With full support for NVIDIA JetPack 7.2 for Yocto and Ubuntu-based projects, the system integrates the WISE-Edge Developer Architecture (WEDA) and NVIDIA NemoClaw to enable advanced multimodal reasoning and autonomous decision-making capabilities in robotics, industrial automation, and agentic AI applications. Furthermore, the validated, integrated DRAM ensures critical memory availability, eliminating market supply risks and addressing the growing demand for edge AI.
Multi-camera machine vision acceleration via native 4x 10GbE connectivity:
Based on NVIDIA Jetson Thor and the NVIDIA Blackwell architecture, the AIR-075 delivers high-performance edge AI inference in a compact, thermally optimized, industrial-grade chassis. Its four native 10GbE RJ45 interfaces provide the high bandwidth needed to connect multiple IP cameras, enabling real-time video capture and AI processing without the need for external aggregation switches. This direct connection capability dramatically reduces system complexity and integrates seamlessly with existing IP-based industrial vision infrastructures. With a wide power input range of 19 to 36 V DC and flexible M.2 expansion for NVMe storage, 5G, and Wi-Fi, the AIR-075 provides a highly scalable platform for autonomous machines and distributed AI deployments at the edge.
Faster deployment of agentic AI with NVIDIA JetPack 7.2 and Advantech WEDA.
The AIR-075 is backed by Advantech’s edge AI software ecosystem and NVIDIA’s open models, including NVIDIA Cosmos, NVIDIA Nemotron, NVIDIA GR00T, and NVIDIA JetPack 7.2, to simplify development, deployment, and fleet management. Advantech WEDA acts as the AI deployment infrastructure for the AIR-075, enabling centralized management of AI model lifecycles, agent workflows, software updates, and operational policies across distributed edge AI environments. Along with support for NVIDIA NemoClaw-ready runtimes, the AIR-075 enables multimodal AI agents to interact with cameras, sensors, enterprise systems, and physical devices using natural language and automated workflows. The Advantech Edge AI SDK provides pre-validated AI frameworks, development tools, and reference models, while NVIDIA JetPack 7.2 delivers agent-optimized Jetson software and official Yocto support for custom Linux distributions designed to maximize system performance. Furthermore, bit-by-bit reproducibility ensures deterministic builds.
By combining the AI processing power of NVIDIA Jetson Thor with Advantech’s deployment-ready hardware and software ecosystem, the AIR-075 significantly reduces the effort required to move from proof of concept to large-scale production deployment of physical AI solutions in industrial environments.
