ARCANE ALGEBRA
Promoting learning through VR games
Arcane Algebra is a first-person VR game designed for students who are beginning to learn basic algebraic operators (Addition, Multiplication, and Subtraction).
Using their controller as a wand, players cast mathematical spells to defeat the group of angry goblins attacking the village.

June 2022 -
Sept. 2022
4 Months

Oculus VR
Unity 3D
Blender
ONNX ML

Assets from Unity Asset Store

Solo Project
SYSTEM DESIGN
From my experience playing education games growing up, it has always felt like there is a lot of room for improvement. An example of this is Math Agar, a reskinned version of the popular web game agar.io. Compared to the original game, Math Agar adds a math question on the every of each players screen. By eating special orbs with the answer to your math question, players can gain gain extra mass, while eating an incorrect answer will lose mass instead.
While this may be fun for the first few minutes, it quickly becomes apparent that Math Agar isn’t really an educational game. You’re not playing a Math game, you’re just playing a game and also doing mathematics on top of it. There isn’t any integration between the two.
I created Arcane Algebra as an attempt to integrate Mathematics education in a fun and engaging way for players. I did this by utilizing the 3D drawing capabilities of the Oculus Quest 2, allowing my players to feel like “mathemagical wizards”.
Players have to fight hordes of goblins by using their magical wand to draw out solutions to basic arithemtic problems.

MACHINE LEARNING


For Arcane Algebra, I wanted to utilize the immersive capabilities of VR to make players feel powerful while writing out their solutions. To do this, I used a convolutional neural network model trained on the MNIST dataset, to parse hand-written digits.
When given a 26x26 greyscale image of a number, the model will return a confidence value of what that number might be. By finding the value with the highest confidence interval, we can fairly accurately interpret a user’s handwriting.
I did initially run into a lot of issues with the accuracy of the model, despite it having a 99% accuracy rate with the training data. I intended on disguising this inaccuracy as an “unstable spell”, which would occur when the model did not meet a certain level of confidence for a number. When players cast an unstable spell, the monster they were facing would be sent backwards, giving them additional time to try writing their solution again.
With guidance from some of my peers, I found that this inaccuracy was caused from the way my images were being created. While the images I was feeding the model had thick lines and often took up the whole image, the training dataset always had the image centered and written with very thin lines. This difference in how the data was presented caused the model to behave unpredictably. Yet, it was resolved by adding some padding and decreasing the stroke width of the drawings.
TRY IT OUT!
Using Arthur Guiot's MNIST Model
Scanning handwriting for numbers is a problem that has been studied very robustly in the field of Machine Learning. As such, a fairly competent trained network can be ran inside a web browser like the one you’re using right now!
To the left is a MNIST model that has had all of its matrix operations loaded into the browser.
Feel free to try it out!
PLAYTESTING
Update - March 2023
I'm currently reaching out to VR Educators to provide them with some builds of Arcane Algebra.
I'd love to further develop the project and release it onto the Oculus Store!