A lot of fascinating research goes on at MIT’s Computer Science and Artificial Intelligence Lab (CSAIL). Just recently, we learned about the group’s work on the development of glasses-free 3D TV, and now they’re working on making CAD easier and faster. Making changes to computer aided designs can be frustrating and time-consuming, so CSAIL thought there must be a better way – and it came in the form of InstantCAD, a plug-in that streamlines the process of editing, improving and optimizing CAD models.
The development of the tool was documented in a recently published paper entitled “Interactive Design Space Exploration and Optimization for CAD Models.”
“From more ergonomic desks to higher-performance cars, this is really about creating better products in less time,” says CSAIL PhD student and lead author Adriana Schulz, who will be presenting the paper at this month’s SIGGRAPH computer-graphics conference in Los Angeles. “We think this could be a real game changer for automakers and other companies that want to be able to test and improve complex designs in a matter of seconds to minutes, instead of hours to days.”
The issue with CAD software is that while it’s parametric, meaning that parameters such as shape and size can be changed based on designers’ priorities, it’s not easy to determine the best design for the object because there are so many options. Changing even one property takes a lot of time, too – the new design has to be regenerated, then a simulation has to be run before the designer can see the result and figure out what the next step will be. The complexity is due to the design space being too large – there are just too many design options.
With InstantCAD, however, users can improve and optimize their designs in real time. Once an object is designed in CAD software, it’s sent to a cloud platform where multiple geometric evaluations and simulations are run at the same time. Then there are two options for the user to improve an optimize the design. “Interactive exploration” features a user interface that provides real time feedback on how design changes will affect performance, while “automatic optimization” allows the user to tell the system to provide a design with specific characteristics – like, for example, a drone that is as lightweight as possible while still being able to carry maximum weight.
“It’s too data-intensive to compute every single point, so we have to come up with a way to predict any point in this space from just a small number of sampled data points,” says Schulz. “This is called ‘interpolation,’ and our key technical contribution is a new algorithm we developed to take these samples and estimate points in the space.”
According to associate professor Wojciech Matusik, one of the authors of the paper, the tool could be especially useful for more intricate designs for things like cars, planes and robots, as well as other applications where manufacturers are trying to optimize performance as much as possible.
“Our system doesn’t just save you time for changing designs, but has the potential to dramatically improve the quality of the products themselves,” says Matusik. “The more complex your design gets, the more important this kind of a tool can be.”
Schulz believes that InstantCAD will have immediate applications for industry, but that it will eventually also prove useful for casual users looking to begin working with CAD.
“In a world where 3-D printing and industrial robotics are making manufacturing more accessible, we need systems that make the actual design process more accessible, too,” says Schulz. “With systems like this that make it easier to customize objects to meet your specific needs, we hope to be paving the way to a new age of personal manufacturing and DIY design.”
Additional authors of the paper include PhD student Jie Xu and postdoctoral associate Bo Zhu of CSAIL, as well as associate professor Eitan Grinspun and assistant professor Changxi Zheng of Columbia University. The work was supported by the National Science Foundation. Discuss in the InstantCAD forum at 3DPB.com.
[Photos: Rachel Gordon, MIT CSAIL]
