AMD Says Real-Time Control, Reliability Key to Physical AI

What happened

In an official blog post on Oct. 19, Salil Raje, senior vice president and general manager of AMD's Adaptive and Embedded Computing Group (AECG), said that what robot manufacturers demand most is not the highest AI computing performance, but combining advanced AI models with real-time control capabilities that precisely execute computational results within required time limits, arguing that physical AI performance evaluation should shift from raw computing power toward real-time control and system-wide reliability. AMD proposes a heterogeneous semiconductor architecture: the robot's brain uses a Kria AI system-on-module (SOM) based on Ryzen AI Embedded X100 series processors, Versal Adaptive SoCs serve as the spine, Zynq SoCs control the joints, and Spartan FPGAs handle sensor functions; this architecture forms the basis of AMD's Kria AI solutions for robotics. In third-party testing cited by AMD, the Kria AI SOM achieved AI inference times of less than 0.1 seconds and supported 8,000 control decisions per second; in open navigation benchmark tests, a Ryzen AI Embedded configuration delivered up to 3.4 times greater control timing reliability and up to 1.6 times more available computing headroom than Nvidia's Jetson T5000; and according to Mimic analysis, the configuration supported up to 2.3 times as many simultaneously operating autonomous agents. Foundation Robotics and Generative Bionics are designing products using AMD's Kria AI solutions.

Impact and signal

Affected components and suppliers

Source and time

Source: The Elec · 10/20/2026 · View original source