Affiliated project Deep4EnvMonitoring
Affiliated CEA Université d'Abomey-Calavi / SMIA & Université Gaston Berger / MITIC
Title: Design and integration of deep learning for adaptive and contextual control of unmanned aerial vehicles: application to environmental monitoring
Start date: 01/01/2021
Unmanned aerial vehicles (UAVs) are flying robots that are currently widely used in many military and civilian fields. They are an active research topic, attracting the interest of a wide community.
Drones can be used for environmental monitoring, waste detection, anarchic land use or precision agriculture, facilitating various analysis and control missions.
The aim of this work is to design flight plan and optimal trajectory generation algorithms for the localization and autonomous navigation of a drone dedicated to environmental monitoring (detection of illegal dumps, anarchic land use or precision agriculture).
Objectives / Expected results :
The Artificial Intelligence resulting from this work will be able to define a flight plan according to the problem (detection of illegal dumps, anarchic land use or precision agriculture).
It will be able to adapt the overflight altitude, definition and capture frequency, for example. In addition to the camera mounted on the drone, other ground-based sensors can also be used.
Contribution / added value to the affiliated project :
In this program, there is another thesis on evolutionary hyper network for convolutional neural networks (CNN). In collaboration with this thesis, the present thesis will adopt and apply the generalization of the evolutionary hyper network to UAV control in order to address different environmental monitoring problems.
Thesis director : Eugène EZIN, CEA SMIA, Benin
Thesis co-supervisor : Jean Marie DEMBELE, CEA MITIC, Senegal
Other contributors to thesis supervision :
Christophe CAMBIER, Sorbonne-Université - IRD
Cédric HERPSON, Sorbonne-Université - LIP6