47 Views

MIPS and INOVA unveil physical AI reference platform for robotics

LinkedIn Facebook X
March 12, 2026

Get a Price Quote

MIPS and Inova Semiconductors have collaborated to introduce a new reference platform aimed at expediting the development of robotics and physical AI systems. The platform is specifically designed to streamline the architecture of advanced robotic systems, particularly humanoids, by reducing size, power consumption, and development complexity. This initiative is expected to benefit engineers and developers working on robotics, edge AI, and embedded systems, providing them with a practical blueprint for creating scalable robot control architectures. With the increasing demand for intelligent machines at the edge, the collaboration aims to facilitate faster development cycles and lower system costs for next-generation robotics platforms.

The collaboration has brought together technologies from MIPS, Inova Semiconductors, and manufacturing partner GlobalFoundries to create a robotics control reference platform optimized for physical AI workloads. At its core, the system implements a “sense-think-act-communicate” architecture that is tailored to handle real-time control loops alongside secure AI processing. The platform integrates Inova’s APXpress high-speed interface technology with MIPS’ RISC-V processor portfolio, including the Atlas M8500 high-performance microcontroller processor and the Atlas S8200 AI processor. These components are complemented by MIPS mixed-signal technologies and implemented on GlobalFoundries’ FDX process platform, which is designed for low-power operation.

This approach enables mixed-criticality computing in robotics applications, allowing real-time motion control, AI inference, and secure communications to operate within a unified architecture. MIPS CEO Sameer Wasson stated, “Together with INOVA, we’re delivering a Physical AI reference platform that simplifies robot design, reduces BOM cost, and gives builders an open, standards-based path to create whole product families with low latency and functionally safe connectivity.” The scalable reference platform aims to lower risk, reduce cost, and accelerate time to market for robotics innovations.

The reference design focuses on advanced robotics applications such as multi-axis motion control in robotic arms and humanoid systems. By consolidating multiple data interfaces and supporting various network topologies, the platform aims to simplify the communication backbone required for complex robotics systems. Inova’s expertise in automotive zonal architectures is leveraged in the design, with the APXpress data backbone supporting hundreds of independent data channels with minimal latency, enhancing efficiency in handling large sensor and actuator networks for robotics developers.

INOVA CEO Robert Isele highlighted the significance of the collaboration, stating, “Advanced humanoids demand secure, deterministic connectivity and a scalable control backbone. INOVA, together with GF & MIPS, is providing robot makers with a zonal, RISC-V-based blueprint that reduces complexity and cost, facilitating the scaling of humanoids and advanced robotics from prototype to production at an accelerated pace.” The creation of a reference zonal architecture for advanced robotics is expected to simplify and expedite the development of humanoid and other robotic form factors.

To support early development, the companies are offering access to the platform through the MIPS Atlas Explorer environment, a simulation-based hardware/software co-design platform that enables developers to optimize AI and control software before hardware is available. MIPS and GlobalFoundries are showcasing the platform at Embedded World 2026 in Nuremberg, Germany, demonstrating the potential of the collaboration in advancing the field of robotics and physical AI systems.

Recent Stories


Privacy Overview

This website uses cookies so that we can provide you with the best user experience possible. Cookie information is stored in your browser and performs functions such as recognising you when you return to our website and helping our team to understand which sections of the website you find most interesting and useful.