qixing: NXP and NVIDIA Launch Innovative Solution for Advanced Physical AI

San Jose, CA – March 17, 2026 – NXP Semiconductors N.V. (NASDAQ: NXPI) announced an innovative robotics solution that provides reliable, secure real-time data processing and transmission, as well as advanced networking capabilities, supporting sensor fusion, machine vision, and precision motor control. As the first result of NXP’s portfolio of foundational robotics solutions, this deployable solution, jointly developed by NXP and NVIDIA, combines the NVIDIA Holoscan Sensor Bridge with NXP’s highly integrated System-on-Chip (SoC). This solution reduces the number of discrete components, significantly reduces footprint, lowers power consumption and cost, while simplifying the software complexity of robot perception and execution, and is also applicable to humanoid robot forms.
Physical AI represents the next frontier of innovation, characterized by systems that can accurately, reliably, and safely perceive, understand, and interact with their environment. Humanoid robots represent one of the most advanced forms of physical AI, requiring secure, reliable, and low-latency data processing and transmission throughout the robot's body to achieve synchronized motion, high-density sensor fusion, and advanced actuation control.
NXP's newly launched integrated robot body solutions address this challenge by providing powerful edge intelligence and low-latency network connectivity for secure and reliable real-time communication. These solutions seamlessly integrate NVIDIA Holoscan Sensor Bridge into NXP's software enablement architecture, allowing developers to easily implement real-time processing and establish direct transmission paths between the robot body and pre-defined areas of its "brain," significantly reducing latency. This significantly simplifies the challenges of bringing AI into the physical world, with real-time decision-making being a key requirement.
Charles Dachs, Executive Vice President and General Manager of the Secure Connected Edge Business Unit at NXP Semiconductors, stated, “Physical AI is redefining the capabilities of machines in the real world, and humanoid robots represent the most complex manifestation of this transformation. By combining NXP’s deep expertise in edge processing, secure networking, functional safety, and real-time control with NVIDIA’s robotics platform, we are significantly simplifying the development process for physical AI, enabling seamless connectivity between the physical AI edge and the central brain. In the future, NXP will bring more groundbreaking innovations to accelerate the development of the physical AI ecosystem; the achievements showcased today are just the tip of the iceberg.”
Deepu Talla, Vice President of Robotics and Edge AI at NVIDIA, stated, “The development of autonomous machines requires a high-performance computing architecture to synchronize complex motor control with real-time perception. By integrating the NVIDIA Holoscan Sensor Bridge into its edge product portfolio, NXP provides developers with a scalable foundational platform to accelerate the deployment of physical AI.”
NXP and NVIDIA are working closely together to help define a unified architecture suitable for full-body humanoid robots. NXP's edge processors, motor control MCUs, automotive-grade networking technology, high-throughput asymmetric data transfer capabilities acquired through the acquisition of Aviva Links, and functional safety expertise built on decades of experience in the automotive industry, combined with NVIDIA's AI infrastructure, create a flexible, energy-efficient system architecture for next-generation robots.
The first solutions in NXP's robotics portfolio to support the Holoscan Sensor Bridge include a machine vision solution based on the i.MX 95 application processor, which transmits high-bandwidth data to the robot's "brain"; and a motor control solution based on the i.MX RT1180 crossover MCU kinematics chain, aggregated by an NXP S32J TSN switch and directly connected to the "brain." This motor control solution integrates support for mainstream industrial protocols such as EtherCAT® and Time-Sensitive Networking (TSN). These flexible, software-driven solutions employ a highly integrated design that effectively reduces footprint, power consumption, and cost without sacrificing performance, functional safety, or information security, providing a complete and scalable foundational platform for the design of full-body humanoid robots.
looking for IGBT modules such MIG50J201HC and 40MT120UHA, igbtexpress.com have more than 300 thousand parts you can choose.