Texas Instruments announced a collaboration with NVIDIA to support the transition from simulation to real-world deployment of humanoid robots. The partnership combines TI's real-time motor control, sensing, radar, and power technologies with NVIDIA's robotics compute, Ethernet-based sensing, and simulation technologies. This integration allows robotics developers to validate perception, actuation, and safety functions earlier in the development process. TI connects NVIDIA's physical AI compute to real-world applications through deterministic control, sensing, power, and safety mechanisms at joints and subsystems.
A key element of the collaboration is TI's sensor fusion solution, which integrates its mmWave radar technology specifically the IWR6243 sensor with NVIDIA Jetson Thor via NVIDIA Holoscan Sensor Bridge. This setup provides low-latency 3D perception and safety awareness for physical AI applications in humanoid robots.
By fusing camera and radar data, the solution enhances object detection, localization, and tracking while reducing false positives to support real-time decision-making. The radar enables reliable detection in challenging conditions, including low light, glare, fog, dust, and transparent obstacles like glass doors, addressing limitations in camera-only systems for environments such as offices, hospitals, and retail spaces.
TI will demonstrate its semiconductor technologies for humanoid robots at NVIDIA GTC, scheduled for March 16–19, 2026, in San Jose, California. The exhibit will be at booth 169 in the San Jose McEnery Convention Center, featuring a live demonstration titled “Real-time sensor fusion for reliable robotic perception with Holoscan,” developed with D3 Embedded. This includes an end-to-end software processing chain and visualization.
On March 18, from 3:00–3:40 p.m. PT, TI’s Giovanni Campanella, general manager of industrial automation and robotics at TI, will deliver a lightning talk titled “The Edge of the Edge: Redefining GPU-Enabled AI Sensor Processing.” The presentation will cover tight integration of sensing, networking, and GPUs for real-time physical AI at the edge in industrial systems. "The next generation of physical AI requires more than just advanced compute it demands seamless integration between sensing, control, power and safety systems," said Giovanni Campanella.
“The safe operation of humanoid robots in unpredictable environments requires a massive leap in processing power to synchronize complex AI models with real-time sensor data and motor controls,” said Deepu Talla, vice president of robotics and edge AI at NVIDIA. “The integration of Texas Instruments’ sensing and power management technologies with the NVIDIA Jetson Thor platform provides developers with a functional safety-capable foundation to accelerate the deployment of next-generation physical AI.”
