The robot has beaten humans at the race

Running a Drone on a Board with Artificial Intelligence: A Simulation-to-Real Gap for a Robotic Drone

AIs have been beating humans at games for years, but in these cases the AI has always trained in exactly the same conditions in which it competes. The board can be recreated exactly in chess. Researchers have demonstrated an artificial intelligence that can beat humans in a place where simulation isn’t feasible. The system is capable of beating humans at their best, and can race drones against them. This research can improve the efficiency of drones.

Humans and computers have been playing games for a while now. IBM’s Deep Blue bested Garry Kasparov in 1997. In 2016 Google built a program using artificial intelligence that could beat world champion Lee Sedol at the game of Go. Humans have been beaten at poker and video games.

The most recent one took place at a desk. The computers haven’t been able to compete in real-world contests. Kaufmann says that’s because it’s much harder to simulate real-world conditions if you’re flying a drone than if you’re playing a game on a board. “This is called a sim-to-real gap,” he says.

The team overcame the gap using a variety of AI and conventional programing strategies. Kaufmann taught the drone what racing gates looked like by hand-identifying the fabric gates in tens of thousands of images — a technique known as “supervised learning.” The team also used more conventional code to help the drone triangulate its position and orientation based on visual cues from its cameras.

Leonard Bauersfeld, a PhD student at the University ofZURICH in theRobotics and perception group, thinks that it would be better to have all gates in the correct sequence.

A Little Robot to Test the Forces that Hold Atomic Nuclei Together: Two Observations of Oxygen 28 from the Indian Space Research Organization

There are many limitations of the drone. Only the course it’s been trained on and in will work. Moving the course from inside to outdoors, for example, would throw the drone off due to changes in lighting. And the slightest things can send it spinning. If a rival bumps it, it has no idea how to handle it, says Bauersfeld.

It’s not easy to design this kind of technology into a military drone, according to Bauersfeld.

According to the commentary in Nature, the new technology has a way to go.

He writes that the drone needs to deal with wind, light, gates, and many other factors to beat human pilots.

The little robot is a sign that artificial intelligence is ready to go into the real world even if its human opponents aren’t.

Oxygen 28 is an element that has 20 neutrons and eight protons. Physicists wanted to be able to put their theories of how atomic nuclei work to the test, as the proposed unusual property of this strange isotope would allow them to do so. Now, after decades of experiments physicists believe they have observed oxygen 28. The observations indicate that there is more physicists that don’t know about the forces that hold atomic nuclei together.

This time, the Indian Space Research Organization’s successful moon landing, and the low level of support offered to researchers whose first language isn’t English by journals.

Previous post A dilated porp in a TRPV3 channel
Next post Idalia extends its destruction along the southeastern US coastline