Texas Instruments has announced a collaboration with NVIDIA to accelerate the safe deployment of humanoid robots in real-world environments. The partnership combines TI’s expertise in real-time motor control, sensing, radar, and power technologies with NVIDIA’s advanced robotics computing, ethernet-based sensing, and simulation capabilities. By integrating these technologies, developers can validate key robotic functions such as perception, actuation, and safety earlier and with greater accuracy. TI’s solutions help bridge NVIDIA’s physical AI computing platforms with real-world systems, delivering deterministic control, sensing, power management, and safety across robotic joints and subsystems. This collaboration aims to help developers move more efficiently from virtual design to scalable, production-ready robotic systems that meet safety standards.
As part of the initiative, TI has developed a sensor fusion solution that integrates its mmWave radar technology with the NVIDIA Jetson Thor platform using the NVIDIA Holoscan Sensor Bridge. The solution enables low-latency, 3D perception and enhanced safety awareness for humanoid robots. TI plans to demonstrate this technology at NVIDIA GTC 2026, scheduled from March 16–19, 2026, in San Jose, California.
Also Read: https://webnewsaddiction.com/tata-elxsi-rolls-out-devstudio-ai-for-automotive-software-innovation/
“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, general manager of industrial automation and robotics at TI. “TI’s comprehensive portfolio bridges the gap between NVIDIA’s powerful AI compute and real-world applications, enabling developers to validate complete humanoid systems earlier in development. This integrated approach will help accelerate the evolution from prototypes to commercially viable humanoid robots operating safely alongside humans.”
“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.”
Enabling safer humanoid robots with real-time sensor fusion technology
Texas Instruments’ mmWave radar sensor, IWR6243 mmWave Radar Sensor, connected via ethernet to NVIDIA Jetson Thor, enables scalable, low-latency 3D perception and enhanced safety awareness for physical AI applications. By combining camera and radar data through sensor fusion, the system improves object detection, localization, and tracking while minimizing false positives. This enables humanoid robots to make more accurate, real-time decisions in dynamic environments.
The solution delivers human-like perception that remains reliable in challenging conditions such as low light, bright glare, fog, or dusty environments, both indoors and outdoors. It also addresses a key safety challenge that has limited the deployment of humanoid robots in real-world settings. For instance, while cameras may struggle to detect transparent or reflective surfaces like glass doors, radar can consistently identify these obstacles, allowing robots to navigate safely in environments such as office buildings, hospitals, and retail spaces.
TI at NVIDIA GTC
TI will present its technologies at NVIDIA GTC in booth 169 at the San Jose McEnery Convention Center. TI and D3 Embedded’s live demonstration, “Real-time sensor fusion for reliable robotic perception with Holoscan,” showcases how TI’s mmWave radar technology integrates with NVIDIA’s Jetson Thor and Holoscan ecosystem using an end-to-end software processing chain and visualization from D3 Embedded.
On Wednesday, March 18 from 3:00-3:40 p.m. PT, TI’s Giovanni Campanella, will participate in a lightning talk, “The Edge of the Edge: Redefining GPU-Enabled AI Sensor Processing.” Campanella will discuss how tight integration of sensing, networking and GPUs is enabling real-time physical AI at the edge of industrial systems.
