Syslogic’s RML A5AGX Leverages NVIDIA Jetson AGX Thor for Real-Time Sensor Fusion
August 13, 2026
News
Syslogic introduced the dual-deck RML A5AGX, an AI rugged computer developed for real time sensor fusion. Integrated I/Os allow for direct connections with cameras, LiDAR systems, radar sensors, and in-vehicle sensors. High-speed interfaces such as Automotive Ethernet (Single Pair Ethernet) and Gigabit Ethernet deliver a central building block for sensor fusion and intelligent vision applications at the edge.
The platform supports up to four Single Pair Ethernet (SPE) interfaces engineered for automotive applications. With its SPE technology, the RML A5AGX provides low-latency connectivity for next-generation cameras and other automotive sensors with data rates of up to 1 Gbps.
SPE interfaces are equipped with their own dedicated network interface controller (NIC) for deterministic, parallel processing of multiple sensor streams. When combined with Time-Sensitive Networking (TSN), the solution is ideal for sensor fusion and real-time control applications in autonomous machines.
NVIDIA Jetson Thor
Compute functions leverage NVIDIA's Jetson Thor delivering up to 2,070 FP4 TFLOPS of AI performance. Power consumption is configurable between 40 and 130 watts. According to the press release, the performance allows advanced edge AI workloads that previously required data center infrastructure, including multimodal AI agents, real-time reasoning, generative AI, and autonomous navigation with simultaneous processing of multiple high-resolution sensor streams.
The RML A5AGX is now available with either the NVIDIA Jetson Thor T4000 or Jetson Thor T5000 module. Both have an operating temperature range of –25°C to +60°C and are certified to IP67 and IP69 ingress protection standards making it ideal for constant operation in vehicles, mobile machinery, and autonomous systems.
"Jetson AGX Thor enables sophisticated autonomous reasoning and generative AI directly on mobile machines and robots," says Michael Jung, Product Manager at Syslogic. "Applications that previously depended on data center resources can now be executed directly at the point of operation."
Specifications:
- NVIDIA Jetson Thor T4000, up to 1200 FP4 TFLOPs
- NVIDIA Jetson Thor T5000, up to 2070 FP4 TFLOPs
- 100/1000 BASE-T1 Single Pair Ethernet with 4 dedicated NIC’s
- 2x 10Gbit Ethernet
- 8x GMSL2 camera inputs, with Power over Coax (PoC)
- 2x CAN 2.0A/B, CAN FD support, isolated (optionally up to 6 CAN ports available)
- 1x USB 3.2 (Type-A, IP67 rated)
- Cellular 5G, RTK GNSS & WiFi7
- NVMe SSD storage up to 2TB
For more information, visit syslogic.com/nvidia-jetson-agx-thor.
Chad Cox is the Production Editor at Embedded Computing Design. His responsibilities are centered around content creation, writing and editing, and article research and development. Chad covers industry news and events and is known to interact with various industrial leaders via on-premise visits and online interviews. He is responsible for the digital footprint and dissemination of news via social media posts, advertising creation and the production of newsletters including the Embedded Computing Design’s Daily.
He is well versed in many facets of industrial computing including Edge AI, IoT, Processing, Security, Open Source, and more.
Chad graduated from the University of Cincinnati with a B.A. in Cultural and Analytical Literature and holds a master’s in education.
