Building autonomous combines with CNH Industrial
Impact
CNH Industrial sought ML6's assistance in efficiently transferring an algorithm from training environments to embedded hardware systems in combines, enabling them to rapidly acquire the required knowledge and successfully deploy the algorithm on a multispectral camera, ultimately accelerating production and gaining expertise for future embedded system deployments.
Intro to the customer
With innovation high on the agenda, CNH Industrial has developed strong AI capabilities in-house. As the use cases are custom and complex, the organization looks to build up internal knowledge on how to build, deploy, monitor and improve algorithms. More specifically, CNH Industrial was looking to build internal knowledge on how to move algorithms from training environments to embedded hardware systems in combines.
Challenge
With innovation high on the agenda, CNH Industrial has developed strong AI capabilities in-house. As the use cases are custom and complex, the organization looks to build up internal knowledge on how to build, deploy, monitor and improve algorithms. More specifically, CNH Industrial was looking to build internal knowledge on how to move algorithms from training environments to embedded hardware systems in combines.
"Working with ML6 is investing in our own people. We believe it’s important that we have internal knowledge, and through our collaboration we received a knowledge transfer in a very efficient way to bring our people to a higher level. We buy knowledge, we buy flexibility, we make an investment in our people towards the future."
Solution
To build up that knowledge as quickly and efficiently as possible, CNH Industrial turned to ML6 to help move an algorithm to a multispectral camera. ML6 helped downscale and optimize the algorithm and helped get it embedded by working together with the camera provider.
Results
Through the collaboration, CNH was able to go into production much faster. They now also have the necessary expertise to deploy algorithms on an embedded system for future use cases.