Avitas Systems, a newly formed company of GE Ventures, is partnering with NVIDIA to enhance artificial intelligence (AI) to power drones and other robots for inspections.
The companies say they will use the latest advances in AI computing to optimize the use of robotics to better detect defects on industrial assets.
Avitas Systems can target specific points of an inspection and develop paths to collect data in the form of images and video for a variety of robotics, including unmanned aircraft, robotic crawlers and autonomous underwater vehicles. These paths, driven by 3D models, can be repeated from the same angles and locations. The paths’ repeatability means a wide variety of images captured over time can be inputted into Avitas Systems’ cloud-based platform; then, advanced image analytics can detect changes and measure exact defects on an industrial asset (e.g., cracks and corrosion).
The platform can also rate the severity of defects, oftentimes not visible to the human eye, allowing customers to determine when equipment needs to be replaced and enabling earlier resolution of potential issues.
Avitas Systems is using NVIDIA DGX-1 and DGX Station systems for AI training involved in automated defect recognition. Avitas Systems’ data scientists build convolutional neural networks for image classification and generative adversarial neural networks to minimize the amount of work involved in labeling captured images. NVIDIA allows Avitas Systems to train software to process many different images and determine when it is ready to identify defects.
Avitas Systems stores deep learning models in its AI Workbench, a solution that can process inspection data in real time and retrain the models to adapt to new use cases.
“Working with NVIDIA allows us to fully commercialize our cutting-edge, self-service AI Workbench, and we look forward to expanding its capabilities using the new NVIDIA DGX Stations with Volta,” says Alex Tepper, founder and head of corporate and business development at Avitas Systems. “With our workbench, our engineers can easily create and access new deep learning models that train the software deployed to recognize defects automatically at inspection sites.”
“Avitas Systems is breaking new ground by bringing NVIDIA DGX Station beyond the deskside and into the field for the first time,” adds Jim McHugh, general manager of DGX Systems for NVIDIA. “Using our latest DGX systems to help train robots and better predict industrial defects increases worker safety, protects the environment and leads to substantial cost-savings for companies.”
More can be found here.