[robotics-worldwide] [jobs] Ph.D. position on "Drones learning how to autonomously exploit updrafts"

guido_de_croon g.c.h.e.decroon at tudelft.nl
Wed Dec 11 10:54:56 PST 2019

The Faculty of Aerospace Engineering  of Delft University of Technology, the
Netherlands, announces a vacancy for one *Ph.D. student* within the project:  

*Learning how to autonomously exploit updrafts*

/Description of the project: /

Birds exploit various types of updrafts in their environment in order to
save energy when flying. Birds of prey use thermals to gain height, pigeons
use updrafts around hills and buildings, while albatrosses use dynamic
soaring over the waves of the sea.

The primary goal of this PhD project is to provide Micro Air Vehicles (MAVs)
with similar updraft exploitation capabilities. In order to achieve
autonomous exploitation of updrafts, MAVs will have to perceive the airflow,
the structure of the environment, and their own movement. Moreover, they
need to be able to perform control that minimizes energy expenditure,
preferably by learning to do so in their own environment.

The project entails demonstrating autonomous updraft exploitation strategies
in the real world, flying in updrafts around ships (with preliminary tests
over dunes, and perhaps final tests in urban areas). Hence, the project
involves elaborate outdoor flight testing besides the development of new
perception and learning strategies in theory and simulation.  

The project will be carried out within the MAVLab
(https://urldefense.proofpoint.com/v2/url?u=http-3A__mavlab.tudelft.nl_&d=DwIFaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=FjY0Q9t5M3CpxJzpJtm1ly2-eoC0XpZOQ77eOJcxCIs&s=LxUYvCVf2loLRRjRiZ4Zc1CLGJKKlM1m04LPQ4rJc_A&e= ), which is part of the Control and Simulation
section of the Faculty of Aerospace Engineering. The MAVLab investigates the
design and control of novel types of MAVs, such as the DelFly (a 16-gram
flapping wing MAV) [1] and the DelftaCopter (a hybrid MAV that has both a
wing and a helicopter blade) [2]. In terms of control, the MAVLab has
experience both with “traditional” control methods ranging from low-level to
high-level control loops and with machine learning – ranging from
evolutionary robotics to self-supervised learning. The proposed position
will involve the learning of control by a fixed wing and / or hybrid MAV.
The study will have a big experimental component, testing out the
developments in a real-world environment. The supervisors will be dr. Guido
de Croon, ir. Bart Remes, and ir. Christophe De Wagter from the Micro Air
Vehicle Laboratory. 

/What do we ask? /

We are looking for a candidate with an MSc degree in an area such as
Robotics, Aerospace Engineering, Artificial Intelligence, Computer Science,
Mechatronics, Control Systems Theory, or a similar field. The candidate is
expected to be passionate about developing autonomous robots, not only
focusing on the AI or control algorithms, but also on hands-on development
and flight testing. Programming experience is required in Matlab/Python
and/or C/C++. It is very much appreciated if the candidate has experience
working with or designing electronics and / or drone hardware.

Previous experience with robotic or mechatronic systems and their control is
an asset. Please note that the Ph.D. candidate will work within a team with
ample experience in design and prototyping of tiny drones, autopilots (in
particular Paparazzi) and micro-electronics as well as with bio-inspired
artificial intelligence and control. The candidate must have strong
analytical skills and must be able to work at the intersection of several
research domains (artificial intelligence, control, mechatronics, mechanical
design, aerospace). A very good command of the English language is required,
as well as excellent communication skills. 

/What do we offer? /

We offer the opportunity to do scientifically challenging research in a
multi-disciplinary research group. The appointment will be for a period of 4
years. As an employee of the university you will receive a competitive
salary, as well as excellent secondary benefits in accordance with the
Collective Agreement (CAO) of the Association of Universities in the
Netherlands (VSNU). Your gross salary in the first year will be according to
the first step of the standard Dutch salary scale for a PhD candidate, which
is currently € 2,325.00 gross per month (approximately € 1,856.00 net)
excluded the 30% rule. In the second year, your salary will be increased to
€ 2,709.00 gross. This salary is to increase further in your third and
fourth year. Assistance with accommodation can be arranged.

/How to apply? /

*Submit your application to Bertine Markus *(email: b.m.markus at tudelft.nl )
*before December 18, 2019 *with “Updraft exploitation” in the subject.
Include a cover letter along with a detailed curriculum vitae, a separate
motivation letter stating why the proposed research topic interests you,
electronic links to or copies of a few selected publications (if
applicable), an overview (photos / videos) of possible “hobby projects” in
the area of robotics / drones, the summary of your MSc thesis, your MSc and
BSc course programs and the corresponding grades, names and addresses of two
to three reference persons, and other information that might be relevant to
your application. Job interviews will take place from January 5 – January 10


[1] De Croon, G. C. H. E., Perçin, M., Remes, B. D. W., Ruijsink, R., & De
Wagter, C. (2016). The DelFly. Berlin: Springer Netherlands.
[2] De Wagter, C., Ruijsink, R., Smeur, E. J., van Hecke, K. G., van Tienen,
F., van der Horst, E., & Remes, B. D. (2018). Design, control, and visual
navigation of the DelftaCopter VTOL tail‐sitter UAV. Journal of Field
Robotics, 35(6), 937-960.

Sent from: https://urldefense.proofpoint.com/v2/url?u=http-3A__robotics-2Dworldwide.1046236.n5.nabble.com_&d=DwIFaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=FjY0Q9t5M3CpxJzpJtm1ly2-eoC0XpZOQ77eOJcxCIs&s=IfKsZJ0BR1XrFDErBizJtW-UGXRNwOcKpeDHFISu_OA&e= 

More information about the robotics-worldwide mailing list