392206 ISY Project: Computer Vision for Autonomous Agents and Vehicles (Pj) (WiSe 2020/2021)

In this project will get an opportunity to build an AI agent in a simulated environment. All available topics for the project or a thesis are listed here:
https://docs.google.com/presentation/d/1eG0RGXnBiyXhFq1cepCRmcnyTB1VxuBQWkYoLbKc7jQ

Teilnahmevoraussetzungen, notwendige Vorkenntnisse

In the project, you will gain practical experience with Computer Vision for Autonomous Vehicles [1] in simulated environments, apply neural networks and computational approaches [2-3] to learn and produce complex purposeful actions in the context of one of the following environments on your choice [4-7]

[1] Udacity: https://www.udacity.com/course/computer-vision-nanodegree--nd891
[2] ORB-SLAM2: an Open-Source SLAM for Monocular, Stereo and RGB-D Cameras
https://www.youtube.com/watch?v=ufvPS5wJAx0
[3] YOLO COCO Object Detection
https://youtu.be/yQwfDxBMtXg
https://youtu.be/9s_FpMpdYW8
[4] Unity Obstacle Tower Challenge: https://youtu.be/owKdLnCjy3o
[5] Minecraft: https://www.aicrowd.com/challenges/neurips-2019-minerl-competition
[6] Doom: http://vizdoom.cs.put.edu.pl
[7] Autonomous Drone Navigation with Deep Learning
https://www.youtube.com/watch?v=H7Ym3DMSGms
Required skills:
Introduction to Neural Networks course or Advanced Neural Networks
Python or C++ (>= 1 year)