TU Delft
Year
print this page print this page     
NEDERLANDSENGLISH
Organization
2016/2017 Aerospace Engineering Master Aerospace Engineering
AE4317
Autonomous Flight of Micro Air Vehicles
ECTS: 4
Responsible Instructor
Name E-mail
Dr. G.C.H.E. de Croon    G.C.H.E.deCroon@tudelft.nl
Instructor
Name E-mail
Ir. C. de Wagter    C.deWagter@tudelft.nl
Contact Hours / Week x/x/x/x
0/0/4/0
Education Period
3
Start Education
3
Exam Period
3
4
Course Language
English
Expected prior knowledge
Programming experience (any language)

If the student has no previous background in C / C++, we expect the student to do an online tutorial before / at the beginning of the course. For example: http://www.e-reading.link/bookreader.php/135186/Sams_Teach_Yourself_C_in_21_Days,_6th_Edition.pdf

Desired prior knowledge:
Programming experience with C / C++
AE4393 (Avionics and Operations)
Course Contents
This course covers the challenges and existing state-of-the-art methods for enabling autonomous flight of Micro Air Vehicles (MAVs), ranging from 20-gram flapping wings.to 1 kg quad rotors. The emphasis is on computationally efficient, bio-inspired approaches to MAV autonomous flight.

The theoretical knowledge will be applied by the students in the practical assignment, in which student groups program quad rotors in order to avoid obstacles in TU Delft's Cyberzoo.
Study Goals
(1) Students can explain the differences between MAVs and larger aircraft in terms of control, design, aerodynamics, and electronics.
(2) Students can explain how the above-mentioned differences affect the task of achieving autonomous flight with MAVs.
(3) Students can list and explain Artificial Intelligence (AI) and control techniques useful for autonomous flight of Micro Air Vehicles (MAVs).
a) Bio-inspired robotics
b) Vision-based navigation
c) Evolutionary robotics
d) Swarm robotics
(4) Students can apply the learned AI and control techniques to, and create new algorithms for an autonomous flight task.
(5) Students can reproduce the current state of regulations for MAV operations. In addition, they can assess and discuss on the safety and ethical aspects of MAV operations.
Education Method
The course will consist of theory (7 lectures) and a practical assignment (6 practical sessions and a competition session).
Brief description practical assignment:
Student teams will develop an efficient, purely vision-based approach to autonomously navigate through an obstacle field. The algorithm will have to run onboard the Parrot AR drone 2, a commercially available quad rotor equipped with a range of sensors. Importantly for the project, it has a single frontal camera. Hence, the developed algorithm concerns a monocular vision solution to obstacle avoidance.
Assessment
The assessment of the course will consist for 50% of the theoretical exam, and 50% of the practical assignment. Assessment of the practical assignment is based on the performance of the drone on the task, the followed approach as explained in a presentation, and the code produced by the team.