Qualcomm introduces Snapdragon autonomous driving platform
Qualcomm introduced its new Qualcomm Snapdragon Ride Platform, a scalable and open autonomous driving solution that consists 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 ADAS (advanced driver-assistance systems) by leveraging its high-performance, power-efficient hardware, artificial intelligence (AI) technologies, and autonomous driving stack to deliver what the company is saying is a comprehensive cost- and energy-efficient systems solution.
The combination of Snapdragon Ride SoCs, accelerator, and autonomous stack aims to offer automakers a scalable solution designed to support three industry segments of autonomous systems, namely L1/L2 active safety ADAS for vehicles enabled with 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 autonomous urban driving, robotaxis, and robo-logistics.
The Snapdragon Ride Platform, based on the family of SoCs and accelerator, is built on scalable and modular heterogenous high-performance multi-core CPUs (central processing unit), energy efficient AI and computer vision (CV) engines, GPUs (graphics processing unit). The platform with SoCs and accelerator can be in concert as needed to offer from 30 Tera Operations Per Second (TOPS) for L1/L2 applications to over 700 TOPS at 130W for L4/L5 driving. The company says that this platform will result in designs that can be passively air-cooled, thereby reducing cost and increasing reliability, avoiding the need for expensive liquid cooled systems and allowing for simpler vehicle designs, and also extending the driving range for electric vehicles. Thermal efficiency for the vehicle domain controllers is possible because of the energy-efficient, purpose-built AI engines for automotive applications. The Snapdragon Ride SoCs and accelerator are designed for functional safety ASIL-D systems. Snapdragon Ride will be available for pre-development to automakers and Tier 1 suppliers in the first half of 2020. Qualcomm Technologies expects Snapdragon Ride-enabled vehicles to be in production in 2023.
Introducing the Qualcomm Snapdragon Ride autonomous stack
Integrated as a part of Snapdragon Ride is Qualcomm Technologies’ purpose-built autonomous driving software stack, a modular and scalable solution available to automotive OEM and Tier 1 suppliers to accelerate their development and innovations. This software stack aims to facilitate automakers’ abilities to bring more safety and comfort to everyday driving by offering optimized software and applications for complex use cases, such as self-navigating human-like highway driving, as well as choice of modular options like perception, localization, sensor fusion, and behavior planning. This software infrastructure for Snapdragon Ride supports customer specific stack components to be co-hosted with the Snapdragon Ride autonomous stack components.
“Solutions that integrate the highest levels of functional safety are critical to the mass deployment of advanced driver-assistance systems and autonomous vehicles,” said Chet Babla, Vice President of Automotive, Automotive and IoT Line of Business, Arm. “The future of mobility mandates collaboration across the industry, and the work we are doing with Qualcomm Technologies to help integrate Arm functional safety solutions into Snapdragon Ride is one example of what can be achieved by working together to improve the safety of autonomous driving technologies.”
The company says that the Snapdragon Ride benefits include:
- Proven and integrated safety board support package with safe OS (operating system) and hypervisors
- Safety frameworks from automotive industry leaders, including Adaptive AUTOSAR
- Optimized and comprehensive foundational function libraries for computer vision, sensor signal processing, and standard arithmetic libraries
- AI tools for improving model efficiencies, as well as optimizing runtime on heterogeneous compute units
- Comprehensive autonomous driving stack for highway functions, such as perception, and planning for highway driving functions
- Cost-efficient localization solution with Qualcomm Vision Enhanced Precise Positioning (VEPP)
- Hardware and Software in Loop Test environment
- Data Management Tools for intelligent data collection and automated annotation
For more information, visit www.qualcomm.com.