Home > Storage > PowerScale (Isilon) > Industry Solutions and Verticals > Analytics > PowerScale Deep Learning Infrastructure with NVIDIA DGX A100 Systems for Autonomous Driving > Overview
Computer vision and machine learning (ML) solutions are integrated into vehicles to improve safety, convenience, and the driver experience. Data coming from multiple sources such as camera, lidar, radar and ultrasonic sensors are processed and used to extract information and characteristics of the surrounding environment. Modern vehicles have moved from passive safety systems such as seat-belt pre-tensioning and airbags (designed to minimize injury resulting from collisions).to active safety systems, such as anti-lock braking (ABS) and autonomous emergency braking (AEB) to avoid collisions.
With the evolution of Artificial Intelligence (AI) and DL, the industry is developing embedded control units (ECUs) into vehicles with computer vision algorithms that can interpret real-time sensor data and point cloud data to make corresponding predictions and to derive actions.
The significant automotive safety improvement in the past was passive safety, mainly designed to minimize damage during an accident. Advanced driver assistance systems (ADAS) in many of today’s vehicles can proactively help the driver to avoid accidents by utilizing innovative DL technologies. For example, blind spot detection can alert a driver as they try to move into an occupied lane, pedestrian detection notifies the driver that pedestrians are in front of or behind the car, AEB activates the brakes to avoid an accident or pedestrian injury. More ADAS features like path planning combine with sensor fusion, which brings us closer to the goal of an autonomous vehicle. As the level of accuracy and sophistication increases, autonomous driving (AD) can realize improved capabilities. Critical success factors include improved safety algorithms, increased and efficient computational power, and access to large, comprehensive verification datasets.
This paper focuses on the IT infrastructure challenges faced by automotive original equipment manufacturers (OEMs), and suppliers in developing DL algorithms for ADAS/AD and proposes a scale-out compute and storage solution. The solution is optimized for ADAS/AD workloads—delivering high performance, high concurrency, massive scalability, and flexibility.