Taiwanese firm Aetina has launched two palm-sized in-vehicle edge AI systems for the transportation market.

The AIE-VN34/44 and AIE-VO24/34 combine up to 100Tops of AI performance, four GMSL2 camera connections and fanless rugged operation for transportation applications, as well as robotics and industrial use.

They are powered by Nvidia Jetson Orin NX and Jetson Orin Nano modules, are ready for mass production, and target smart transportation, autonomous mobile robots (AMRs) and industrial automation deployments where space and reliability are critical.

As AI-powered vision systems become increasingly essential across smart cities, intelligent transportation and industrial automation, real-time processing of high-quality, multi-camera video streams within space-constrained environments remains a challenge. The AIE-VN34/44 and AIE-VO24/34 address this directly: powered by Jetson Orin NX (8 and 16Gbyte) and Jetson Orin Nano with Super Mode (4 and 8Gbyte), the systems deliver up to 100 and 67Tops of AI performance, respectively, packed into a palm-sized 136.3 by 132 by 63mm chassis. Each has four GMSL2 (Fakra-Z) ports, enabling long-distance, low-latency multi-camera streaming, real-time AI inference, and 360-degree environmental perception for surround-view monitoring, blind-spot detection and situational awareness.

They can be flexibly expanded with Aetina validated GMSL2 adapter boards and camera modules, with plug-and-play driver-ready for image transmission up to 15m. This bundle brings together camera sensing, high-speed visual data transmission and Jetson Orin-powered edge inference, helping simplify system integration, shorten development and validation cycles, and achieve highly scalable, customisable AI deployment.

Engineered for mobile and industrial applications, they pair rugged reliability with flexible connectivity. Both have passed MIL810H shock and vibration testing and carry E-Mark (E24) certification for automotive electronic equipment, streamlining integration into global vehicle markets. A fanless architecture supports stable, throttle-free operation from -25 to +55˚C, while a 9 to 36V DC wide-voltage input and integrated ignition power control protect against voltage fluctuations and enable safe start-up and shutdown.

Isolated Can-FD and GPIO/RS-232 interfaces connect vehicle signals, controllers, sensors and industrial peripherals, complemented by Gigabit Ethernet, USB 3.2, HDMI, M.2 M-Key storage and optional M.2 E-Key wireless expansion.

The convergence of V2X and edge computing continues to drive demand for compact, rugged in-vehicle computing platforms that can process multi-camera vision data locally and in real time. They turn visual data into actionable intelligence for AI agents and autonomous systems, supporting surround-view monitoring and blind-spot detection for commercial vehicles, obstacle avoidance and path planning for AMRs, real-time defect inspection on production lines, and people tracking and security monitoring across smart retail and building environments.

“As real-time, multi-camera perception becomes the sensing layer for AI agents operating in vehicles, AMRs, and industrial equipment, customers need edge compute that is rugged enough for the field and ready for mass production from day one,” said James Ho from Aetina (www.aetina.com).

The AIE-VN34/44 and AIE-VO24/34 (www.aetina.com/products-detail.php?i=737) are available now for mass production, supporting BSP built on Nvidia (www.nvidia.com) JetPack 6.2, with JetPack 7.2 support to be added soon.