IAAC – Master in Robotics and Advanced Construction
Software III
Faculty: Mateusz Zwierzycki
Faculty Assistant: Soroush Garivani


Credits: MRAC19-20 Public Seating


This course will be an opportunity to experiment with various machine learning tools and algorithms available in Owl. It will start with a lecture explaining the current and the past problems of AI in design. The presentation will introduce the notions of supervised, unsupervised and reinforcement learning. Using Owl, the participants will then learn the Grasshopper-based workflow for neural networks (supervised learning) and Q-Learning (reinforcement learning). Introduction will end with an overview of Owl components used for image and data pre- and post-processing.

After the introduction, the focus will be put on the group projects and the ways to utilize ML to aid the designs either in sensing/responding or controlling. Reinforcement learning will be taught in the context of one of the most popular algorithms – Q-Learning. Students will learn about the inner mechanics of the algorithm, reward engineering, exploration vs exploitation problem, Markov decision process etc. Neural networks will be used for both regression and classification problems. The students will learn how to understand and control the learning process with all its hyperparameters. 

Over the course of the semester this knowledge shall be extended to application of QL and ANN in the students’ projects. Additional online consultations will be held to help the participants with that task. 

Learning objectives

During this course the students will be challenged to incorporate ML either for sensing/response or control. In that process several AI-based tools will be used: 

  • Neural Networks
  • Reinforcement Learning 
  • Evolutionary Solvers