Keyboard ALT + g to toggle grid overlay
Generative design mimics nature’s evolutionary approach to design. Designers or engineers input design goals into generative design software, along with parameters such as materials, manufacturing methods, and cost constraints. Then, using cloud computing, the software explores all the possible permutations of a solution, quickly generating design alternatives. It tests and learns from each iteration what works and what doesn’t.
With generative design, there is no single solution; instead, there are potentially thousands of great solutions. You choose the design that best fits your needs.
In the time you can create one idea, a computer can generate thousands, along with the data to prove which designs perform best.
Generative design lets you create optimized complex shapes and internal lattices. Some of these forms are impossible to make with traditional manufacturing methods. Instead, they're built using new additive manufacturing methods.
Set goals and parameters, and the software will create high-performing design options based on those constraints. The software resolves conflicting design constraints so you can focus on innovating.
Generative design is a broadly used term. Here are the four most common methods of generative design.
With this approach, designers or engineers input their goals and constraints, and the software runs artificial intelligence-based algorithms to produce a wide range of design alternatives.
This method applies internal lattices and optimized surface structures to an existing component to make it lighter and stronger.
This approach reduces the weight of an existing component by running analysis to remove unnecessary material, while meeting or exceeding performance criteria.
This method precisely scales and distributes tiny pores through solid materials, and creates surface roughness to mimic bone in medical implants to help patients heal.
Aircraft manufacturer trims the weight of its A320 plane, helping to reduce the carbon footprint of air travel. (video: 2:07 min.)
California-based team designs and builds the world’s fastest production electric bike by reducing its weight.
Sportswear company creates the first dual-purpose 3D-printed performance training shoe for athletes. (video: 31 sec.)
All the things ever imagined, designed, and created—buildings, bridges, cars, and more—have one thing in common: They’re all dead.
Autodesk CTO Jeff Kowalski envisions a more positive outcome for humans and artificial intelligence. And it’s already unfolding.
Autodesk Nastran software lets you analyze linear and nonlinear stress, dynamics, and heat transfer characteristics of structures and mechanical components to create high-performing products.
How do you define the function of a swingarm so an algorithm can design one for you? Read about the process and view images, including alternative designs.
Generative design at the architectural scale.
MIT Tech Review explores how Autodesk software takes designers’ input, and then evolves new designs on its own.
A report on how professionals generate and evaluate design ideas using design optimization tools.