From Publication to Production: Interactive Deployment of Forklift Activity Recognition

As the rise of the Internet of Things has made a vast amount of sensory data readily available, research that develops data-driven methods for industrial applications has become increasingly popular. Yet, there are not many reports presenting the deployment of these methods. One can always expect "there is a gap between theory and reality, , but then, what is the gap? How big is it, and how to handle it? This paper demonstrates the deployment of machine learning (ML) models on a real forklift truck and the utilization of an interactive method that essentially bridges the gap between laboratory and realistic settings of the forklift application. The interactive method suggests a gradual adaptation to various user cases in practice: to test the offline method in an environment slightly different from what the training data presents and adjust the method according to these new usages. Additionally, the interactive model deployment allows modification of the offline method in the telematics unit of the forklift truck, which enables an immediate validation of the method adjustment. The result shows that the proposed method can effectively revise erroneous predictions from the ML method and provide quick adaptation to different forklift operations. It also gives a positive signal for further large-scale deployment of offline ML methods and shows their potential to create value and provide optimization in the industry.