John Lygeros: Catalogue data in Autumn Semester 2021

Award: The Golden Owl
Name Prof. Dr. John Lygeros
FieldControl and Computation
Address
Institut für Automatik
ETH Zürich, ETL I 22
Physikstrasse 3
8092 Zürich
SWITZERLAND
Telephone+41 44 632 89 70
E-mailjlygeros@ethz.ch
URLhttp://control.ee.ethz.ch/people/profile.john-lygeros.html
DepartmentInformation Technology and Electrical Engineering
RelationshipFull Professor

NumberTitleECTSHoursLecturers
227-0085-21LProjects & Seminars: Quad-Rotors: Control and Estimation Restricted registration - show details
Only for Electrical Engineering and Information Technology BSc.

The course unit can only be taken once. Repeated enrollment in a later semester is not creditable.
2 credits2PJ. Lygeros
AbstractThe category of "Laboratory Courses, Projects, Seminars" includes courses and laboratories in various formats designed to impart practical knowledge and skills. Moreover, these classes encourage independent experimentation and design, allow for explorative learning and teach the methodology of project work.
ObjectiveThe objective of this P&S is to make a real-world quad-rotor fly autonomously by applying the control and estimation theory taught in class.
Details of this P&S course can be found at: http://www.dfall.ethz.ch/pands.php
A video showing highlights from HS2018 can be see here: http://www.youtube.com/watch?v=PEg-XHSXd58

In the first half of the P&S, we will introduce the physical model for a quad-rotor and use this to apply the control and estimation techniques that are taught in the 5th semester in the Control System 1 class. The students will then create their own control function for a quad-rotor and test these in simulation. The second half of the course will involve the students implementing the control and estimation algorithms they design in the real-world on our fleet of nano-quad-rotors. Once stable flight is achieved, the students will have the freedom to perform tasks with the quad-rotor. By implementing the control and estimation algorithms on a real-quadcopter, the students will gain experience with how decisions in the modelling and design stage affect real-world performance.

Important Information:
Students must be in the 6th semester.
The first class will be Monday, September 21 for all students.
Classes will then occur every second week. The students will be split into two groups and the classes for each group will occur on alternating weeks.
It is preferable to be taking the Control Systems 1 (CS1) course but not mandatory. Those students who are not taking CS1 will need to complete some extra reading to understand some aspects of this P&S.
Due to COVID-19, the course will be offered in an online setting with classes being held over Zoom. The students will be able to take a real-world quad-rotor to their homes in order to implement the control and estimation algorithms taught in the course.
227-0085-24LProjects & Seminars: Vision and Control in RoboCup Restricted registration - show details
Only for Electrical Engineering and Information Technology BSc.

The course unit can only be taken once. Repeated enrollment in a later semester is not creditable.
3 credits1PJ. Lygeros, L. Van Gool
AbstractThe category of "Laboratory Courses, Projects, Seminars" includes courses and laboratories in various formats designed to impart practical knowledge and skills. Moreover, these classes encourage independent experimentation and design, allow for explorative learning and teach the methodology of project work.
ObjectiveVision and Control in RoboCup is jointly offered by Prof. John Lygeros (IFA) and Prof. Luc Van Gool (CVL).

RoboCup is a tournament where teams of autonomous robots compete in soccer matches against each other. The ETH team NomadZ plays in the standard platform league with the humanoid NAO robot, where the focus lies on developing robust and efficient algorithms for vision, control and behavior. In this course, the basic challenges we encounter in RoboCup are presented and approached in practical exercises using MATLAB and Python. The topics cover visual localization, deep learning for object detection and reinforcement learning for control.

The course is offered to students of the 5th semester.
227-0920-00LSeminar in Systems and Control Information 0 credits1SF. Dörfler, R. D'Andrea, E. Frazzoli, M. H. Khammash, J. Lygeros, R. Smith
AbstractCurrent topics in Systems and Control presented mostly by external speakers from academia and industry
Objectivesee above
401-5850-00LSeminar in Systems and Control for CSE4 credits2SJ. Lygeros
Abstract
Objective