In theory, 3-D printing gives consumers the ability to conceive of and make various products. But designing many objects requires specialized knowledge of geometry, materials, and manufacturing processes. Researchers at PARC are now building software tools meant to automate that kind of judgment. The goal, says PARC CEO Stephen Hoover, is to build programs that enable non-experts to “kind of think their way through a design space” before sending any instructions to the printer.
Participants in a growing online community of enthusiasts have already uploaded hundreds of thousands of designs for 3-D-printed objects. The problem is that in conventional production settings, manufacturing engineers who are well versed in the design constraints imposed by specific materials and manufacturing methods “eliminate a whole set of choices at the beginning because they know what can cause problems down the road,” says Hoover (see “The Difference Between Makers and Manufacturers”). That doesn’t necessarily happen in the world of 3-D printing.
For an example of the type of constraint that can cause problems for novice designers, look at the thermoplastics used by popular consumer 3-D printers, says Tolga Kurtoglu, who runs PARC’s design and digital manufacturing program. Each material has a minimum thickness; at any one point within an object, it must be that thick for the object to support itself. This does not necessarily mean designs that fail to comply with this constraint can’t be printed, says Kurtoglu, but they are more likely to encounter problems like distortion or warping.
The first system Kurtoglu’s group has built draws on libraries containing the specifications of standard 3-D printers on the market, information about the materials each can handle, and basic information about material properties. Armed with this information, the tool can assess the feasibility of printing a given design on a specific type of printer. It compares the geometric features of the design with the parameters dictated by the printer and material. It then simulates layer-by-layer production of the proposed object to expose problematic areas. It can recommend changes to the fabrication approach to make sure that the printed object ends up the way the designer intended.
PARC is also working on a similar tool that, instead of using data about 3-D printers, would draw on detailed information about the capabilities and limitations of contract manufacturers. Simulating the production of a newly designed part at different facilities could reveal which ones are most capable of making that part, and at what cost.
The dark secret behind those cute AI-generated animal images
Google Brain has revealed its own image-making AI, called Imagen. But don't expect to see anything that isn't wholesome.
The hype around DeepMind’s new AI model misses what’s actually cool about it
Some worry that the chatter about these tools is doing the whole field a disservice.
The walls are closing in on Clearview AI
The controversial face recognition company was just fined $10 million for scraping UK faces from the web. That might not be the end of it.
This horse-riding astronaut is a milestone in AI’s journey to make sense of the world
OpenAI’s latest picture-making AI is amazing—but raises questions about what we mean by intelligence.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.