I was a research assistant under the supervision of Prof. Sara McMains at UC Berkeley. Our project was to construct a 3D model database for training a supervised machine learning algorithm that can determine the best FDM printing orientation. I wrote the pipeline that sources engineering-related models from Thingiverse with a Creative Commons license, rotates the object into various orientations, and uploads them to Google Drive which can be accessed through the backend of our database website.

In total, my program helped collect over 570000 models and is continuing to add new models to our database.

I am the second author of a journal paper that is currently under review and will explain the details of our work.

The source code can be found on my GitHub page: https://github.com/itschendai/autostlpipeline