Persönlicher Status und Werkzeuge

Home Teaching Summer Semester 2015 Autonomous Navigation for Flying Robots (EdX course, 2 ECTS)

Autonomous Navigation for Flying Robots (EdX course, 2 ECTS)

In this course, we will introduce the basic concepts for autonomous navigation with quadrotors, including topics such as probabilistic state estimation, linear control, and path planning.

About this course

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 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 including topics such as probabilistic state estimation, linear control, and path planning. You will learn how to infer the position of the quadrotor from its sensor readings, how to navigate along a series of waypoints, and how to plan collision free trajectories. The course consists of a series of weekly lecture videos that we be interleaved by interactive quizzes and hands-on programming tasks. The programming exercises will require you to write small code snippets in Python to make a quadrotor fly in simulation.

This course is intended for graduate students in computer science, electrical engineering or mechanical engineering. The course is based on the TUM lecture “Visual Navigation for Flying Robots” which received the TUM TeachInf best lecture award in 2012 and 2013.

Organization

The lecture will be given by Dr. Jürgen Sturm and Prof. Dr. Daniel Cremers. The teaching assistant is Christian Kerl.

Enrollment: Via EdX website.

Classes Start: 28 April 2015

Course Length: 8 weeks

Estimated effort: 6 hours/week

ECTS: 2 ECTS

Course Dates

Date Topic
28.4.2015 Kickoff meeting in room 00.12.019, 14:00-16:00 pdf
5.5.2015 Lecture 1: Introduction
12.5.2015 Lecture 2: Linear Algebra and 2D Geometry
19.5.2015 Lecture 3: 3D Geometry and Sensors
26.5.2015 Lecture 4: Actuators and Control
2.6.2015 Lecture 5: Probabilistic State Estimation
9.6.2015 Lecture 6: Kalman Filter
16.6.2015 Lecture 7: Visual Odometry
23.6.2015 Lecture 8: Visual SLAM and 3D Reconstruction
30.6.2015 + 1.7.2015 Oral Exam

Note: Please contact Sabine Wagner for the assignment of a time slot for the oral exam.

Course Material

Topic Video Handout
Lecture 1.1 Welcome mp4 pdf
Lecture 1.2 Why Quadrotors? mp4 pdf
Lecture 1.3 Flying Principle mp4 pdf
Lecture 1.4 Brief History on Quadrotor Research mp4 pdf
Lecture 2.1 Recap on Linear Algebra mp4 pdf
Lecture 2.2 2D Geometry mp4 pdf
Lecture 2.3 2D Robot Example mp4 pdf
Lecture 3.1 3D Geometry mp4 pdf
Lecture 3.2 Sensors mp4 pdf
Lecture 4.1 Motors and Controllers mp4 pdf
Lecture 4.2 Feedback Control mp4 pdf
Lecture 4.3 Kinematics and Dynamics mp4 pdf
Lecture 4.4 PID Control mp4 pdf
Lecture 5.1 State Estimation mp4 pdf
Lecture 5.2 Recap on Probability Theory mp4 pdf
Lecture 5.3 Reasoning with Bayes Law mp4 pdf
Lecture 6.1 Bayes Filter mp4 pdf
Lecture 6.2 Kalman Filter mp4 pdf
Lecture 6.3 EKF Example mp4 pdf
Lecture 7.1 2D Motion Estimation in Images mp4 pdf
Lecture 7.2 Visual Odometry mp4 pdf
Lecture 8.1 Visual Navigation with a Parrot Ardrone mp4 pdf
Lecture 8.2 Tracking and Mapping using Signed Distance Functions mp4 pdf
Lecture 8.3 Direct Visual SLAM mp4 pdf
Last edited 25.06.2015 10:25 by sturmju