Lazaro Gamio / Axios

Robots are normally only good at the task they are programmed to do. Now, scientists have programmed robotic controllers to learn to avoid obstacles and cooperate by mimicking Darwinian evolution.

Just like genes, the robot's programming could mutate and be selected upon. Additionally, like in evolution, the robots could co-opt previous parts of their programming to find solutions more quickly. Because the robots were connected online, when they were close together they were also able to exchange their evolving robo-genomes.

Why it matters: Robots are usually only programmed for one task, and when confronted with an obstacle, they can falter. Online evolution allows them to adapt and learn to find solutions outside of their programming.

"It is not directly analogous to nature, but it is inspired by nature," Luís Correia, a scientist at the University of Lisbon in Portugal and an author of the study told Axios.

What they did: In the study, published Wednesday in the journal Royal Society Open Science, the scientists gave the robots three tasks: avoiding obstacles while moving in as fast as possible with little detours, searching for and finding a small target, and a cooperative task that involved gathering together. Robots that had evolved solutions to the cooperative aggregation task then had faults that mimicked hardware problems injected into their programming to see if the robots could evolve work-arounds.

The bottom line: In the past, online evolution in real-world robots wasn't feasible because there wasn't enough processing power, so learning took days. (Imagine a robot running into an obstacle over and over again, damaging itself as it slowly evolves the programming to go around.) But these real-life robots were given an hour to complete their tasks, and appear to be able to adapt to damage acquired while learning. Although the tasks were very simple, this shows that online evolution is another viable type of robot learning and might let them address more complex tasks in the future.

Go deeper

Felix Salmon, author of Capital
10 mins ago - Economy & Business

A white-collar crime crackdown

Illustration: Eniola Odetunde/Axios

America has waited a decade for an aggressive government crackdown on white-collar crime. Now, just before the election, and in the middle of a bull market, it has arrived.

Why it matters: When times are good, investors become more trusting and more greedy. That makes them more likely to put their money into fraudulent or criminal enterprises.

  • After a decade-long bull market, there is no shortage of those frauds to prosecute.
37 mins ago - Technology

Lawyers crystal-ball the Google antitrust case

Illustration: Eniola Odetunde/Axios

The Justice Department's antitrust suit against Google is a strong, straightforward monopoly case, competition lawyers and experts tell Axios. But that doesn't mean it'll be an easy journey for the government.

The big picture: Winning any antitrust case is a heavy lift. It's even more of a challenge to pull off victory in a future-looking case that seeks to make room for potential new competition to flourish.

The pandemic is getting worse again

Expand chart
Data: The COVID Tracking Project, state health departments; Note: Due to a database error, Missouri had a 3 day gap in reporting from Oct. 11-13; Map: Andrew Witherspoon/Axios

Every available piece of data proves it: The coronavirus pandemic is getting worse again, all across America.

The big picture: As the death toll ticks past 212,000, at a moment when containing the virus ought to be easier and more urgent than ever, we are instead giving it a bigger foothold to grow from.