AMD Takes On NVIDIA in Robotics With New Kria Module and X100 Chip
AMD says its new Ryzen AI Embedded X100 processor and Kria system module can outperform NVIDIA's flagship robotics chips. A growing list of robot makers is already switching over.
Key points
- AMD launched the Ryzen AI Embedded X100, a system-on-a-chip designed for robotics, earlier this month.
- AMD claims the Kria AI system-on-module delivers 3.4 times better real-time performance than NVIDIA's Thor T5000 chip.
- Foundation Robotics, a humanoid robot developer, is migrating from Intel and NVIDIA to AMD's X100 platform.
- The Kria module uses COM-HPC, an open industry connector standard, so manufacturers can build compatible hardware without AMD's involvement.
- AMD's robotics partner network includes Open Robotics, Open Navigation, OpenCV, and sensor suppliers.
AMD has a well-known name in PC processors, but its latest announcement targets a very different machine: robots. The company unveiled the Kria AI Robotics platform and the Ryzen AI Embedded X100, a system-on-a-chip (SoC, meaning a single chip combining processor, graphics, and AI compute into one piece of silicon), aimed at factory robots, autonomous mobile robots, and humanoid machines. It's a direct challenge to NVIDIA, which currently dominates this market. Three days earlier, we covered NVIDIA's own push into robotics with Cosmos 3 Edge and a Japanese industrial coalition.
What does the X100 chip actually do differently?
The key change is memory. Traditional robot computers pair a main processor with a separate graphics chip, each holding its own memory pool and constantly passing data back and forth. The X100 places the central processor (CPU), graphics processor (GPU), and AI accelerator (NPU) on one chip, sharing a single memory space. That removes the delays caused by shuffling data between chips.
For a robot, those delays matter. Perceiving an obstacle, fusing sensor data, and deciding how to move all happen in milliseconds, so shaving time off each step adds up.
AMD says the chip hits an interrupt latency (the delay before a chip reacts to a signal) below seven microseconds at high reliability levels. For hard real-time tasks, it recommends pairing the X100 with a Zen hypervisor and FreeRTOS, two software tools that isolate critical tasks from everything else running on the chip.
How does AMD compare to NVIDIA on paper?
AMD's numbers, presented at the launch, are pointed. According to the company, the Kria AI module delivers:
| Metric | AMD claim vs. NVIDIA Thor T5000 |
|---|---|
| Real-time performance | 3.4x better |
| Spare compute headroom | 1.6x more |
| Agentic AI capacity | 2.3x more |
| FP32 signal-processing compute | 3x better than NVIDIA Thor |
Those figures come from AMD, not independent testers, so treat them as a starting point rather than settled fact.
What is the Kria module, and why does the open standard matter?
The Kria AI SoM (system-on-module, a small self-contained board that slots into a larger device) is built on the X100. It uses the COM-HPC connector standard rather than a proprietary one AMD controls, so a robot maker isn't locked into AMD-only hardware.
"We don't want to have a proprietary form factor," said KV Thanjuvar Bhaaskar, robotics lead at AMD. Any company can build a compatible carrier board using publicly available schematics.
A development kit ships with the module, including high-speed camera connectors, an inertial measurement unit (a sensor tracking movement and orientation), Wi-Fi, Bluetooth, an on-board FPGA (a reprogrammable chip for real-time safety tasks), and open-source baseboard schematics.
Should you watch for anything beyond the press release?
AMD's performance claims need independent confirmation before robot makers stake production lines on them. Foundation Robotics' migration from NVIDIA to the X100 is the most concrete early test: if it goes smoothly, expect more humanoid developers to take a serious look. Castec International is using the platform for a semiconductor factory robot, giving AMD a second industrial reference point.
The pattern here is worth noting. AMD is now pressing NVIDIA on data centres and robotics simultaneously. Whether the software ecosystem catches up to the hardware claims is the thing to watch.
