Researchers from the Massachusetts Institute for Technology (MIT)’s Computer Science and Artificial Intelligence Laboratory (CSAIL) and Columbia University, USA, have developed a new CAD plug-in which is reported to allow designers to interactively edit, improve and optimise models using a more streamlined and intuitive workflow.
Traditional CAD systems are parametric, meaning that parameters like shape and size are changed based on different priorities (such as airflow vs energy generation for a wind turbine). According to MIT’s researchers, the range of modification options available can make it difficult to determine the best design for the required purpose.
In addition, this process can be very time-consuming, as changing a single property requires a complete regeneration, re-simulation and analysis of the model.
In a paper published by MIT’s Adriana Schulz, Jie Xu, Bo Zhu and Wojciech Matusik, and Columbia’s Changxi Zheng and Eitan Grinspun, the team stated that InstantCAD is capable of improving and optimising designs in real-time, saving days or weeks of regenerations and re-simulations. With InstantCAD, after an object is designed in a commercial CAD program, it is sent to a cloud platform where multiple geometric evaluations and simulations are run simultaneously.
With this precomputed data, the researchers state that users can instantly improve and optimise designs in two ways: using ‘interactive exploration’, a user interface provides real-time feedback on how design changes may affect performance, such as how the shape of a plane wing will impact on air pressure distribution. With ‘automatic optimisation’, the system automatically generates a design with specific characteristics, such as a drone that is as lightweight as possible while still being able to carry a heavy weight.
“From more ergonomic desks to higher-performance cars, this is really about creating better products in less time,” stated Schulz. “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.”
One of the key benefits of InstantCAD is its ability to analyse large, complex designs with an enormous number of potential design options based on just a small number of sampled data points. “It’s too data-intensive to compute every single point,” added 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.”
The research team also expressed its hope that the plugin will help lower the barrier for entry into Additive Manufacturing for casual users. “In a world where 3D printing and industrial robotics are making manufacturing more accessible, we need systems that make the actual design process more accessible, too,” she stated. “With systems like this that make it easier to customise objects to meet your specific needs, we hope to be paving the way to a new age of personal manufacturing and DIY design.”