Neurala, Inc. is known for its work developing its own Neurala Brain.
This is a piece of deep learning neural network software that makes smart products like robots, drones, toys, self-driving cars and smart cameras more autonomous.
The firm has this month announced a software development kit (SDK) for industrial inspection drones with sophisticated deep learning neural network AI functions.
Developer use case
Developers can use this technology to augment industrial drone-based inspection solutions with Artificial Intelligence (AI).
The Brains4Bots SDK is hardware-agnostic and helps provide machine vision, spatial navigation and obstacle avoidance functionality.
Neurala says that its Lifelong Deep Neural Network (L-DNN) technology enables machines to learn after deployment in the field. The SDK transforms any type of drone device into an intelligent “situational partner” that can perform operational assignments both on- and offline.
“Neurala’s newest SDK leverages our cutting-edge Lifelong Deep Neural Network technology and will greatly facilitate the development of the next generation of AI-powered inspection drones,” said Neurala CEO Massimiliano ‘Max’ Versace.
Neurala’s Brains4Bots SDK offers embedded analytics to pre-train and embed ‘learned analytics’ to edge devices. This feature enables operators to find and recognise objects and asset configurations out of the box.
There is also real-time detection power so that, using unmanned aerial systems, enterprise customers can enable close inspection tasks on critical infrastructure, such as cell tower assets or insulators.
Neurala’s APIs come with sample code and testing tools and can be deployed on Linux, iOS and Android and support Nvidia, ARM and Intel processors.