Using artificial intelligence (AI), scientists have now created a robot dog that can easily conquer an obstacle course.
That’s right. A robot dog can now do parkour.
“By aiming to match the agility of free runners, we can better understand the limitations of each component in the pipeline from perception to actuation, circumvent those limits, and generally increase the capabilities of our robots,” ETH Zurich researchers wrote in their study published in the journal Science Robotics.
Using machine learning the scientists were able to teach their robot dog ANYmal how to maneuver its way through the obstacle course using trial and error.
“Before the project started, several of my researcher colleagues thought that legged robots had already reached the limits of their development potential, but I had a different opinion,” said ETH doctoral student Nikita Rudin. “In fact, I was sure that a lot more could be done with the mechanics of legged robots.”
A lot more indeed.
Rudin and his fellow researchers replaced the standard software used in most robots with neural networks. This allows the robot dog to achieve behaviors that would otherwise not be possible, New Scientist reports.
“In the process, ANYmal learned like a child would – through trial and error,” the researchers said in a statement. “Now, when presented with an obstacle, ANYmal uses its camera and artificial neural network to determine what kind of impediment it’s dealing with. It then performs movements that seem likely to succeed based on its previous training.”
“We do not perform any pre-mapping or pre-planning,” said David Hoeller of ETH Zurich, NVIDIA. “Everything is happening online and in real-time.”
Advancements in the world of robotics and artificial intelligence are coming fast and furious these days. And fast and furious is exactly how these robots are going to be coming after us if we don’t slow our roll when it comes to these advancements.
On the plus side, ANYmal and similar robot dogs can be used anywhere that is too dangerous for people to venture, such as inspecting a collapsed building in a disaster area.