Forlinx Embedded Unveils P2P Family & Edge AI Solutions At Embedded World 2026
Forlinx Embedded presents its latest range of embedded modules and application-ready solutions at embedded world 2026 (Booth 3-561).
At the show, we showcase diverse embedded modules including system-on-module, single-board-computer and embedded PCs. Many engineers are looking for high-scalability module to reduce their time and cost. To address this need, we introduced our new Pin-to-Pin compatible SoM series——UP4 Family.
With this UP4 P2P series, you can directly replace an older one without requiring changes to the baseboard design, wiring, or software. This means products can easily scale across performance tiers, allowing the same carrier board to support different SoMs depending on project requirements.
Highlights are below:
- LCC + LGA 487 available pins
- 40mm×40mm 1.2mm thickness
- One carrier board works for multiple SoMs
- SoC cross-brand compatible
- Various peripheral interfaces ready-to-use
- 48 reserved pin-outs
Pin-to-Pin Compatible SoMs & Edge AI Demos
At embedded world 2026, we returned to the event with a strong focuses on real-world AI inference, industrial networking, and multi-display ARM computing, designed for industrial automation, smart energy, intelligent security, and edge AI applications.
High-Performance AI Pipeline:A collaboration with NXP featuring the i.MX 95 applications processor and the Ara240 Discrete NPU. By combining the 8 eTOPS Neutron NPU with a 40 eTOPS accelerator, this solution handles complex multi-modal queries for industrial security.
360° Surround-View:An RV1126B-based solution that stitches four AHD camera feeds into a seamless panoramic view, optimized for power efficiency.
Face Recognition & Tracking:An RV1126B 3TOPS NPU-driven system for instant feature extraction and local database matching.
Edge Intelligence:The FCU3501 embedded computer demonstrates local video analytics. With a 6TOPS NPU, it can process up to 16 camera streams simultaneously for real-time surveillance.
Intelligent Display Solution:The i.MX 94x solution features a built-in TSN switch and Cortex-M7/M33 real-time cores. It is designed for edge computing tasks that require both high-speed control and functional safety.
Battery Management (BMS):A dedicated solution for Energy Storage Systems (ESS) using the T536 SoC, supporting 8×CAN interfaces for large-scale battery data acquisition.
EV Charger HMI:A UI demo using the TI AM62L32 and LVGL library, showing fluid animations and data visualization while maintaining low power consumption.
Strategic Ecosystem: NXP & ROCKCHIP & CRA
As a Gold Partner of NXP Semiconductors, Forlinx continues to deepen its collaboration by expanding the i.MX 95 ecosystem with high-performance inference modules. At the heart of our presence at the show is the jointly multimodal industrial security demo based on the i.MX 95 processor and Ara240 computing card, enabling secure, AI-ready, and scalable edge solutions ranging from different industrial applications.
Forlinx also maintains a long-term partnership with Rockchip. At Embedded World 2026, we showcased our latest system on modules based on theRockchipRK3588,Rockchip RV1126, andRockchip RK3506platforms at both Rockchip booth and Forlinx booth, highlighting our close collaboration in embedded AI solutions.
To address growing cybersecurity regulations such as the EU Cyber Resilience Act (CRA), Forlinx presented itsCRA-ready embedded platform, the FCU2601. With dual IEC 62443 certifications, the platform helps device manufacturers accelerate compliance with global cybersecurity regulations while ensuring robust industrial-grade security.
Having gone through the entire certification process ourselves, we are deeply familiar with the complex documentation and compliance workflow. This experience allows us to share proven practices with customers and help simplify the path to market, especially for products targeting the European market.
Global Dealership Showcases
Quad-Screen Display Solution built on the OK3588 single board computer from DATA MODUL in Germany: Powered by the Rockchip RK3588 processor, the system supports four independent displays with different video content from a single embedded board, eliminating the need for multiple boards or external graphics processors.
AI Image Recognition Solution built on the OK3576 single board computer from Demsay in Turkey: Demonstrating efficient local object recognition using YOLOv5 on the 6TOPS NPU of the RK3576 platform.
Source: Forlinx Embedded