The Neurala Intelligence Engine (NIE) can immediately learn to recognize an object using an ordinary camera. Then, as the object moves, Neurala’s deep learning algorithms learn more about the object in different environments. The recognition gets even better.
NIE goes beyond conventional visual processing by other deep learning companies. Neurala creates Deep Autonomy by learning in real-time and in the real-world so that robots can adapt, react and respond.
The Neurala Intelligence Engine can be trained in advance to track an object in different situations. As the object gets closer, a robot can be instructed to avoid or come in contact with the object.
To help a robot avoid collisions, Neurala used Microsoft Flight Simulator to train the Neurala software to identify and track a distant airplane in different weather conditions.
Deep learning and object recognition are not enough to make a smart robot.
The Neurala Intelligence Engine goes beyond conventional technologies to learn and identify by comparing them to other things it has learned in the past. The NIE then places all of the objects on a three dimensional map to make Deep Autonomy possible.
The NIE does not require expensive active sensors. Instead, robot makers can use common CMOS cameras, which are available for most off-the-shelf robots, cell phones, security cameras, etc