NVIDIA reports that developer adoption of its AI Aerial and Sionna wireless software has grown tenfold over the past year, with its open-source 5G/6G tools surpassing 1 million downloads and use at more than 8,000 research and academic institutions worldwide, according to a November 6 company blog post.
The company open-sourced its Aerial wireless software a year ago. Together with Sionna, the tools are designed to connect simulation and AI training with experiments on live wireless systems, allowing researchers to test ideas and compare results as they work toward 6G network development.
Researchers at King’s College London connected a camera-equipped robot arm to an NVIDIA Jetson AGX Orin running Sionna to explore goal-oriented semantic communications. Instead of sending full images, the robot transmitted compact descriptions of objects, positions and relationships. In fruit-packing and cube-stacking experiments with deliberately introduced faults, the approach reduced robot task completion time by up to 52.6% and improved task success compared with sending periodic images, according to the researchers. The system also proved more resilient, detecting dropped objects and recovering from unsuccessful actions.