-007 / 598-005.