Browse Publications Technical Papers 2023-01-0993

ADAS Sensor Data Handling in the World of Autonomous Mobility 2023-01-0993

By 2030, about 95% of new vehicles sold globally will be connected, up from around 50% today. Around 45% of these vehicles will have intermediate and advanced connectivity features (source: McKinsey, 2021).
Modernization, standardization, and automation are the key steps in the roadmap of data handling for connected vehicles. Vehicle software increasingly sits within a connected ecosystem of devices. Consumer expectations are shifting more towards digital compatibility, connectivity, and new functionalities offered in autonomous vehicles. Digitalization is turning the vehicles of the future into commodities that are as experimental as they are useful. Many OEMs are at the beginning of this transformation journey and have struggled on the software side of things. The entire automotive industry is putting its efforts into effectively monetizing the data captured during the development and management of autonomous vehicles. It is not easy to handle the complexity, elasticity, and volume of data involved.
We are now realizing the possibilities of connected vehicles. Soon, the day will come when data no longer has to be stored directly in the vehicles, and this will naturally result in an enormous advantage in terms of performance and cost improvements for OEMs. However, the challenge is how the automotive industry will manage this transformation and maximize the inherent value of this huge amount of data. E.g., one single car can generate up to 1 TB of data in an hour. Traditional data storage methods simply cannot effectively manage costs to meet all the needs of customer experience and expectations.
Leveraging the ADAS sensor data to speed up innovation and improve the customer experience will call for totally new capabilities and infrastructure. Load balancing and failover management are used to achieve data protection, integrity, and availability. Data is one of the assets of an organization, but without robust data handling, the right strategy can detect problems and automatically provide insights into your data center. This paper will give an excellent overview of how to handle petabytes of data on a daily basis in an automatic way with proper utilization of infrastructure and HPC resources and minimum manual tasks. I will describe how to handle data in a hybrid work model. hybrid if you have a data center on premises and, in the next stage, you want to go to any of the cloud data storage options because of time constraints, customer demand, or a third-party company involved in the data sharing concept. how to handle the number of HDDs in both data centers in an effective way without any impact on legacy systems and with complete data integrity.


Subscribers can view annotate, and download all of SAE's content. Learn More »

Members save up to 16% off list price.
Login to see discount.
Special Offer: Download multiple Technical Papers each year? TechSelect is a cost-effective subscription option to select and download 12-100 full-text Technical Papers per year. Find more information here.