Instant evolution: AI designs new robot from scratch in seconds

A team led by Northwestern University researchers has developed the first artificial intelligence (AI) to date that can intelligently design robots from scratch.

The researchers gave the system a simple prompt to test the new AI: Design a robot that can walk across a flat surface. While it took nature billions of years to evolve the first walking species, the new algorithm compressed evolution to lightning speed — designing a successfully walking robot in mere seconds.

The new AI program is faster, runs on a lightweight personal computer, and designs novel structures from scratch. This contrasts sharply with other AI systems, which often require energy-hungry supercomputers and massive datasets. And even after crunching all that data, those systems are tethered to the constraints of human creativity — only mimicking humans’ past works without an ability to generate new ideas.

“We discovered a high-speed AI-driven design algorithm that bypasses the traffic jams of evolution without falling back on the bias of human designers,” said Northwestern’s Sam Kriegman, who led the work. “We told the AI we wanted a robot that could walk across land. Then we pressed a button, and presto! In the blink of an eye, it generated a blueprint for a robot that looks nothing like any animal that has ever walked the earth. I call this process ‘instant evolution.'”

From xenobiotics to new organisms

In early 2020, Kriegman garnered widespread media attention for developing xenobots, the first living robots made entirely from biological cells. Now, Kriegman and his team view their new AI as the next advancement in their quest to explore the potential of artificial life. The robot itself is unassuming — tiny, squishy, and distorted. And, for now, it is made of inorganic materials. But Kriegman says it represents the first step in a new era of AI-designed tools that, like animals, can act directly on the world.

Zero to walking within seconds

While the AI program can start with any prompt, Kriegman and his team began with a simple request to design a physical machine capable of walking on land. That’s where the researchers’ input ended, and the AI took over.

The computer started with a block about the size of a soap bar. It could jiggle but not walk. AI quickly iterated on the design because it had yet to achieve its goal. The AI assessed its strategy with each iteration, identified flaws, and whittled away at the simulated block to update its structure. Eventually, the simulated robot could bounce in place, hop forward, and shuffle. Finally, after just nine tries, it generated a robot that could walk half its body length per second — about half the speed of an average human stride.

The entire design process — from a shapeless block with zero movement to a full-on walking robot — took just 26 seconds on a laptop.

To see if the simulated robot could work in real life, Kriegman and his team used the AI-designed robot as a blueprint. First, they 3D printed a mold of the negative space around the robot’s body. Then, they filled the mold with liquid silicone rubber and let it cure for a couple of hours. When the team popped the solidified silicone out of the mold, it was squishy and flexible.

Now, it was time to see if the robot’s simulated behavior — walking — was retained in the physical world. The researchers filled the rubber robot’s body with air, expanding its three legs. When the air deflated from the robot’s body, the legs contracted. By continually pumping air into the robot, it repeatedly grew and then contracted — causing slow but steady locomotion.

Unfamiliar design

While the evolution of legs makes sense, the holes are a curious addition. AI punched holes throughout the robot’s body in seemingly random places. Kriegman hypothesizes that porosity removes weight and adds flexibility, enabling the robot to bend its legs for walking.

“We don’t know what these holes do, but we know they are important,” he said. “Because when we take them away, the robot either can’t walk anymore or can’t walk as well.”

“When humans design robots, we tend to design them to look like familiar objects,” Kriegman said. “But AI can create new possibilities and paths forward that humans have never considered. It could help us think and dream differently. And this might help us solve some of our most difficult problems.”

Potential future applications

Although the AI’s first robot can do little more than shuffle forward, Kriegman imagines a world of possibilities for tools designed by the same program. Someday, similar robots might be able to navigate the rubble of a collapsed building, following thermal and vibrational signatures to search for trapped people and animals, traverse sewer systems to diagnose problems, unclog pipes, and repair damage. The AI also might be able to design nano-robots that enter the human body and steer through the bloodstream to unclog arteries, diagnose illnesses, or kill cancer cells.

“The only thing standing in our way of these new tools and therapies is that we have no idea how to design them,” Kriegman said. “Lucky for us, AI has ideas of its own.”