In my life I created many, many, many projects. A lot of them can be found on youtube, my github page, or my LinkedIn page. If you are searching for project in a certain area: please let me know. This page features my own personal top-10.
When living in Paris I tried to learn the French language by using the website Duolingo, talking to people, reading books, and listening to music. Unfortunately it was difficult to find music that fitted my vocabulary at the time. To solve this problem I created the website http://duomusico.com/. Here you can enter your Duolingo username, and my server will search for songs that match your vocabulary in the language you are learning.
- Nao Karate teacher
- Brain viewer
- Teaching Mario
During the “Twitch plays pokemon” https://en.wikipedia.org/wiki/Twitch_Plays_Pok%C3%A9mon hype there were between 60.000 and 70.000 viewers watching and steering an agent playing the game Pokémon. If we could use all these human resources to train a machine learning algorithm we could achieve some great results.
The game I wanted to learn playing was Mario, because of the available open source platform, and the wide amount of existing solutions. In the end an existing reinforcement-learning implementation was used. The traditional problem with reinforcement-learning is that the agent chooses many actions that we as humans know will lead to the death of Mario. This was solved by letting the algorithm learn from the actions that a normal playing user would take. While the user played our game on a beamer the algorithm was constantly evaluating if their action was beneficial, and learned from it.
On the BNAIC 2014 conference this game was playable by everybody who downloaded an Android or Iphone app. During the conference the agent learned faster than without human input. My accepted paper can be found here: http://bnaic2014.org/?page_id=154 .
Personally I always felt that something “real” was missing when I saw people control a computer program using a Brain Computer Interface (BCI). Together with two friends we created an interface with our brain to control a small Sphero robot. The user can select the direction the ball has to roll in and its speed. By doing so he has to reach the four corners of a small area while avoiding obstacles.
Multi-touch painting program
In the first year of my studies we got the assignment of creating a painting program for the course “human computer interaction”. During the course we saw a video about a guy that created a touch-screen using a cardboard box. I created the same cardboard box and made my paint app multi-touch.
Flapping wing that autonomously flies through the hallway
During my time at the TU Delft I worked a lot with a small stereo camera board. This board was so light (only 3 grams) that it was possible to attach it to a “Delfly”. By programming the stereo cameras in a smart way it was possible to autonomously navigate through our hallway: hands off!
Automatically 3D printing keys
In 2013 I participated in a developers camp. With a group of four people we made a program that created a 3D version of a key requiring only a picture of the key and a picture of the lock.
Within a week we were able to refine this process such that we could take the two pictures, print the key, and immediately open the lock. As far as we know we were the first people in the world to 3D print keys. A video of the process can be found here:
Tracking and following Christmas presents
Predicting good places for fish stuff