Autonomous Navigation for Flying Robots

Dr. Jürgen Sturm and Dr. Daniel Cremers

Technische Universität München

In recent years, flying robots such as miniature helicopters or quadrotors have received a large gain in popularity. Potential applications range from aerial filming over remote visual inspection of industrial sites to automatic 3D reconstruction of buildings. Navigating a quadrotor manually requires a skilled pilot and constant concentration. Therefore, there is a strong scientific interest to develop solutions that enable quadrotors to fly autonomously and without constant human supervision. This is a challenging research problem because the payload of a quadrotor is uttermost constrained and so both the quality of the onboard sensors and the available computing power is strongly limited.

In this course, we will introduce the basic concepts for autonomous navigation for quadrotors. The following topics will be covered:

3D geometry,
probabilistic state estimation,
visual odometry, SLAM, 3D mapping,
linear control.

In particular, you will learn how to infer the position of the quadrotor from its sensor readings and how to navigate it along a trajectory.

The course consists of a series of weekly lecture videos that we be interleaved by interactive quizzes and hands-on programming tasks. For the flight experiments, we provide a browser-based quadrotor simulator which requires the students to write small code snippets in Python.

This course is intended for undergraduate and graduate students in computer science, electrical engineering or mechanical engineering. This course has been offered by TUM for the first time in summer term 2014 on EdX with more than 20.000 registered students of which 1400 passed examination. The MOOC is based on the previous TUM lecture “Visual Navigation for Flying Robots” which received the TUM TeachInf best lecture award in 2012 and 2013.

key words, tags

quadrotors, autonomous navigation, robots

Course properties

Competition track
Science and engineering
Form of education
Learning language
Engineering, manufacturing and construction, Information and Communication Technologies (ICTs)
Course authors
Dr. Jürgen Sturm and Dr. Daniel Cremers
Technische Universität München
Output knowledge, abilities, skills
After successful participation of this module, students will be able to 1.) understand the flight principles of quadrotors and their application potential, 2.) specify the pose of objects in 3D space and to perform calculations between them (e.g., compute the relative motion), 3.) explain the principles of Bayesian state estimation, 4.) implement and apply an extended Kalman filter (EKF), and to select appropriate parameters for it, 5.) implement and apply a PID controller for state control, and to fine tune its parameters, 6.) understand and explain the principles of visual motion estimation and 3D mapping
Entrance test
Groups formation by readiness level
Teachers presence
Tutors presence
Facilitators presence
Training materials forms
texts, multimedia, presentation, quiz questions
Interactivity in training materials
Collaborative learning presence
Practical activities
coursework, project
Discussions, forums presence
Webinars, video conferences presence
meetup presence
LMS integration
Learning Analytics
Certification presence
Certification types
edX Honor Code Certificate, edX Verified Certificate
Course time limits
8 (weeks)
Learning types (sync/async)
Assessment types
Personal learning path possibility, course individualization
Operating System
Windows, Mac, Linux
Supported browsers
All standard browsers (Safari, Firefox, Chrome, Internet Explorer)
Special needs support