Engineers from Columbia University in New York, have announced that they have created an AI that – for the first time – is able to learn to generate kinematic designs in response to visual shape prompts. In a new study, the researchers demonstrated how their AI used its abilities to design thousands of new mechanisms to trace specified geometries.
Mechanism design – the art of assembling linkages and joints to create machines with prescribed motion – is one of the quintessential activities of mechanical engineers, but has resisted automation for almost two centuries. In his seminal 1841 book Principles of Mechanisms, Oxford professor Robert Willis famously noted, ‘When the mind of a mechanician is occupied with the contrivance of a machine, he must wait until, in the midst of his meditations, some happy combination presents itself to his mind which may answer his purpose.’
Advertisement
Almost 200 years later, we still teach machine design mostly by apprenticeship. While we can simulate machines of almost any complexity, systematic methods for design are known only for the most trivial contraptions.
The new AI acquired its ability by watching thousands of videos of mechanisms in motion, like an apprentice studying a master. Since mechanisms are relatively straightforward to simulate, the team first created more than a million random mechanisms and proceeded to simulate each one of them with high fidelity. They discarded the mechanisms that didn’t move smoothly, leaving them with a curated dataset of about 400,000 robust mechanisms.
Advertisement
After watching hours of these videos, the AI acquired the necessary knowledge to design new mechanisms for prompts it had not seen before. In the beginning, many of these designs were incorrect or even impossible to construct. But like a child playing with a construction set, the AI tested its ideas in simulation and learned from its mistakes. After about a day of training, it announced that it was ready.
‘Mechanism design is a fundamental aspect of mechanical engineering,’ explained Hod Lipson, James and Sally Scapa professor of innovation in the Department of Mechanical Engineering and director of Columbia’s Creative Machines Lab, where the work was done. ‘It is an important aspect of many fields, ranging from robotics to aerospace and even toy design. But like electronics and chemistry, it is one of those fields where simulation is easy while creativity is difficult, and so it lends itself well for generative AI.’
Advertisement
The AI doesn’t always have an answer. ‘When the AI is confounded, it produces a blurry design,’ said Jiong Lin, who led the work. ‘The blurry response could indicate that it cannot complete the design, or that there is more than one solution. We don’t really know.’
The researchers lament that they don’t understand how the AI reaches its designs. ‘We don’t really know how it thinks. We can test it and find its limits, but it can’t yet teach us new design principles,’ said Jialong Ning, who co-led the work. ‘It’s like the AI developed a kind of gut intuition that it can’t explain.’
The researchers acknowledge that these are early days for automating mechanical design. So far, the AI can only design planar mechanisms with a single degree of freedom, composed only of rigid linkages connected with revolute joints. ‘This is just the beginning. Our goal is to expand this process from 2D to 3D, to multiple degrees of freedom, and from rigid linkages to other types of components such as springs, gears, wheels, soft materials and even other kinds of actuators,’ Lipson added.
Advertisement
The work is part of Lipson’s decades-long quest to automate creativity. Serving as a design engineer in his early career, Lipson set his target on designing machines that can design other machines. ‘Instead of solving problems one at a time, I concluded we should try to design a machine that can solve problems autonomously. Then, all we would have to do is point it at the problem we want to solve.’
The vision of automating creativity was challenged by skeptics who insisted that creativity was uniquely human. ‘With generative AI, we are beginning to see the rise of truly creative machines,’ Lipson said. ‘AI’s newfound ability to create code, materials, circuits, molecules – and now mechanisms – will ultimately allow us to reach new parts of the design space we could not explore with our naked human imagination. We have been stuck in a tiny corner of the possible for too long; we are about to unleash a vast new world of engineering possibilities.’