A cheap robot has appeared that learns due to interaction with the environment

Over the past decade, researchers have tried several times to use approaches based on

Enhanced learning (RL) — for example, they trained robots to navigate in any environment and perform basic tasks.But so far, they have not been able to create affordable devices that are capable of managing research funds.

Now researchers from Aalto University(Finland) and Ote Robotics have unveiled RealAnt, an inexpensive four-legged robot that can be used to test and implement RL algorithms. The new platform is a minimalist and affordable real world version of the robot simulation environment used in reinforced learning research.

It was originally thought that algorithms would do wellonly work if they train on simulators for thousands of hours. However, the researchers were able to train the four-legged robot to walk using a minimal amount of data. Therefore, the robot can be trained in a real environment, without training in the simulator.

The main goal of the researchers was to createa simple and inexpensive robotic platform based on existing core reinforced learning solutions. Such a platform will allow more researchers to build and test autonomous robots that can perform basic tasks in the real world.

RealAnt, the four-legged robot theycreated, is versatile, minimalistic and inexpensive. He can independently learn to walk, moving his legs in concert, and can feel his position and orientation in a given environment. Using RL algorithms, a robot can be trained to perform simple yet valuable tasks. Moreover, for this, he focuses on the environment around him and does not need additional data.

Read also

Found the alleged kingdom of the disappeared Hittites. What have archaeologists found?

The Doomsday glacier turned out to be more dangerous than scientists thought. We tell the main thing

Biologists have figured out how to identify winning sperm