Using deep learning and artificial intelligence, scientists from Florida Atlantic University’s Machine Perception and Cognitive Robotics (MPCR) Laboratory are bringing Astro, the robotic dog to life.
A robotic tail wagger is not exactly new: Boston Dynamics has been honing its all-electric Spot lineup for years.
Astro, features a 3D-printed head (designed to resemble a Doberman pinscher) that contains a computerized brain.
He doesn’t just look like a dog, though. He learns like one, too: Astro is being trained via deep neural network to learn from experience and perform real-life tasks.
Built-in sensors, radar imaging, cameras, and a directional microphone help ensure that, just like a real dog, he can respond to commands like “sit,” “stand,” and “lie down.”
Eventually, researchers hope Astro will be able to understand hand signals, detect different colors, comprehend various languages, coordinate with drones, distinguish human faces, and recognize other dogs.
“Astro is inspired by the human brain and he has come to life through machine learning and artificial intelligence, which is proving to be an invaluable resource in helping to solve some of the world’s most complex problems,” Ata Sarajedini, dean of FAU’s Charles E. Schmidt College of Science, said in a statement.
Designed to engage and react to his surroundings in real time, the intelligent machine will be able to navigate rough terrains and respond to dangerous situations.
As an information scout, Astro can assist police, the military, and security personnel in sniffing out guns and explosives.
As if that weren’t impressive enough, the robotic dog may be programmed to work as a service dog for the blind or visually impaired or provide medical diagnostic monitoring for those who need it.
He is also capable of rapidly searching faces in a database, smelling the air for foreign substances, and hearing distress calls well outside a human’s audible range.