There's a new squishy robot in town, and was created by AI

The robot couldn't walk at first

The team wanted to build a robot that doesn’t take considerable labor, time, money, and resources, which are typically required to design, test, and deploy the elaborate robots you see today.

“We discovered a very fast AI-driven design algorithm that bypasses the traffic jams of evolution, without falling back on the bias of human designers,” added Kriegman. “We told the AI that we wanted a robot that could walk across land. Then we simply pressed a button and presto! It generated a blueprint for a robot in the blink of an eye that looks nothing like any animal that has ever walked the earth. I call this process ‘instant evolution.’”

The team gave their AI system a prompt to design a physical machine that can walk on land. A custom robot was efficiently and automatically generated in less than 30 seconds on a laptop computer, requiring only 10 design attempts. The AI came up with a blueprint of a robot that was the size of a bar of soap.

At first, the robot didn’t have legs, so of course it couldn’t walk. Then, the AI came up with a solution and gave the robot three legs.

“It’s interesting because we didn’t tell the AI that a robot should have legs,” Kriegman said. “It rediscovered that legs are a good way to move around on land. Legged locomotion is, in fact, the most efficient form of terrestrial movement.”

An AI program that builds robots

To bring the robot to life, the team first 3D printed a mold of the negative space around the robot’s body, as explained in the press release. 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. The robot could finally walk.

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

The study was published inthe Proceedings of the National Academy of Sciences.

Study abstract:

Robots are notoriously difficult to design because of complex interdependencies between their physical structure, sensory and motor layouts, and behavior. Despite this, almost every detail of every robot built to date has been manually determined by a human designer after several months or years of iterative ideation, prototyping, and testing. Inspired by evolutionary design in nature, the automated design of robots using evolutionary algorithms has been attempted for two decades, but it too remains inefficient: days of supercomputing are required to design robots in simulation that, when manufactured, exhibit desired behavior. Here we show de novo optimization of a robot’s structure to exhibit a desired behavior, within seconds on a single consumer-grade computer, and the manufactured robot’s retention of that behavior. Unlike other gradient-based robot design methods, this algorithm does not presuppose any particular anatomical form; starting instead from a randomly-generated apodous body plan, it consistently discovers legged locomotion, the most efficient known form of terrestrial movement. If combined with automated fabrication and scaled up to more challenging tasks, this advance promises near-instantaneous design, manufacture, and deployment of unique and useful machines for medical, environmental, vehicular, and space-based tasks.