Anyone who designs components for 3D printing almost inevitably ends up using traditional CAD software – and with it a steep learning curve. Thousands of commands, nested menus, and complex workflows make it difficult for beginners to quickly arrive at printable 3D models. A team at MIT is now inserting an AI layer between sketch and CAD program that partially takes over interaction with the software.
At the core of the work is the VideoCAD dataset with more than 41,000 recorded CAD sessions. Instead of storing only the high-level commands used, such as “Line”, “Circle” or “Extrude”, the researchers log all UI actions: mouse clicks, drag motions, tool changes, and zooms. From these sequences, a model learns to operate a CAD interface in a human-like way and to generate a 3D solid model step by step from a 2D sketch – from a simple bracket to more complex geometries.
“There’s an opportunity for AI to increase engineers’ productivity as well as make CAD more accessible to more people,” says Ghadi Nehme, a graduate student in MIT’s Department of Mechanical Engineering.
“This is significant because it lowers the barrier to entry for design, helping people without years of CAD training to create 3D models more easily and tap into their creativity,” adds Faez Ahmed, associate professor of mechanical engineering at MIT.
For 3D printing applications, this is directly relevant: The quality of the STL or STEP file strongly depends on how cleanly sketches, constraints, and extrusions are set up. A “CAD co-pilot” could automate repetitive operations, derive variants of a part, or suggest typical preparations for printing – such as adding chamfers, radii, or reinforcing ribs.
“For example, let’s say we drew a sketch by drawing a line from point 1 to point 2,” Nehme says. “We translated those high-level actions to user-interface actions, meaning we say, go from this pixel location, click, and then move to a second pixel location, and click, while having the ‘line’ operation selected.”
“VideoCAD is a valuable first step toward AI assistants that help onboard new users and automate the repetitive modeling work that follows familiar patterns,” says Mehdi Ataei, who was not involved in the study, and is a senior research scientist at Autodesk Research, which develops new design software tools. “This is an early foundation, and I would be excited to see successors that span multiple CAD systems, richer operations like assemblies and constraints, and more realistic, messy human workflows.”
In the short term, the technology is likely to end up primarily as a learning and automation tool in the design process. In the long term, 3D printing workflows could emerge in which a rough sketch is turned semi-automatically into a printable, parametric model – including the necessary detailed work in CAD.
Subscribe to our Newsletter
3DPresso is a weekly newsletter that links to the most exciting global stories from the 3D printing and additive manufacturing industry.
