TAIPEI, May 19, 2025 /PRNewswire/ — Advantech, a global leader in industrial edge computing, is showcasing its complete integration capabilities with NVIDIA Jetson Thor at COMPUTEX 2025, Booth K0605. Featuring the high-performance MIC-743 Edge AI platform, Advantech delivers an optimized, compact, and rugged solution for intelligent mobility, VLM (Vision Language Model) at the edge, and humanoid robotics.
This live demo highlights Advantech’s ability to architect a full sensor-to-inference pipeline, from multi-format camera input to real-time AI processing at the edge, all connected through high-speed Ethernet with minimal latency.
Complete Edge AI Architecture: From Sensors to Real-Time Inference
The system integration begins at the sensor level, supporting a variety of camera interfaces such as MIPI CSI and other high-speed industrial protocols. Sensor data is routed through NVIDIA Holoscan Sensor Bridge, a sensor-to-ethernet streaming platform designed for low latency applications, and aggregated via Advantech’s high-speed sensor switch, supporting up to 2×10GbE uplinks depending on system configuration. This data is then streamed directly into the MIC-742, a compact, rugged, high-performance AI computing system built on NVIDIA Jetson Thor module and powered by NVIDIA Holoscan platform.
Leveraging Camera over Ethernet and high-throughput networking, the architecture ensures ultra-low latency and efficient data processing, crucial for safety-critical mobile and edge AI applications.
MIC-743 : Compact Embedded Computer for Physical AI and Humanoid robotics
The MIC-743 is purpose-built for edge deployment in harsh environments, offering:
- NVIDIA Jetson Thor Module with 2,070 FP4 TFLOPS AI performance powered by the NVIDIA Blackwell GPU
- 128GB LPDDR5X memory for seamlessly running generative AI models including LLMs, VLMs and Vision Transformers.
- 1 x 100G QSFP28 + 1 x 5GbE LAN for high-bandwidth sensor input
- Rich I/O: 4 x USB 3.2, HDMI, 4 x CAN, I2C, SIM card, audio
- Expansion: GMSL2 camera support, M.2 NVMe, M.2 Wi-Fi, SATA, TPM
- Rugged Design: -10°C to 60°C operation, 3Grms vibration, 9–36V input
By replacing traditional x86 systems with a single ARM-based platform, the MIC-743 offers higher AI performance, lower power consumption, smaller footprint, and faster deployment, ideal for physical AI and humanoid robotics.
Accelerating Deployment with Ecosystem Integration
With deep experience in edge architecture, Advantech bridges AI hardware, sensor infrastructure, and networking into a ready-to-deploy Edge AI solution. From heavy-duty machinery to humanoid robotics and autonomous systems, the MIC-743 shortens time-to-market, enabling multi-tasking with real-time performance for vision-based decision-making.
This integrated approach helps customers:
- Reduce system complexity and deployment time
- Optimize form factor and energy efficiency compared to traditional systems
- Scale across mobility and industrial use cases with minimal engineering effort
See It Live at COMPUTEX – Booth K0605
At COMPUTEX 2025, Advantech is offering an exclusive live demo of its full-stack Jetson Thor implementation powered by NVIDIA Video Search and Summarization. Visitors can explore how sensor fusion, and AI acceleration come together in the MIC-743.
Visit Booth K0605 to experience the future of mobility-ready AI computing, designed and delivered by Advantech.
About Advantech: Advantech’s corporate vision is to enable an intelligent planet. The company is a global leader in the fields of IoT intelligent systems and embedded platforms. To embrace the trends of IoT, big data, and artificial intelligence, Advantech promotes IoT hardware and software solutions with the Edge Intelligence WISE-PaaS core to assist business partners and clients in connecting their industrial chains. Advantech is also working with business partners to co-create business ecosystems that accelerate the goal of industrial intelligence. (www.advantech.com)
Advantech Contact:
Julia Chen — Industrial Edge AI and Video Solution Marketing
Tel: +886-2-2792-7818, Ext. 1325
Mobile: +886-975-150-580
[email protected]
