TI and NVIDIA team up to accelerate humanoid robot safety

Collaboration between Texas Instruments (TI) and NVIDIA is set to revolutionize the development and deployment of humanoid robots. By combining sensing, real-time control, and AI compute technologies, the partnership aims to accelerate the transition of robotics developers from simulation to real-world applications. This collaboration underscores the increasing importance of semiconductor integration and sensor fusion as fundamental components for the advancement of next-generation robotics and physical AI systems.

The focus of the collaboration lies in the integration of TI’s sensing, control, and power technologies with NVIDIA’s robotics computing and simulation platforms. This strategic alignment aims to create a seamless ecosystem that empowers developers to enhance the capabilities of humanoid robots efficiently. The announcement signifies a significant step towards bridging the gap between theoretical simulations and practical implementation in the field of robotics.

Sensor Fusion Enhances Perception and Safety

One of the key outcomes of the collaboration is the integration of TI’s mmWave radar technology with NVIDIA’s Jetson Thor platform through the Holoscan Sensor Bridge. This integration results in a sensor-fusion system that enables low-latency 3D perception and enhances safety awareness for humanoid robots. By combining radar and camera data, the system improves object detection, localization, and tracking accuracy while minimizing false positives.

Radar technology plays a crucial role in enhancing reliability, especially in environments where traditional cameras face challenges. For instance, radar can effectively detect transparent or reflective surfaces like glass doors, which may pose obstacles for camera-based systems. This capability is essential for enabling robots to navigate safely in diverse settings such as offices, hospitals, and retail spaces.

Giovanni Campanella, the general manager of industrial automation and robotics at Texas Instruments, emphasized the importance of seamless integration between sensing, control, power, and safety systems for the next generation of physical AI. This comprehensive approach not only accelerates the development process but also ensures the validation of complete humanoid systems at an early stage. The collaboration between TI and NVIDIA is poised to expedite the evolution of prototypes into commercially viable humanoid robots that can operate alongside humans safely.

Deepu Talla, the vice president of robotics and edge AI at NVIDIA, highlighted the critical need for advanced processing power to enable humanoid robots to operate safely in dynamic environments. The integration of Texas Instruments’ sensing and power management technologies with the NVIDIA Jetson Thor platform provides developers with a robust foundation that supports functional safety capabilities. This integration is expected to streamline the deployment of next-generation physical AI systems, marking a significant advancement in the field of robotics.

Technology Showcase at NVIDIA GTC 2026

TI is gearing up to showcase the collaborative technology at NVIDIA GTC, scheduled to take place from March 16–19, 2026, in San Jose, California. The live demonstration, developed in partnership with D3 Embedded, will highlight real-time sensor fusion using TI’s mmWave radar integrated with the Jetson Thor platform and the Holoscan ecosystem. Additionally, Campanella will deliver a lightning talk at the event titled “The Edge of the Edge: Redefining GPU-Enabled AI Sensor Processing,” shedding light on the transformative potential of tighter integration between sensing, networking, and GPUs in enabling real-time physical AI at the edge of industrial systems.