Taiwanese edge computing firm Advantech has introduced a line of application-focused edge AI products powered by Nvidia Jetson Thor modules for medical AI applications.

The Nvidia Jetson Thor series delivers up to 2070 FP4 TFlops of AI performance, along with significant improvements in CPU performance and energy efficiency.

These target real-world applications through hardware-software integration for robotics, medical AI and data AI.

Each features application-specific hardware platforms, pre-integrated with JetPack 7.0, remote management tools and vertical software suites such as Robotic Suite and GenAI Studio. Built on a container-based architecture, they offer flexibility and faster development cycles.

In addition, Advantech collaborates closely with ecosystem partners on technologies such as sensor and camera integration, as well as thermal design.

By leveraging Nvidia Jetson Thor with SDKs such as Holoscan and Monai, Advantech empowers medical AI board AIMB-294 and system EPC-T5294. These platforms accelerate real-time sensor processing, image analysis and streaming AI pipeline, pre-trained model and 3D imaging optimisation, and surgical robotics with low latency and precision for operating rooms, clinical workflows and intelligent diagnostic tools.

The ASR-A702 and AFE-A702 are purpose-built robotic controllers for humanoids, AMRs and unmanned vehicles. They deliver real-time AI reasoning and inference with GPU-accelerated SLAM, supporting multi-camera GMSL, 2D and 3D sensors, and IMUs. With Robotic Suite for plug-and-play development, plus Isaac ROS/Sim and Holoscan for real-time perception and low latency data flows, they enable rapid integration and deployment. Features include hardware time sync, ESD protection, anti-vibration design and OTA upgrades.

The AIR-075 has four 10GbE and GMSL interfaces to satisfy data AI demands in traffic and factory applications. Combined with Nvidia AI, Metropolis, Triton and Cosmos Reason, and Advantech edge AI SDK and DeviceOn, it enables sensor fusion, multi-model inference, visual AI agent and centralised management for real-time, predictive edge intelligence.

The Advantech (www.advantech.com) ACC container catalogue delivers a cluster of ready-to-develop edge AI applications, including end-to-end computer vision and edge LLM environments optimised for AI agent integration on Nvidia Jetson platforms. It also offers domain-specific options from ecosystem partners. Compatible with WEDA (Wise-Edge Developer Architecture), its containerised architecture enables scalable edge AI expansion, from single-node setups to distributed edge networks.