image accueil du bandeau la rubrique
Learning to fly


Vous êtes ici : Learning to fly » Learning to Fly

Learning to Fly

D 23 février 2017    

L2F enables an Autonomous soaring glider to remain as long as possible in the air by benefiting from artificial intelligence, which allows to control the gilder in a way to benefit from current thermals.

In this website we will present the project in different headings
- People : people involved in the project (Researchers and students)
- Publications : Contains scientific publications related to the project.
- Software : Contains a detailed description of the demonstrator as well as an explanation to how the code can be downloaded and its documentation accessed.
- Demo : Contains an example of simulation and its results.

What is L2F ?

LearningToFLy(L2F) aims at increasing the autonomy of a stand-alone glider and improve energy efficiency by benefiting from thermals. For this, we use artificial intelligence, more precisely reinforcement learning base on a Q-learning algorithm that tries to maximize the expectations of rewards. Hence, our glider will be able to stay as long as possible in the air

Who’s in charge of the project ?

LearningToFly is as project that has involves many people over the years. Researchers and students have contributed to the progress of this project. Most of student involved are from ISAE-Supaero a prestigious engineering school that deals mainly with aeronautics. Therefore, they were able to highlight their scientific know-how not only in the field of flight mechanics but also in the field of machine learning.

Project progress

At this stage, all our results are simulations on computer, this allows to test different models of control and thermals. Initially, the simulator was coded under Matlab, but for performance reasons, it was decided to recode it under C++, a detailed description of our demonstrator is available in the section « Software ». A more visual simulation of our demonstrator is disposable in the section “Demo”.