MIT Researchers Develop Tool to Simplify Product Design

Designing a product is a complicated task fraught with many trade-offs, including cost, reliability, manufacturability, weight and aesthetics. Changing one parameter can directly affect another—either positively or negatively—and so product designers must find the optimum combination that leads to a viable and economically sound product.

Traditionally, a number of tools have been used for this process, including CAD, material selection software (such as CES Selector) and various simulation packages. Some folks still use tables, pen and paper—even in the 21st century!

The good news for product designers is that researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) have published a paper describing a visualization tool for CAD that allows users to interactively explore all design options that best fit multiple, often-conflicting performance trade-offs, in real time.

To achieve this, the research team has combined multi-objective optimization techniques with a CAD platform, named “InstantCAD,” that was developed by the team in-house.

One important aspect of multi-objective optimization is the so-called “Pareto front,” which represents a set of designs that are optimized for all given performance objectives, where any design change that improves one objective worsens another.

In the CAD software, the Pareto front is represented by a point cloud where each point is a separate design. For example, one point may represent a tool that is optimized for stiffness and less mass, while a nearby point will represent a design that has been optimized for less stiffness but more mass. Moving around the Pareto space will show real-time designs that correspond with the location within the front, as you can see in the lamp design image above.

“Now you can explore the landscape of multiple performance compromises efficiently and interactively, which is something that didn’t exist before,” said Adriana Schulz, a CSAIL postdoctoral researcher and lead author on the paper.

“We’re directly editing the performance space and providing real-time feedback on the designs that give you the best performance. A product may have 100 design parameters … but we really only care about how it behaves in the physical world,” Explained Schulz.

In the past, when using CAD to find these Pareto-optimized designs, engineers would rely on intuition and a certain amount of guesswork. Then they would use the front’s visual representation as a guideline to find a product that met a specific performance.

Now, with the new tool from the research team, engineers can discover the entire Pareto front and turn it into an interactive map. Clicking on the map will display optimized designs, as well as show the variations in the immediate locale of that section of the front.

“This work is an important contribution to interactive design of functional real-world objects,” said Takeo Igarashi, a professor of computer science at the University of Tokyo and an expert in graphic design. “The tools work as black box and allow no or limited user control,” he explained. “This work explicitly addresses this not-yet-tackled important problem.… [It] builds on a solid technical foundation, and the ideas and techniques in this paper will influence the design of design tools in the future.”