Aetina Corporation - Experts & Thought Leaders

Aetina Corporation, a pioneer AI solution provider and an accelerator of AI infrastructure, announces the general availability of its DeviceEdge AIE-KT78 and AIE-KT68 flagship edge AI systems. Powered by NVIDIA Jetson Thor, both new systems integrate NVIDIA Blackwell architecture's high-performance AI compute, high-bandwidth sensor connectivity, and deterministic industrial control into a compact edge system — purpose-built for Collaborative Robots (Cobots), humanoid robots, and next generation autonomous machines — helping developers perceive, reason, decide, and act in unison in real world environments. High-resolution sensor streams As robots evolve from fixed-routine automation toward context-aware, autonomous decision-making, systems must simultaneously process multiple high-resolution sensor streams, run large multimodal models, and maintain real-time, deterministic control over motors, joints, and external actuators. Facing this rapidly escalating compute demand, existing edge platforms delivering only a few hundred TOPS are struggling to keep up. AIE-KT78 is powered by the NVIDIA Jetson T5000 module with 128GB of 256-bit LPDDR5X memory, delivering up to 2,070 FP4 TFLOPS of AI performance; AIE-KT68 is powered by the NVIDIA Jetson T4000 module with 64GB of 256-bit LPDDR5X memory, delivering up to 1,200 FP4 TFLOPS — striking a balance between performance, power consumption, and system cost. Strengthening data control Both systems support on-device execution of multimodal generative AI, large language models, vision-language models, and Vision-Language-Action (VLA) models, reducing cloud latency and strengthening data control. The AIE-KT78/68 enables robots to run advanced VLA models locally, integrating visual perception, language understanding, and action generation into a single decision-making pipeline that interprets environmental context and responds in real time. To handle such data-intensive perception workloads, the AIE-KT Series simultaneously integrates QSFP28 connectivity (delivering up to 4x25Gbps of bandwidth depending on configuration) and dual RJ45 10GbE ports, enabling high-speed processing of massive real time data streams from high-resolution cameras, 3D LiDAR, radar, depth cameras, IMUs, and various industrial sensors — while supporting up to 8 GMSL2 camera inputs to provide the high-bandwidth data foundation robots need for multi-view environmental perception and spatial understanding. Advanced autonomous machines A dedicated RJ45 1GbE EtherCAT port functions as an independent EtherCAT Master, using microsecond level synchronisation to tightly connect high-level AI inference with underlying motors, joints, sensors, and actuators — consolidating perception, decision-making, and deterministic control within a single system. For collaborative robots, this architecture enhances the flexibility to safely work alongside people and quickly switch between tasks; for humanoid robots, it supports more complex spatial awareness and continuous motion decision-making. It also reduces the need for additional control hardware and cross-platform integration, simplifying the system architecture for cobots, humanoid robots, industrial robotic arms, and advanced autonomous machines — helping businesses accelerate the transition from proof-of-concept to real-world deployment. Deploying multimodal inference The AIE-KT78/68 integrates compute performance, industrial interfaces, and thermal design into a compact system just 80mm thick, supporting a wide 9–48VDC input range and stable operation across −25°C to +55°C. The system is equipped with USB 3.2, isolated digital I/O, and M.2 expansion slots. It runs Linux with the full NVIDIA AI software stack, including NVIDIA JetPack 7, NVIDIA CUDA, NVIDIA TensorRT, NVIDIA DeepStream, NVIDIA Holoscan, and NVIDIA Isaac ROS, helping developers optimise and deploy multimodal inference, computer vision, sensor fusion, and robotics applications. Fully validated peripheral ecosystem “The competitive edge for cobots and humanoid robots has shifted from the compute performance of a single model to whether a system can integrate perception, reasoning, decision-making, and action in real time in real-world environments,” said Richard Hung, Vice President of Product Division at Aetina. “The AIE KT78/68 transforms the powerful compute capability of NVIDIA Jetson Thor into a compact, mass production-ready system. As an NVIDIA Elite Partner, we combine over a decade of edge AI engineering experience with a fully validated peripheral ecosystem, providing end-to-end technical support — from mechanical design and thermal engineering to BSP and system integration — to help developers and system integrators reduce integration risk and total cost of ownership, accelerate the path from proof-of-concept to scaled deployment, and further realise the return on their automation investment.”

Aetina Corporation, a foremost provider of edge AI solutions and accelerator of edge AI infrastructure, announced the launch of MegaEdge AIP-RQ87, a ready-to-deploy 2U edge agentic AI system designed to help enterprises and system integrators (SIs) rapidly implement AI agent, private LLM, RAG application, multimodal AI, and AI-driven intelligent automation. Powered by Intel® Core™ Ultra processors with high-bandwidth PCIe Gen5 x16 architecture, AIP-RQ87 delivers enterprise-grade AI computing in a compact 2U rackmount design purpose-built for on-premises and edge deployment. Deploying advanced AI workloads As enterprises transition from AI experimentation to production, organisations demand on-premises solutions delivering robust performance, data security, and seamless integration. Traditional AI servers often require complex infrastructure planning, large footprints, and specialised resources. AIP-RQ87 addresses these challenges with a compact 2U chassis, flexible AI accelerator support, high power capacity, exclusive Power Distribution Board (PDB) design, and modular tool-less maintenance—enabling businesses to reduce deployment complexity while efficiently deploying advanced AI workloads where data is generated. Deconstructing heterogeneous edge computing MegaEdge AIP-RQ87 is purpose-built for system integrators, AI developers, research labs, and SMEs, delivering a flexible on-premises AI platform that eliminates the complexity of traditional infrastructure. The system features high-bandwidth, low-latency PCIe Gen5 x16 architecture with support for both NVIDIA RTX PRO 6000 Blackwell Series GPUs and Qualcomm® Cloud AI 100 Ultra accelerators—allowing enterprises to select optimal computing configurations based on workload requirements, power constraints, and budget.AIP-RQ87 integrates Intel® Core™ Ultra 5/7/9 processors with Intel® Q870 chipset, supporting up to 256GB DDR5 memory within a compact 2U footprint (500mm depth). Optimised for private large-parameter LLMs, RAG, and enterprise AI inference, the platform enables deployment of AI agents, multimodal AI, and intelligent automation across verticals—from knowledge assistants and legal compliance to video analytics and smart retail. Proprietary hardware innovations for maximum field reliability To enable stable operation of dual 600W AI accelerators in a compact 2U edge system, AIP-RQ87 incorporates patent-pending hardware innovations and industrial-grade specifications: Proprietary Power Distribution Board (PDB) [Patent Pending]: Aetina’s innovative “cable-free split-circuitry design” disrupts conventional chassis designs plagued by dense cable bundles. By distributing power through a centralised backplane, this architecture optimises delivery to high-wattage accelerators, reduces cable clutter, and enhances stability during sustained high-load operations. Modular Tool-Less GPU and SATA Box Design [Patent Pending]: This service-friendly innovation enables instant tool-free hardware installation, upgrades, and maintenance—significantly reducing mean time to repair (MTTR) while improving service efficiency and deployment flexibility 2000W Power Supply: Integrated industrial-grade high-wattage PSU provides maintainable power capacity for mission-critical AI applications—ideal for smart retail, smart cities, enterprise data centers, and edge nodes requiring continuous operation Featured 1x 10G LAN Port (10GbE): High-speed 10GbE transmission eliminates bandwidth bottlenecks in massive data exchange and distributed machine learning, ensuring millisecond-level responsiveness and optimised AI inference performance. Enabling private AI, intelligent automation and real-time decisions As enterprise AI progresses from proof-of-concept toward scaled deployment, organisations prioritise data sovereignty, deployment efficiency, and long-term operations over model performance alone. For enterprises processing sensitive data internally while minimising cloud dependency, on-premises AI deployment is becoming critical.MegaEdge AIP-RQ87 helps enterprises retain core data internally, reduce cloud transfer costs and latency, and provide controllable computing foundations for private LLMs and AI agents. Key deployment scenarios span three directions: Private AI Knowledge Assistants & Legal Compliance: Integrate product documentation, SOPs, internal knowledge bases, and regulatory data for real-time semantic retrieval and knowledge Q&A. Intelligent Document Processing (IDP) & Business Automation: Support classification, extraction, summarisation, and report generation from contracts, invoices, and business records—enhancing workflow approval and operational efficiency. Financial Industry Applications: Serve as intelligent wealth management advisors, smart regulatory compliance assistants, and financial risk management solutions. Richard Hung, Vice President of Product Division at Aetina, stated: “Enterprise AI competitiveness now extends beyond model capabilities to deployment efficiency, data sovereignty, and long-term operations. Aetina MegaEdge AIP-RQ87’s rapidly deployable 2U edge platform helps enterprises and SIs pragmatically implement private LLMs, AI agents, and intelligent automation—making on-premises AI truly achievable.” Expanding global on-premises AI markets MegaEdge AIP-RQ87 has entered mass production with CE, FCC Class A, and UKCA certifications, ready for global deployment. With AIP-RQ87 joining the MegaEdge PCIe Series, Aetina expands its enterprise-grade edge AI infrastructure portfolio—helping customers build secure, scalable, maintainable on-premises AI environments and accelerate from private LLM adoption to large-scale intelligent automation.

The new AIE-VN34/44 and AIE-VO24/34 combine up to 100 TOPS of AI performance, four GMSL2 camera connections, and fanless rugged operation for transportation, AMR, and industrial automation applications. Aetina Corporation, a pioneer AI solution provider and an accelerator of edge AI infrastructure, announces the DeviceEdge AIE-VN34/44 and AIE-VO24/34, Aetina’s first palm-sized in-vehicle edge AI systems, powered by NVIDIA Jetson Orin NX and NVIDIA Jetson Orin Nano modules. Delivering up to 100 TOPS of AI performance and supporting up to four GMSL2 cameras in an ultra-compact, rugged form factor, the new systems are ready for mass production and target smart transportation, autonomous mobile robots (AMR), and industrial automation deployments where space and reliability are equally critical. Industrial automation deployments 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 persistent challenge. The AIE-VN34/44 and AIE-VO24/34 address this directly: powered by NVIDIA Jetson Orin NX (8GB/16GB) and NVIDIA Jetson Orin Nano with Super Mode (4GB/8GB), the systems deliver up to 100 TOPS and 67 TOPS of AI performance respectively, packed into a palm-sized 136.3 x 132 x 63 mm chassis. Each system features 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. Long-distance image transmission To accelerate system integration, the AIE-VN34/44 and AIE-VO24/34 can be flexibly expanded with Aetina validated GMSL2 adapter boards and camera modules, which support with plug-and-play driver-ready for long-distance image transmission of up to 15 meters. This bundle offering brings together camera sensing, high-speed visual data transmission, and NVIDIA Jetson Orin–powered edge inference, helping customers simplify system integration, shorten development and validation cycles, and achieve highly scalable, customisable AI deployment. Automotive electronic equipment Engineered for demanding mobile and industrial applications, the AIE-VN34/44 and AIE-VO24/34 pair rugged reliability with flexible connectivity. Both systems have passed MIL-STD-810H 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°C to +55°C, while a 9–36V DC wide-voltage input and integrated Ignition Power Control protect against voltage fluctuations and enable safe startup and shutdown. Isolated CAN FD and GPIO/RS-232 interfaces connect vehicle signals, controllers, sensors, and industrial peripherals, complemented by Gigabit Ethernet (GbE), USB 3.2, HDMI, M.2 M-Key storage, and optional M.2 E-Key wireless expansion. Actionable intelligence for AI agents The convergence of V2X and edge computing continues to drive demand for compact, rugged in-vehicle computing platforms that capable of processing multi-camera vision data locally and in real time. The AIE-VN34/44 and AIE-VO24/34 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. AI computing portfolio James Ho, Manager of Edge Computing Product Division at Aetina, stated: “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, Aetina’s palm-sized in-vehicle edge AI systems bring four-camera GMSL2 support, automotive-grade certification, and NVIDIA Elite Partner-backed BSP support together in one rugged multi-vision platform, helping customers simplify integration and accelerate the deployment of intelligent vision at the edge.” The AIE-VN34/44 and AIE-VO24/34 are available now for mass production, supporting BSP built on NVIDIA JetPack 6.2, with NVIDIA JetPack 7.2 support to be added soon.