Advantech Releases Edge AI Inference System
Advantech has expanded its edge AI portfolio with the release of the MIC-735 AI inference system powered by the Nvidia IGX T5000 module.
Key to the development of MIC-735 is Advantech’s partnership with Fort Robotics to integrate their safety architecture. This collaboration with Fort Robotics aims to ensure that robotic and autonomous mobile robot applications can operate with deterministic performance and SIL-certified dependable control.
Important features of the MIC-735 include:
- Integrated functional safety architecture: The MIC-735 is built on the Nvidia IGX Thor solid reference design with integrated functional safety. It also supports direct integration with Fort Robotics’ Nano Safety Controller Pro as well as the Nvidia AI Enterprise-IGX software stack, providing access to Nvidia NIM microservices, Nvidia Isaac’s open models, libraries and frameworks for robotics, Nvidia Metropolis for vision AI and Nvidia Holoscan for real-time sensor processing.
- Sensor synchronization and rugged connectivity: By integrating the Nvidia Holoscan platform, including Holoscan Sensor Bridge technologies for real-time sensing, the MIC-735 enables high-bandwidth, synchronized communication between multiple sensors and AI processors. The system can operate from –30°C to +60°C and offers high-speed connectivity including 5G and SFP28 4x25 GbE. Inputs are securely routed through the Fort Robotics’ Endpoint Controller, which interfaces with the embedded Nano Safety Controller Pro via a specific protocol.
- Real-world robotics deployment: MIC-735 is designed for environments that require real-time, certified e-stop capabilities via secure radio or IP networks, using devices like the Endpoint Controller to send fleet-wide commands, or Fort Robotics’ Safe Remote Control Pro and Wireless E-Stop Pro for local control or command of single autonomous mobile robots as needed.
More automation partnership insights from Automation World:
