MyAdvantech Registration

MyAdvantech is a personalized portal for Advantech customers. By becoming an Advantech member, you can receive latest product news, webinar invitations and special eStore offers.

Sign up today to get 24/7 quick access to your account information.

Advantech Unveils ROM-2860, a Size-L Open Standard Module (OSM), Featuring Qualcomm QCS6490 for On-Device AI Scenarios

4/10/2024

TAIPEI, Taiwan, April, 2024 - Advantech, a global leader in AIoT and Edge Computing, proudly unveils ROM-2860, the latest breakthrough in the Size-L lineup of Open Standard Modules (OSM)—a miniature yet potent solder-on module. Powered by the Qualcomm® Octa-core QCS6490 processor, ROM-2860 sets a new benchmark for performance within its ultra-compact 45 x 45 mm form factor, revolutionizing AIoT and handheld applications. Designed to outpace industry standards, ROM-2860 is fortified with AI computing capabilities, offering intelligent solutions that enhance machine vision. With its array of extensive connectivity options, ROM-2860 presents an unparalleled solution tailored to meet the diverse demands of AIoT scenarios.

Tiny size, unlimited power

The ROM-2860 stands out with exceptional performance in an ultra-compact 45 x 45 mm OSM size-L design. Powered by the Qualcomm® Octa-core QCS6490 processor with a 6.9-watt TDP, the ROM-2860 outperforms traditional computer-on-modules, catering to diverse industrial and handheld applications such as HMI and embedded machine vision with its tiny form factor. Notably, the QCS6490 achieves nearly 20% better performance than mid-tier x86 processors, coupled with an impressive 43-75% reduction in power consumption. This ensures robust computing performance on site. 

Furthermore, by supporting Windows 11 on ARM, the ROM-2860 maximizes its potential with Arm architecture, enhancing battery life and ensuring consistent performance. Arm Systems on Chip (SoC) often come with essential features including CPU, GPU, Wi-Fi, mobile data networks, and Neural Processor Units (NPUs) to handle AI workloads. This provides users seamless compatibility with existing apps and tools on new Arm-powered devices.

Machine vision solutions empowered by on-device AI

The ROM-2860 accommodates diverse embedded machine vision needs, featuring 12 TOPS of AI capability, dual-camera input support, and a native video codec. This compact solution excels in applications requiring seamless video capture, low-latency signals, limited installation space, and resilience to vibrations, complemented by its AI capabilities. 

Compared to traditional devices, the ROM-2860's on-device AI improves operational efficiency in use cases such as autonomous mobile robots (AMR). These robots use cameras, radar, and LiDAR for initial AI modeling and then gain inference capabilities for tasks like object detection, route optimization, localization, and collision avoidance. 

The ROM-2860 also supports various development tools like Microsoft Azure AI Service, Qualcomm Snapdragon Neural Processing Engine (SNPE) SDK, and Qualcomm AI Hub, streamlining machine learning deployment and converting models from Aware, Azure, and other cloud service providers. With the Qualcomm QCS6490 CPU, it offers 64-bit program support. Developers can update Visual Studio to version 15.9 or above for ARM64 compatibility, simplifying binary compilation for existing projects.

Abundant interfaces and smooth connectivity in AIoT applications

The ROM-2860, with its compact OSM form factor, supports a variety of interfaces including PCIe Gen3 for 5G / Wi-Fi 6, LPDDR5, UFS, USB 3.2, URAT, GPIO, and more. Additionally, it offers dual-display capability with support for up to 2K resolution, including DSI, DP, and eDP. These features provide diverse I/O options that facilitate seamless connections within AIoT applications. 

Qualcomm, a leader in 5G technology, ensures ROM-2860's superior compatibility and minimal latency with its integration of the Octa-core QCS6490 CPU. When paired with Qualcomm's 5G and Wi-Fi 6 modules, ROM-2860 delivers enhanced performance, promising improved connectivity and efficiency within AIoT ecosystems.