MIT Libraries logoDSpace@MIT

MIT
View Item 
  • DSpace@MIT Home
  • MIT Libraries
  • MIT Theses
  • Graduate Theses
  • View Item
  • DSpace@MIT Home
  • MIT Libraries
  • MIT Theses
  • Graduate Theses
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Ally: Designing Interfaces for Human + AI Collaborative Creativity for Computer Aided Design (CAD) Applications

Author(s)
Chong, Isabelle
Thumbnail
DownloadThesis PDF (8.528Mb)
Advisor
Maes, Pattie
Terms of use
In Copyright - Educational Use Permitted Copyright MIT http://rightsstatements.org/page/InC-EDU/1.0/
Metadata
Show full item record
Abstract
Creativity is an essential component to design and is something that is seen as intrinsically human. As the world continues to become more and more digital, computers become ever more present in the world of creativity. However, the relationship between human and technology does not have to be adversarial. My research for Ally builds on the work of Paper Dreams, an adaptive drawing canvas platform with the objective of augmenting creativity using machine learning and multimodal inputs. In collaboration with PTC, Ally expands Paper Dreams, taking digitally drawn sketches using a Sketch-A-Net model or webcam images using a YOLOv5 model to recognize user input and build a Computer Aided Design (CAD) scene that has been collaboratively created by a human and an algorithm. The devised model is ultimately able to correctly identify the desired part for the user’s design in one of the top five most similar results at a rate better than by chance on a test set of possible user input data. Using the CAD capabilities of PTC Onshape and the Sketch-A-Net/YOLOv5 models, an extension to Paper Dreams has been built that will hopefully be usable in industry to create "digital twins" and allow humans and machines to design together.
Date issued
2022-05
URI
https://hdl.handle.net/1721.1/144948
Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Publisher
Massachusetts Institute of Technology

Collections
  • Graduate Theses

Browse

All of DSpaceCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

My Account

Login

Statistics

OA StatisticsStatistics by CountryStatistics by Department
MIT Libraries
PrivacyPermissionsAccessibilityContact us
MIT
Content created by the MIT Libraries, CC BY-NC unless otherwise noted. Notify us about copyright concerns.