These advancements make Jetson Thor the ideal platform for customers integrating AI workloads and applications at the edge. Advantech brings this power to real-world use cases through integrated hardware and software solutions designed for robotics, medical AI, and data-driven AI. Each solution incorporates application-specific hardware platforms pre-integrated with Jetpack 7.0, remote management tools, and vertical software suites such as Robotic Suite and GenAI Studio. Thanks to their container-based architecture, these solutions offer greater flexibility and faster development cycles. In addition to providing boards, systems, and software design services with NVIDIA Jetson Thor for vertical applications, Advantech collaborates with various ecosystem partners on key technologies such as sensor and camera integration, as well as thermal design. This comprehensive approach enables developers to build and deploy edge AI applications faster, easier, and more efficiently, ensuring a seamless and powerful AI experience.
Robotic Controllers for Humanoid Robots, AMRs, and Unmanned Vehicles:
The ASR-A702 and AFE-A702 are robotics-focused controllers specifically designed for humanoid robots, AMRs, and unmanned vehicles. They enable real-time AI reasoning and inference with GPU-accelerated SLAM, compatible with multi-camera GMSL, 2D/3D sensors, and IMUs. Featuring Robotic Suite for plug-and-play development, along with Isaac ROS/Sim and Holoscan for real-time perception and ultra-low-latency data streams, these controllers facilitate rapid integration and deployment. Key features include hardware time synchronization, ESD protection, anti-vibration design, and OTA updates, ensuring stable, safe, and high-performance computing in intelligent logistics, service robotics, and mission-critical unmanned applications.
Medical AI Systems for Surgical Robots, Image Analysis, and Diagnostics:
Leveraging NVIDIA Jetson Thor with advanced SDKs such as Holoscan and MONAI, Advantech is driving the next generation of AI medical boards, the AIMB-294 and the EPC-T5294. These platforms accelerate real-time sensor processing, image analysis, and streaming AI workflows, optimization of pre-trained models and 3D images, and enable low-latency, high-precision surgical robotics applications for operating rooms, clinical workflows, and intelligent diagnostic tools.
The AIR-075 data AI systems for VLM/LLM and multi-camera AI vision analytics offer advanced computing capabilities with 4× 10GbE and GMSL interfaces, designed to meet the demands of data AI in traffic applications and industrial environments. Combined with NVIDIA AI, NVIDIA Metropolis, NVIDIA Triton, NVIDIA Cosmos Reason, and Advantech Edge AI SDK & DeviceOn, it enables sensor fusion, multi-model inference, AI visual agents, and centralized management for real-time predictive edge intelligence.
Advantech Container Catalog
The Advantech Container Catalog (ACC) offers a suite of on-premises AI applications ready for development, including end-to-end machine vision solutions and Edge LLM environments optimized for integrating AI agents on NVIDIA Jetson platforms. It also incorporates partner-specific solutions from ecosystem partners, such as robotic perception, surgical imaging, digital health, and smart city sensing, enabling rapid deployment across industrial and vertical markets. Fully compatible with WEDA (WISE-Edge Developer Architecture), its container-based architecture allows for scalable on-premises AI expansion, from single-node configurations to distributed networks.
