| KEYWORD |
Sheltering factor zone recognition for UAVs via machine learning
keywords MACHINE LEARNING, RISK ANALYSIS, SAFETY, UAV
Reference persons GIORGIO GUGLIERI, ALESSANDRO RIZZO
Research Groups SYSTEMS AND DATA SCIENCE - SDS
Thesis type SIMULATIONS AND DESIGN
Description The use of unmanned aerial vehicles (UAV) in urban environments requires to consider
risk, one way is through the generations of risk maps. These maps can be provided to
the path planning modules to generate way points to the UAV control system. One of
these values is the sheltering factor [1], obtainable through aerial images. The purpose
of this proposal is to create a tool utilizing machine learning and aerial photography,
calculates the proper sheltering factor, which is necessary to obtain the maps. The
system is developed for be implemented in cloud-computing strategy [2].
Objectives
1. Develop a model based on aerial photo database through machine learning approach
(Matlab).
2. Create an algorithm that generate the sheltering factor layer from an aerial photo
based (C++/ ROS).
References
[1] K. Dalamagkidis, K. Valavanis, and L. A. Piegl, On integrating unmanned aircraft
systems into the national airspace system: issues, challenges, operational restrictions,
certification, and recommendations, vol. 54. Springer Science & Business Media, 2011.
[2] S. Primatesta, E. Capello, R. Antonini, M. Gaspardone, G. Guglieri, and A. Rizzo,
“A cloud-based framework for risk-aware intelligent navigation in urban environments,”
in 2017 International Conference on Unmanned Aircraft Systems (ICUAS),
pp. 447–455, IEEE, jun 2017.
Required skills - Matlab
- C++
- ROS
Notes Please contact Dr Carlos Perez-Montenegro (carlos.perez@polito.it) for more information and a preliminary interview.
Deadline 04/10/2017
PROPONI LA TUA CANDIDATURA