NXP Semiconductors introduces robotics solutions with NVIDIA for physical AI applications
NXP Semiconductors has introduced a new set of robotics solutions developed in partnership with NVIDIA, targeting real-time data processing and transportation for physical Artificial Intelligence (AI) applications. The solutions prioritize secure and reliable operations, facilitating tasks such as sensor fusion, machine vision, and precise motor control.
The release highlights the operational significance of these technologies in enabling synchronized motion and advanced actuation in robotic systems, especially humanoid robots. These applications demand dependable, low-latency data transport and processing across multiple robotic components to ensure coordinated function and safety.
On the technical front, the solutions integrate NVIDIA's Holoscan Sensor Bridge with NXP's system-on-chip devices. This integration reduces the need for discrete components, which results in smaller physical footprints, lower power consumption, and cost efficiencies. The approach also simplifies software requirements for robotic sensing and actuation processes. Components include the i.MX 95 applications processor and i.MX RT1180 crossover microcontrollers, coordinated via NXP’s S32J Time-Sensitive Networking (TSN) switch. The motor control solution supports industrial protocols such as EtherCAT and provides real-time processing connectivity between the robot's body and brain.
This collaboration facilitates the definition of a uniform architecture for full-body humanoid robotics by combining NXP's edge processing, networking, and safety expertise with NVIDIA's AI infrastructure. The partnership aims to create a scalable and energy-efficient system architecture applicable to next-generation robotics.
Charles Dachs, Executive Vice President and General Manager at NXP, said, “Physical AI is redefining what machines can do in the real world, and humanoid robots represent the most complex expression of that revolution. By combining NXP’s deep expertise in edge processing, secure networking, functional safety and real-time control with NVIDIA robotics platforms, we are greatly simplifying physical AI development, enabling seamless connectivity between the physical AI edge and the central brain. This is just the beginning of what NXP will deliver to accelerate the ecosystem for physical AI.” Deepu Talla, vice president of robotics and edge AI at NVIDIA, said, “The development of autonomous machines requires a high-performance computing architecture that can synchronize complex motor controls with real-time perception. By integrating NVIDIA Holoscan Sensor Bridge into its edge portfolio, NXP is providing developers with a scalable foundation to accelerate the deployment of physical AI.”
The initial solutions featuring Holoscan Sensor Bridge integration, including machine vision and motor control solutions, are scheduled for availability in the first half of 2026. These offerings aim to provide developers with foundational elements for designing and deploying physical AI-based humanoid robotics.