Creepy AI robot dog created with ‘virtual spine’ observed learning to walk on its own one hour after ‘birth’

A ROBOTIC dog has taught itself to walk in an amazing demonstration of quick machine learning and robotic mobility.

Morti the robotic dog has demonstrated the development of human and animal instincts powering a manmade robot.

Researchers have built a robotic dog that taught itself to walk just an hour after coming online.

“Our robot is practically ‘born’ knowing nothing about its leg anatomy or how they work,” Felix Ruppert study co-author, told .

As people and animals learn to become independent, the Central Pattern Generator (CPG) in the spinal cord communicates with the limbs and muscles to move.

Ruppert and co-author Alexander Badri-Sprowitz built the “walking intelligence” system in a computer to model a naturally occurring CPG.

The robot’s CPG is housed in a computer on the “Labrador-sized” robot dog’s head.

Polyurethane tips affixed to Morti’s paws would compress against a sensor when making contact with the treadmill.

To learn how to walk, Morti’s “virtual spinal cord” would check the pressure of a step against the CPG’s predictions.

If Morti fell, the computer’s algorithm would adjust the pendulum swing of its legs or the speed or time spent contacting the ground.

“This is fundamental research at the intersection between robotics and biology,” study co-author Alexander Badri-Sprowitz said in a from the Max Planck Institute for Intelligent Systems.

“The robotic model gives us answers to questions that biology alone can’t answer.”

CPGs play a role in other unconscious systems like digestion and .

Morti’s impressive machine learning capabilities and graceful mobility represent an approaching solution to the problem of robots’ clumsiness.

The robotic dog is also another physical representation of artificial intelligence as opposed to strictly software-based applications like AI translators.