Snapdragon Ridge hails autonomous vehicles with customisable SoC
Scalable and open autonomous driving solutions from Qualcomm Technologies, a subsidiary of Qualcomm, consist of the family of Snapdragon Ride Safety system on chips (SoCs), Snapdragon Ride Safety Accelerator and Snapdragon Ride autonomous stack.
Snapdragon Ride aims to address the complexity of autonomous driving and advanced driver assistance systems (ADAS) by leveraging power-efficient hardware, artificial intelligence (AI) technologies and what Qualcomm describes as a pioneering autonomous driving stack. The combination of Snapdragon Ride SoCs, accelerator and autonomous stack offers vehicle manufacturers a scalable solution designed to support three industry segments, namely: L1/L2 active safety ADAS for vehicles that include automatic emergency braking, traffic sign recognition and lane keeping assist functions, L2+ convenience ADAS for vehicles featuring automated highway driving, self-parking and urban driving in stop-and-go traffic and L4/L5 fully autonomous driving for urban driving, robo-taxis and robo-logistics.
The Snapdragon Ride platform is based on the Snapdragon family of automotive SoCs and accelerator. It is built on scalable and modular heterogenous high-performance multi-core CPUs, energy efficient AI and computer vision (CV) engines, and a graphics processing unit (GPU). It offers 30 Tera operations per second (TOPS) for L1/L2 applications to over 700 TOPS at 130W for L4/L5 driving. This enables it to be used in designs that can be passively or air-cooled to reduce cost and increase reliability by avoiding the use of expensive liquid cooled systems. It also allows for simpler vehicle designs and extends the driving range for electric vehicles (EVs), says Qualcomm. The Snapdragon Ride SoCs and accelerator are designed for functional safety ASIL-D systems.
The Snapdragon Ride autonomous stack is modular and scalable for automotive manufacturers to use optimised software and applications for complex use cases, such as self-navigating human-like highway driving as well as modular options like perception, localisation, sensor fusion and behaviour planning. This software infrastructure for Snapdragon Ride supports customer-specific stack components to be co-hosted with the Snapdragon Ride autonomous stack components.
The Snapdragon Ride integrated safety board support package has safe OS and hypervisors and operates within safety frameworks from automotive industry leaders, including Adaptive AutoSAR. It has optimised foundational function libraries for computer vision, sensor signal processing, and standard arithmetic libraries
AI tools for improving model efficiencies, as well as optimising runtime on heterogeneous compute units
Snapdragon Ride is expected to be available for pre-development to automakers and tier-1 suppliers in the first half of 2020 and the company anticipates Snapdragon Ride-enabled vehicles to be in production in 2023.