Kuura : leveraging Eclipse Kuksa in vehicular data collection and digital twin creation environment

Abstract

The advancement of automotive technology has significantly increased the integration of sensing and computing capabilities in vehicles, necessitating robust data delivery, testing, and machine learning pipelines for optimal utilization. Concurrently, the concept of vehicular digital twins has emerged as a critical tool for enabling versatile testing and simulation capabilities, essential for the development of automotive software. This study introduces the Kuura platform, leveraging Unreal Engine 5 and Eclipse Kuksa, to create a Vehicle-In-The-Loop (VIL) cloud interface, facilitating the verification of data consistency across simulated and real test drives. Utilizing the MQTT protocol for data storage and transfer, this research not only ensures the accurate replay of test drives within Unreal Engine 5 but also highlights the integration of digital twin technology in automotive software development. Our approach enables the testing and validation of complex use cases, such as traffic accidents and extreme weather conditions, which are otherwise challenging or expensive to execute in real-life scenarios. By providing a novel perspective on verifying data consistency and complementing the vehicle abstraction capabilities offered by Eclipse KUKSA, this work paves the way for significant advancements in the field of vehicular computing, data transfer, and digital twins.