Astro the robot dog looks like and learns like its canine namesake. This 100-pound quadruped robot features a 3D printed Doberman Pinscher head, a tail, and a deep neural network computerized brain that learns from experience and can be trained. Designed and developed by a Florida Atlantic University research and psychology team, Astro’s potential is far-reaching.
Using deep learning and artificial intelligence (AI), scientists from Florida Atlantic University’s Machine Perception and Cognitive Robotics Laboratory (MPCR) in the Center for Complex Systems and Brain Sciences in FAU’s Charles E. Schmidt College of Science packed Astro full of some serious technology. Unlike previous iterations of quadruped robots, Astro isn’t “programmed” to perform simple tasks. Due to the kind of neural network in Astro’s Doberman-shaped head, this robot can be trained to perform a wide variety of tasks, just like a real dog. Astro can see, hear, process, and respond to a wide variety of sensory input.
Developmentally, Astro is still a puppy. It can sit, lie down, move forward, and perform other basic commands. The research team who built the robot wants to teach it to respond to hand signals, colors and multiple languages. Additionally, they also want Astro to recognize different people by sight, which would allow it to be paired with a wider variety of handlers. In addition to responding to cues and commands, Astro’s “brain,” can, with training, sync up with drones and other mechanized technology. The K9 robot could send and receive a wide variety of intel and respond to real-world input on the fly.
Astro the Robot Dog’s Uses
Astro’s is no lightweight — it weighs 45 kilos (100 pounds) and can traverse extremely rough terrain. Not only can Astro move through challenging geographical areas like dense forests or over mountains, but it can also enter disaster zones more safely than human rescuers or search dogs. Originally, the FAU team built Astro for military applications. The robot was to serve as a scout. The team equipped Astro with over a dozen sensors including optical, auditory, olfactory, gas, and radar. Its key missions include detecting guns, explosives and gun residue to assist police, the military, and security personnel.
This robotic dog can also be trained for and/or assist in the following ways, as well:
- Guiding the blind
- Pulling wheelchairs
- Assisting with mobility tasks
- Medical diagnostic monitoring
- Exploring hazardous environments
- Assisting soldiers on the battlefield
- Search through thousands of faces in a database
- Sniff out and identify airborne substances
- Able to hear distress calls that are inaudible to humans
- Serving as a first responder for search and rescue missions such as hurricane reconnaissance
The Brains Behind Astro
FAU’s MPCR team will program Astro to have an extensive database of experiences that he can draw upon to help him make immediate decisions on the go. Teams of neuroscientists, IT experts, artists, biologists, psychologists, high school students and undergraduate and graduate students at FAU all helped to bring Astro to life. Running the project are Dr. Elan Barenholtz, Ph.D., an associate professor in FAU’s Department of Psychology, co-director of FAU’s MPCR laboratory, and a member of FAU’s Brain Institute (I-BRAIN), one of the university’s four research pillars; Dr. William Hahn, Ph.D., an assistant professor in FAU’s Department of Mathematical Sciences and co-director of FAU’s MPCR laboratory; and Pedram Nimreezi, director of intelligent software in FAU’s MPCR laboratory, chief technology officer for RedGage. There’s also a martial arts expert on the team to help provide Astro with some self-defense training.
“Our Machine Perception and Cognitive Robotics laboratory team was sought out by Drone Data’s Astro Robotics group because of their extensive expertise in cognitive neuroscience, which includes behavioral, neurophysiological and embedded computational approaches to studying the brain,” shares Ata Sarajedini, Ph.D., dean of FAU’s Charles E. Schmidt College of Science. “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.”