en.Wedoany.com Reported - Industrial IoT provider Advantech has announced an expanded partnership with NVIDIA, jointly launching an AI-based factory architecture focused on Agentic AI and Physical AI applications. The architecture integrates NVIDIA NeMoClaw, NVIDIA Factory Operations Blueprint, NVIDIA RTX PRO, NVIDIA Jetson Thor, and Advantech's WISE-Edge Developer Architecture, aiming to help manufacturers apply AI in real-time factory operations to enhance production flexibility, workforce management, and energy efficiency.
Within this architecture, Advantech has introduced the AI Factory Brain, a multi-agent system built around factory management agents, leveraging the NVIDIA Factory Operations Blueprint. This system can monitor anomalies, identify potential root causes, and coordinate responses between software agents and human operators. The solution is based on the NVIDIA accelerated computing platform and uses MIC and ICAM edge devices powered by NVIDIA IGX Thor, NVIDIA Jetson Thor, and NVIDIA Jetson Orin to collect data from enterprise systems (such as SAP, MES, and WMS) and edge sensors. Advantech utilizes NVIDIA NeMoClaw, NVIDIA Omniverse, NVIDIA Metropolis, and NVIDIA Isaac Sim to support workflow automation, energy management, and production analysis.
For inspection and process monitoring, Advantech's ICAM-540 camera and MIC-743-AT platform, powered by NVIDIA Jetson Orin NX and NVIDIA Jetson Thor, support AI-based automated optical inspection and the deployment of local large language model (LLM) or vision language model (VLM) chatbots. These systems can be used for defect detection, production monitoring, and natural language interaction in factory environments. For logistics and warehouse operations, Advantech's AIR-427A platform (based on NVIDIA IGX Thor) and AFE-A702 platform (based on NVIDIA Jetson Thor) provide AI computing capabilities for forklifts, humanoid robots, autonomous mobile robots (AMRs), and mobile manipulators, supporting navigation, robotic manipulation, material handling, and coordination.
In terms of security, the architecture integrates safety, access control, and operational governance functions through NVIDIA NeMoClaw, which includes the NVIDIA OpenShell runtime and policy framework. The MIC-735-IT and AIR-427A platforms, based on NVIDIA IGX Thor, also provide functional safety AI computing for humanoid robots and autonomous industrial systems.
Advantech has tested the architecture in its own manufacturing operations through two AI agent pilots. The iEnergy Agent is designed to manage energy by comparing production schedules with visual AI data and SCADA systems to control HVAC and lighting. Advantech expects a 10% reduction in total factory energy consumption after full deployment. Another pilot, the Production Line Efficiency Agent, uses visual AI to collect real-time assembly line data, analyze productivity metrics, identify anomalies and bottlenecks, and generate recommendations and shift reports. Advantech reports that the system improved assembly line productivity by 12% over approximately six months of deployment.
Advantech plans to continue expanding its edge AI and accelerated computing portfolio for applications in smart manufacturing, automated optical inspection, industrial robots, warehouse automation, autonomous logistics, and digital twin deployments.
This article is compiled by Wedoany. All AI citations must indicate the source as "Wedoany". If there is any infringement or other issues, please notify us promptly, and we will modify or delete it accordingly. Email: news@wedoany.com
