RealSense collaborates with NVIDIA to integrate Jetson Thor and simulation platforms on AI depth cameras

Physical AI capabilities enable breakthroughs on humanoids, AMRs and intelligent machines

By Robotics 24/7 Staff August 25, 2025

RealSense

The RealSense and NVIDIA collaboration will integrate RealSense AI depth cameras with NVIDIA Jetson Thor and simulation platforms.

Email Sign Up

Get news, papers, media and research delivered. Sign up for our free newsletters.

Stay up-to-date with news and resources you need to do your job. Research industry trends, compare companies and get weekly market intelligence with Robotics 24/7.

AI-powered computer vision perception technology developer RealSense announced a strategic collaboration with NVIDIA to accelerate the adoption and capabilities of physical AI across humanoids and autonomous mobile robots (AMRs).

RealSense said the initiative integrates the company’s industry-leading AI depth cameras with NVIDIA’s breakthrough robotics platforms, including the NVIDIA Jetson Thor Series for robot run-time computing, NVIDIA Isaac Sim for digital twins to rapidly close the gap from prototype to production and NVIDIA Holoscan Sensor Bridge for ultra-low-latency sensor streaming.

Technology highlights of the RealSense, NVIDIA collaboration

By combining RealSense’s advanced perception technology with NVIDIA Jetson Thor’s AI compute, RealSense said the collaboration will enable robotics developers to shorten time to market, discover new applications and scale safely into production.

Native integration ensures optimal perception performance, delivering the high-fidelity sensor data and processing speed required to accelerate next-generation humanoids and autonomous machines.

RealSense highlighted the following technological elements of the announcement:

The new RealSense D555 depth camera introduces the company’s new v5 Vision Processor and on-chip Power over Ethernet (PoE), delivering native NVIDIA Holoscan Sensor Bridge streaming and on-camera neural network to enable enhanced image post-processing. Its ruggedized design, global shutter, IMU and native ROS 2 support ensure high-fidelity perception data for humanoid robotics and beyond.
Powered by the NVIDIABlackwell GPU and featuring 128GB of memory, Jetson Thor delivers up to 2070 FP4 teraflops of AI compute to effortlessly run the latest generative AI models - all within a 130-watt power envelope. Compared with its predecessor, NVIDIA Jetson Orin, Jetson Thor delivers up to 7.5x higher AI compute and 3.5x greater energy efficiency.

“This initiative cements RealSense’s role as the perception platform of choice for AMRs and humanoids,” said Nadav Orbach, CEO of RealSense. “By providing native integration and performance optimizations with NVIDIA Thor and Holoscan Sensor Bridge, we are accelerating the mainstream adoption of physical AI. Together, we are enabling the robotics industry to unlock the extraordinary potential of physical AI and drive the future of intelligent machines.”

RealSense said the collaboration highlights the company’s commitment to advancing physical AI by ensuring seamless perception integration into NVIDIA’s next-generation robotics stack.

Thanks to this collaboration, RealSense said that developers will now be able to:

Stream native true depth and image data directly into NVIDIA Isaac Sim, dramatically accelerating the path from prototype to deployment.
Leverage fully validated system architectures optimized for NVIDIA Jetson Thor to ensure maximum performance for robotics and physical AI applications.
Integrate RealSense depth perception with the NVIDIA Holoscan Sensor Bridge for real-time sensor fusion and ultra-low-latency data streaming.

Latest in Integration

Latest in Artificial Intelligence

Latest Robotics News

Robotics 24/7

RealSense collaborates with NVIDIA to integrate Jetson Thor and simulation platforms on AI depth cameras