Advantech mentioned its newest methods deliver the facility of NVIDIA’s Jetson Thor platform to real-world functions. | Supply: Advantech
Advantech, a developer of edge computing know-how, launched a brand new lineup of application-focused Edge AI methods powered by NVIDIA Jetson Thor modules. The corporate is concentrating on real-world robotics functions by way of hardware-software built-in methods for robotics, medical AI, and information AI.
Every providing options application-specific {hardware} platforms, pre-integrated with JetPack 7.0, distant administration instruments, and vertical software program suites akin to Robotic Suite and GenAI Studio. Constructed on a container-based structure, these methods supply better flexibility and sooner growth cycles, Advantech mentioned.
Advantech mentioned the NVIDIA Jetson Thor collection set a brand new benchmark for edge AI, delivering as much as 2070 FP4 TFLOPS of AI efficiency, together with important enhancements in CPU efficiency and vitality effectivity.
Along with offering NVIDIA Jetson Thor boards, methods, and software program design-in providers for vertical options, Advantech collaborates carefully with ecosystem companions on key applied sciences akin to sensor and digicam integration, in addition to thermal design. This holistic strategy empowers builders to construct and deploy edge AI functions sooner, extra simply, and extra effectively, the corporate claimed.
Taipei, Taiwan-based Advantech develops IoT clever methods and embedded platforms, with a concentrate on edge computing and edge AI. The firm targets 5 key markets: edge intelligence methods, manufacturing, vitality and utilities, healthcare, and metropolis providers and retail.
Advantech gives robotic controllers for humanoids, AMRs, AVs, and surgical robots
Advantech purpose-built the ASR-A702 and AFE-A702 robotic controllers for humanoids, AMRs, and unmanned automobiles. They ship real-time AI reasoning and inference with GPU-accelerated SLAM, supporting multi-camera GMSL, 2D/3D sensors, and IMUs.
With Robotic Suite for plug-and-play growth, plus Isaac ROS/Sim and Holoscan for real-time notion and ultra-low latency information flows, they permit fast integration and deployment.
Key options embrace {hardware} time sync, ESD safety, anti-vibration design, and OTA upgrades— guaranteeing secure, protected, and high-performance computing throughout good logistics, service robotics, and mission-critical unmanned functions.
By leveraging NVIDIA Jetson Thor with superior SDKs akin to Holoscan and MONAI, Advantech empowers next-generation Medical AI board AIMB-294 and system EPC-T5294. These platforms speed up real-time sensor processing, picture evaluation & streaming AI pipeline, pre-trained mannequin, and 3D imaging optimization, and surgical robotics focus with low latency and excessive precision for working rooms, medical workflows, and clever diagnostic instruments.
Advantech goals to deliver LLMs to the sting
AIR-075 delivers highly effective computing with 4× 10GbE and GMSL interfaces to fulfill Knowledge AI calls for in site visitors and manufacturing unit functions. Mixed with NVIDIA AI, NVIDIA Metropolis, NVIDIA Triton, NVIDIA Cosmos Purpose, and Advantech Edge AI SDK & DeviceOn, it allows sensor fusion, multi-model inference, a visible AI agent, and centralized administration for real-time, predictive edge intelligence.
Advantech Container Catalog (ACC) delivers a cluster of ready-to-develop edge AI functions, together with end-to-end laptop imaginative and prescient and Edge LLM environments optimized for AI agent integration on NVIDIA Jetson platforms. It additionally gives domain-specific options from ecosystem companions—akin to robotics notion, surgical imaging, healthcare, and good metropolis sensing—enabling fast deployment throughout industrial and vertical markets.
Totally appropriate with WEDA (WISE-Edge Developer Structure), its containerized structure allows scalable edge AI growth, from single-node setups to distributed edge networks.
