RealSense and NVIDIA collaborate to usher in the age of physical artificial intelligence

RealSense and NVIDIA announced a collaboration that integrates RealSense depth cameras with NVIDIA Jetson Thor, Isaac Sim and Holoscan Sensor Bridge to accelerate physical Artificial Intelligence for humanoids and autonomous mobile robots. The partnership introduces the RealSense D555 camera with a v5 Vision Processor and native Holoscan streaming and delivers validated system architectures optimized for Jetson Thor.

RealSense, Inc. and NVIDIA announced a strategic collaboration to accelerate physical Artificial Intelligence across humanoid robots and autonomous mobile robots. The initiative links RealSense depth cameras and perception software with NVIDIA robotics platforms, including NVIDIA Jetson Thor for robot run-time computing, NVIDIA Isaac Sim for digital twins and NVIDIA Holoscan Sensor Bridge for ultra-low-latency sensor streaming. The companies position the integration as a way to shorten time to market and scale perception systems into production.

Key product highlights from the announcement include the new RealSense D555 depth camera, which adds a v5 Vision Processor, on-chip Power over Ethernet, native NVIDIA Holoscan Sensor Bridge streaming and an on-camera neural network for enhanced image post-processing. The camera is described as ruggedized and equipped with a global shutter, IMU and native ROS 2 support to provide high-fidelity perception data. On the compute side, Jetson Thor is specified as using a NVIDIABlackwell GPU with 128GB of memory and delivering up to 2070 FP4 teraflops of Artificial Intelligence compute within a 130-watt power envelope. The release compares Jetson Thor to its predecessor, Jetson Orin, citing up to 7.5x higher Artificial Intelligence compute and 3.5x greater energy efficiency.

The collaboration emphasizes native integration for optimal perception performance and validated system architectures optimized for Jetson Thor. Developers will be able to stream true depth and image data directly into Isaac Sim to accelerate prototype-to-deployment cycles, integrate RealSense depth perception with Holoscan Sensor Bridge for real-time sensor fusion and leverage optimized stack configurations for production robotics. RealSense frames the work as advancing physical Artificial Intelligence and accelerating mainstream adoption of intelligent machines. The company is headquartered in Santa Clara, California, and says its mission is to deliver perception systems that safely integrate robotics and Artificial Intelligence into everyday life.

75

Impact Score

NVIDIA renames Maxine to NVIDIA Artificial Intelligence for Media

NVIDIA Maxine has been renamed NVIDIA Artificial Intelligence for Media, a development platform for audio, video, and augmented reality workflows. The platform combines SDKs and cloud-native microservices for real-time media enhancement across local, cloud, and edge deployments.

NVIDIA groq 3 LPX targets low-latency Artificial Intelligence inference

NVIDIA positions Groq 3 LPX as an inference accelerator for Vera Rubin built to handle low-latency, large-context workloads for agentic systems. The platform combines Rubin GPUs and LPUs in a co-designed architecture aimed at boosting throughput, token generation, and efficiency at rack scale.

Nvidia sets the stage for GTC 2026 keynote

Nvidia is preparing to outline its next wave of computing, networking, and rendering plans at GTC 2026, with Jensen Huang leading the keynote. The event is expected to focus on next-generation platforms, broader Artificial Intelligence infrastructure, and the company’s expanding partnership with Intel.

Nvidia chief projects chip sales growth

Nvidia’s chief executive is tied to a projection of massive future Artificial Intelligence chip revenue, but the available source material provides no reported details beyond the headline and a brief author description.

Contact Us

Got questions? Use the form to contact us.

Contact Form

Clicking next sends a verification code to your email. After verifying, you can enter your message.