NVIDIA CloudXR enables seamless, high-fidelity immersive streaming to extended reality (XR) devices over the network. Developers can use CloudXR with NVIDIA Isaac Lab to build teleoperation workflows that require immersive XR rendering for increased spatial acuity and hand tracking for teleoperation of dexterous robots.
In these workflows, a compatible XR system captures operator head and hand motion. CloudXR sends this data to Isaac Lab, which renders and submits stereo views of the robot simulation to CloudXR. CloudXR then encodes and streams the rendered views back to the XR system for display in realtime using a low-latency, GPU-accelerated pipeline.
This guide provides the Isaac Lab-specific details referenced in the First Run Guide, including installation, CloudXR Runtime configuration, and teleoperation settings.
Prior to using CloudXR with Isaac Lab, please review the following system requirements:
Meta Quest 3 (OS version 79 or later).
If you encounter issues, please see Troubleshooting.