Robotics & Physical AI
NXP Launches Modular Robotics Platform for Physical AI Development
Add Unite.AI to your preferred sources on Google
NXP Semiconductors said on November 9, 2026, that its new modular robotics platform for physical AI systems can deliver initial drone functionality within 30 minutes out of the box, using a unified package of processors, open-source software and reference designs.
The company said pre-integrated software and validated subsystem interoperability can cut the months developers often spend integrating and validating robotic subsystems to days or weeks. Its underlying Neural Axis Architecture is a distributed foundation for securely connecting sensing, real-time control, AI processing and communications across robotic systems.
A developer can begin with a motor-control subsystem tested with the SDK, then add AI-based perception, flight control and navigation to build an autonomous drone. The workflow is intended to let teams scale from individual functions to complete physical AI systems in one validated development environment.
Open Software and Drone Hardware
The Robotics SDK supplies supported drivers, middleware integration, reference applications, configuration tools and reusable components. Its listed software includes ROS 2 Jazzy, PX4 autopilot, CogniPilot Cerebri, Zephyr RTOS, NuttX and AM32 electronic-speed-controller firmware, with eIQ Toolkit and Ara SDK for edge-AI work.
Middleware and connectivity support includes Zenoh and rmw_zenoh with zenoh-pico, MAVLink, uORB, DShot, 100BASE-T1 automotive Ethernet and RPMsg inter-core communication. The documented build environment uses Linux with Docker, the west meta-tool, the Arm GNU toolchain, CMake and Ninja, while prebuilt artifacts require a Nexus user token.
NXP’s initial Modular Drone Platform reference designs allocate the main hardware functions as follows:
| Function | Reference design | NXP processor |
|---|---|---|
| Autonomy compute and flight control | NavQ95 | i.MX 95 applications processor |
| Flight management | Tropic VMU/FMU | i.MX RT1064 crossover microcontroller |
| Intelligent sensor networking | 100Base-T1 Sensor Node | MCX N947 microcontroller |
| Motor control | AM32-compliant electronic speed controller | MCX A13 microcontroller |
Each design includes the safety and security enablement of its primary processor, which can be enabled independently of robotics-specific functions. NXP describes the reference designs as interoperable and validated across the complete drone system.
Security, Safety and Product Status
Security and functional safety are central to NXP’s design for robots operating around people. Jerome Legros, the company’s robotics vice president and general manager, identified those properties, real-time control and full-lifecycle reliability as the foundation for trusted physical AI systems.
Orqa CEO and co-founder Srdjan Kovačević emphasized the system-level demands behind that approach: “You need efficient communication between computing elements, predictable behavior and extremely low latency.”
NXP lists the platform, drone reference designs and SDK as available now. The Modular Drone Platform and four associated boards nevertheless carry preproduction labels, and the drone platform’s specifications and other information may change without notice. The current package therefore combines available development resources with hardware that is not yet final.
Expansion Beyond Drones
NXP said future reference designs will address service robots, autonomous mobile robots and other autonomous systems, with additional enablement expected in the second half of 2027. Those machines share requirements for perception, navigation, motor control, connectivity and safe real-time operation.
For robotics developers, the immediate proposition is a common NXP-based route from motor control to autonomous flight. Hardware finalization and expansion to other robot categories are the tangible milestones for judging whether the unified approach extends beyond its initial drone package.
