Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.
Safe Unsupervised Learning for Drone Perception and Control
In this project, we aim to build a system to let a drone learn how to fly in a very agile manner by integrating the knowledge of classical robotics into a neural network.
Supervised learning is the gold standard algorithm to solve computer vision tasks like classification, detection or segmentation.
However, for several interesting tasks (e.g. control of a drone, etc.) collecting a large annotated datasets is a very tedious and costly process.
In this project, we aim to build a system to let a drone learn how to fly aggressively in a complex environment by letting the drone interact with its surroundings in a safe way.
**Requirements**: Computer vision knowledge; programming experience with python. Machine learning knowledge is a plus but it is not required.
Supervised learning is the gold standard algorithm to solve computer vision tasks like classification, detection or segmentation.
However, for several interesting tasks (e.g. control of a drone, etc.) collecting a large annotated datasets is a very tedious and costly process.
In this project, we aim to build a system to let a drone learn how to fly aggressively in a complex environment by letting the drone interact with its surroundings in a safe way.
**Requirements**: Computer vision knowledge; programming experience with python. Machine learning knowledge is a plus but it is not required.
The goal of this project consists of building a system which can control a drone in complex environments.
The goal of this project consists of building a system which can control a drone in complex environments.