Quantum Reference Architecture for Autonomous Driving Systems and Industrial AI/ML Application Development

Quantum Corporation releases an end-to-end reference architecture for Advanced Driver-Assistance Systems (ADAS) and Autonomous Driving (AD) systems.

Portfolio of end-to-end solutions that manage data across entire ADAS/AD development lifecycle

By enhancing the acquisition, movement, storage, and curation of the data necessary to develop autonomous vehicle software, the architecture is designed to address the needs of every stage of ADAS/AD development. It enables autonomous vehicle developers to unleash the power of their data and spearhead the next era of self-driving innovation.

“Although still relatively nascent, organizations developing autonomous vehicles are at a crossroads,” said Jamie Lerner, president and CEO. “The volume of data being captured is increasing exponentially, presenting an urgent need for speed, capacity and cost-efficiency in the data management lifecycle. As the experts in unstructured data capture, storage, management, and enrichment, we are leading the way in delivering a complete portfolio of end-to-end solutions and lab-proven technology that delivers the industry’s best performance, capacity and scalability-all requirements for ADAS/AD solutions – at a fraction of the cost. This new reference architecture empowers ADAS developers to build the self-driving vehicles of tomorrow.“

The vast amount of data generated during autonomous vehicle development illustrates the scale of challenges faced by AV manufacturers. The test vehicles typically capture terabytes of sensor data per hour generated by multiple video cameras, LiDARs, and radars. ADAS/AD development systems rely on collecting and processing these large amounts of unstructured data to build ML models and algorithms, requiring intelligent and efficient data management. By utilizing the new end-to-end reference architecture, developers take advantage of the firm’s complete portfolio of end-to-end data management solutions that deliver the level of performance, capacity and scalability required for ADAS/AD systems.

R6000 storage device

Reference architecture
The data processing in an AV development system starts with capturing data in a test vehicle. The firm’s R6000 is a fast automotive and mil-spec edge storage device developed for high-speed data capture in challenging, rugged environments including car, truck, airplane, and other moving vehicles. It provides a large storage capacity necessary for the in-vehicle logger to store the collected sensor data for an extended period of time, all in a small form factor that makes it well suited for self-driving test vehicles. The R6000 is designed to withstand the demands of a rugged environment and is purpose-built for HA and reliability. Once data is captured, the R6000 removable storage canister enables data offload and on-the-road replacement, allowing cars to stay in service and reduce vehicle downtime.

Data is then uploaded to the StorNext File System for processing. StorNext has demonstrated fast overall response times for video data using independent benchmark testing, and has the ability to process thousands of concurrent streams at high throughput. Further, StorNext software includes a policy engine with options to place and manage data on NVMe, HDD, object storage, cloud, and tape. This data management capability enables full and efficient use of the analytics infrastructure across multiple tiers.

With the company, once the ML model training and verification is complete and new models developed and deployed, the massive data sets required for future ML development can be retained on low-cost storage providing the right balance between the highest performance and best economics. The firm singularly delivers a portfolio of end-to-end solutions that can tier the data to the location that is efficient and cost-effective, are built specifically for ADAS/AD rugged environments and have the necessary performance, capacity and scalability to effectively manage the data across the entire lifecycle.

“Autonomous vehicle manufacturers are capturing massive amounts of roadway data, and then using that data to design, develop, and validate algorithms that can power self-driving cars. The challenge they’re grappling with is how to effectively extract insights, integrate with other pieces of their architecture, and retain that data for longer periods of time,” said Graham Cousens, lead, ADAS/autonomous vehicle solutions practice. “These are challenges that Quantum has been solving for over 40 years in other sectors. Based on solutions that have been proven to outperform the competition in lab testing – driven by the powerful StorNext File System and our ultra-fast automotive & mil-spec R6000 in-vehicle storage device – this new reference architecture is set to streamline and power the future of autonomous vehicles development.“

Resources:
Quantum’s ADAS and mobility solutions
R-Series Edge Storage range    
Video