Teaching

I currently teach the following three courses, broadly spanning my research areas. Below you can find further details of these courses.


Bayesian Estimation for Flight Robotics (Lecture + Practical)

Format: 24 Lectures (12 weeks) + 24 Practical Sessions

Occurrence: Offered every summer semester 

Course Level: Master Students (Typically in their 1st or 2nd semester)

 

 

State estimation in autonomous UAVs, or flying robots, is a critical functionality. It allows a UAV to accurately localize itself and estimate the positions of a tracked target (from the UAV). Without robust state estimation, any of the other functionalities like planning, decision making and even low-level control can be jeopardized. The goal of this course is to provide students with a deep understanding of Bayesian estimation techniques and how they can be applied for UAV state estimation and target tracking. Students should be able to appreciate parametric ad non-parametric forms of estimation and their pros and cons. Finally, they should be able to implement various Bayesian filters for online applications, both in simulation and in a real UAV.

 

Lecture Contents

  • Bayesian filtering: Introduction to recursive state estimation, concept of Markov assumption and basic Bayes filter.
  • Sensor models:
        * Probabilistic sensor models: e.g., laser range finders, RGB cameras.
        * Modeling raw sensor measurements and feature-based approaches.
        * Overview of camera projection models e.g., perspective, equidistant, etc.
        * Barometric pressure based altitude sensors.
        * Differential pressure airspeed sensors     
  • Motion and Sensor models:
        * Probabilistic approaches to robot motion modeling
        * Velocity motion model
        *  Fixed wing UAV with dead reckoning
  • Parametric filters: (Extended) Kalman filter and Information filter
        * Basics of KF, EKF, derivation, assumptions and properties.
        * Canonical representations, their advantages, Information filter (IF) and extended versions. Overview of related state-of-the-art techniques.
  • Non-Parametric filters: Histogram filter and Particle filter and variants
        * Why non-parametric filters? Advantages (multiple modalities, nonlinearities) and Disadvantages (curse of dimensionality). Discretization and Histogram filtering.
    * Particle filters (PFs): concepts and properties. Discussion of state-of-the-art PF-based methods.

Practical Contents

 

  • [Topic 1] Introduction to to ROS, Gazebo and Python
  • [Topic 2] Intro to ‘how to use our UAV environment’ and code a node — Sensors.
  • [Topic 3] State estimation and control -- Code ROS nodes for UAV localization using on-board IMU and simulated GPS
  • [Topic 4] Visual Tracking -- Code ROS node to track the state of a moving target from a UAV.

Flight Robotics Seminar (Seminar + Practical)

Format: 12 sessions (12 weeks) including seminars, tutorials, UAV building sessions, student presentations and a final flight demonstration

Occurrence: Offered every semester (summer and winter)

Course Level: Bachelor Students (Typically in their 4th or 5th semester)

 

  • Learn how to implement a controller
  • Learn how to build a quadcopter

 

Contents

The goal of this course is to give Bachelor students their first hands-on experience in aerial robotics. They will learn how to design, implement and analyse controllers and estimators. Moreover, they will learn how to design and build their own quadcopter robot and measure its system parameters. Additionally, the students will be introduced to the ROS programming environment, Gazebo and Matlab as well as the interfaces between them. The students will also receive training on how to use a motion capture system and fly their vehicle in a hall instrumented with such a system. Grading will be done based on a homework assignments and a presentation, which students have to prepare in groups of 1-2, on a topic such as attitude control, state estimation, etc.

Applied Machine Learning for Engineers (Lecture + Project)

Format: 24 Lectures (12 weeks) + 24 Tutorials Sessions.

Occurrence: Offered every winter semester

Course Level: Master Students (Typically in their 3rd or 4th semester)

 

  • Students learn to use common libraries and apply ML algorithms to various engineering problems, especially in the aerospace domain.
  • Students learn to critically evaluate the results obtained through the application of ML methods.

 

Contents

In this course, Machine Learning algorithms are applied to problems arising in aerospace engineering. Lecture topics include:

  • Introduction to Python and ML packages
  • Basics of linear algebra, statistics and optimization
  • Reinforcement learning
  • Model Order Reduction (PCA, t-sne, ...)
  • Data preparation
  • Regression and classification
  • Artificial Neural Networks

Main tools used are Python, scikit-learn, PyTorch and TensorFlow (Keras).