From Video Game to Real Robot

Tablet Copy 4Created with Sketch.

Can you train a deep learning agent in video game and then transfer this learned information to a real world robot?

Tablet Copy 4Created with Sketch.

How can we handle the differences in visuals and action spaces between the game and reality?

These questions are researched in our conference article, “From Video Game to Real Robot: The Transfer Between Action Spaces”, which was kindly accepted to ICASSP 2020 conference. The research work was conducted while I was working at University of Eastern Finland and is continuation for my master’s thesis.

Check our conference presentation below!

Janne Karttunen
Janne Karttunen

Driven by my fascination with robotics and AI, I decided to specialize in deep learning and robotics research during my Master's degree studies at the University of Eastern Finland. In early 2020, I started my journey with Karelics, where I have had the pleasure to witness our growth story from the very beginning. It has been exciting to develop and integrate core robotics functionalities using ROS from the low level hardware drivers, to safe autonomous navigation, advanced mapping and localization systems, cloud integration and efficient task management solutions. I'm grateful to be part of a team which is in the forefront of building the future with robots.

All Posts