Hesai has launched Kosmo, a 3D world data engine designed to turn real environments into reusable training data for robots and physical-AI models. The system combines the Kosmo One spatial camera with the Kosmo World cloud platform, giving developers a way to capture, reconstruct and manage detailed 3D spaces.
In its October 14 launch announcement, Hesai says Kosmo combines lidar, high-resolution imaging and 3D Gaussian Splatting. The company says a typical 100-square-meter indoor space can be scanned in about 15 minutes, while reconstruction can be up to five times faster than comparable workflows under similar conditions.
Hesai provides a first look at Kosmo and its spatial-intelligence hardware.
Reuters reports that Hesai is positioning the platform as infrastructure for humanoid-robot training, where high-quality spatial data remains a bottleneck. Hesai also announced partnerships with Galbot and Dexmal and showed workflows involving Pixar RenderMan and Amap.
The launch fits a broader move toward richer real-world data for robotics. BitcoinVersus.Tech recently covered NEURA’s multimodal robot model, Lantronix Spotter for autonomous robots and Ubitium’s physical-AI processor work. Hesai’s key claim is that better 3D capture can make those systems easier to train against realistic environments.
BitcoinVersus.Tech Editor’s Note:
We volunteer daily to ensure the credibility of the information on this platform is Verifiably True. If you would like to support to help further secure the integrity of our research initiatives, please donate using the QR code provided
For best QR-code scanning results, please scan this donation code from a desktop or larger screen. Mobile screens may prevent camera recognition.
BitcoinVersus.Tech provides technical education and analysis for informational purposes only.
Leave a Reply