392265 ISY Project: Computer Vision for Autonomous Agents and Vehicles (Pj) (SoSe 2020)

In the project, you will gain practical experience with Computer Vision for Autonomous Vehicles [1] in simulated environments, apply neural networks and computational approaches [2-5] to learn and produce complex purposeful actions in the context of one of the following environments on your choice [6-9]

[1] Udacity: https://www.udacity.com/course/computer-vision-nanodegree--nd891
[2] CNN-SLAM: Real-time dense monocular SLAM with learned depth prediction
https://www.youtube.com/watch?v=z_NJxbkQnBU
[3] DSO: Direct Sparse Odometry
https://www.youtube.com/watch?v=C6-xwSOOdqQ
[4] ORB-SLAM2: an Open-Source SLAM for Monocular, Stereo and RGB-D Cameras
https://www.youtube.com/watch?v=ufvPS5wJAx0
[5] YOLO COCO Object Detection
https://youtu.be/yQwfDxBMtXg
https://youtu.be/9s_FpMpdYW8
[6] Unity Obstacle Tower Challenge: https://youtu.be/owKdLnCjy3o
[7] Minecraft: https://www.aicrowd.com/challenges/neurips-2019-minerl-competition
[8] Doom: http://vizdoom.cs.put.edu.pl
[9] Autonomous Drone Navigation with Deep Learning
https://www.youtube.com/watch?v=H7Ym3DMSGms
In case this would not find enough interest for a team project, this project proposal would be also offered (in reduced/modified form)
[x] as individual project 
[x] as project for 2-3 students

Teilnahmevoraussetzungen, notwendige Vorkenntnisse

Introduction to Neural Networks or Advanced Neural Networks courses.
Python or C++ ( > 1 year).