Technology breakthrough signifies massive potential for the future of aerial inspection use cases
NEW YORK – PARIS – March 10, 2021
Today, Dataiku, one of the world’s leading Enterprise AI and machine learning platforms, and UAVIA, the European Enterprise-Grade Robotics Data Platform leader, announced that their joint product collaboration has resulted in a groundbreaking, fully automated solution for training and deploying machine learning models for edge computing on drones. The end-to-end solution enables industrial operators to deploy neural network models on drones powered by UAVIA’s embedded intelligence, leveraging Dataiku to build and train models while automatically converting and optimizing them to use on any UAVIA Inside drone.
“Optimum data analysis is an essential element of Industry 4.0, which has the potential to completely transform industrial practices,” explains Florian Douetteau, CEO of Dataiku. “This partnership with UAVIA enables the valorization of data collected through robotics on industrial sites and ultimately provides operators on site with critical decision making assistance for their daily tasks. It aligns with our mission at Dataiku of helping teams deliver analytics using the latest techniques and doing so at scale.”
This collaboration is markedly unique for two reasons. First, running a machine learning model in real time for edge computing used to require heavy manual adjustments in order to adapt memory size and speed of execution to the embedded computer. With Dataiku and UAVIA, the process has been fully automated. Further, flying more than 260 feet above ground means that a human-size element only covers a few pixels, leading to excessive false positive detections. The implementation of real-time detection tracker technology solves this problem.
“The outcome of this collaboration with Dataiku affirms our position as a leading deep-tech supplier in the robotization of industrial operations,” said Pierre Vilpoux, CEO of UAVIA. “Beyond technological intelligence, we share another goal with Dataiku — providing an abstraction layer above technology to make it accessible and beneficial for everyone.”
The immediate operational use of this joint breakthrough is that a model trained with Dataiku’s all-in-one platform can be optimized and deployed with a single click on the UAVIA Robotics Platform. This means that drones become capable of risk detection and mitigation on their own or can count assets on site, illustrating a few of the many use cases for industrial site monitoring. To learn more about how Dataiku and UAVIA are working to push the boundaries of unmanned autonomous vehicles further toward real-time aerial inspections, visit this link.
Dataiku is one of the world’s leading AI and machine learning platforms, supporting agility in organizations’ data efforts via collaborative, elastic, and responsible AI, all at enterprise scale. Hundreds of companies use Dataiku to underpin their essential business operations and ensure they stay relevant in a changing world, including models driving fraud detection, customer churn prevention, predictive maintenance, supply chain optimization, and much more. Dataiku is built for companies looking to democratize AI across their organization, bringing agility and preparedness to the business through the use of data by everyone from analysts to data scientists.
Strange Brew Strategies
UAVIA Robotics Platform is an enterprise-grade platform providing a standardized collaborative solution to every worker’s hands for versatile and secured site monitoring operations by drones. Multiple users across the world can access UAVIA’s AI to control heterogeneous drones fleets, while having data processed and shared in real-time for a wide range of value-added applications.
UAVIA is backed by prestigious investors such as Airbus Ventures, Sofimac Innovation and BPI France. The company is entering a scale-up phase and hiring additional talents for its R&D and Customer Operations teams, following the deployment of its solutions by tier 1 industrial operators.
Press Contact :