{"data":{"id":785,"lang":"en","title":"Allen Institute Releases MolmoBot — Robots Trained Entirely in Simulation Now Work in the Real World Without Fine-Tuning","summary":"Ai2 releases MolmoBot, a robot manipulation model trained purely in simulation that works on real robots without any fine-tuning.","category":"technology","category_label":"Technology","published_at":"2026-03-14T06:04:09Z","updated_at":"2026-03-14T06:04:09Z","url":"https://techtools.cz/tools/news/article/785-allen-institute-releases-molmobot-robots-trained-entirely-in-simulation-now","api_url":"https://techtools.cz/news-api/v1/articles/785?lang=en","markdown_url":"https://techtools.cz/news-api/v1/articles/785.md?lang=en","image_url":"https://www.datocms-assets.com/64837/1773238621-molmobotheaderimage-1.jpg","word_count":137,"reading_time_minutes":1,"sources":[{"url":"https://allenai.org/blog/molmobot","domain":"allenai.org"},{"url":"https://roboticsandautomationnews.com/2026/03/12/ai2-claims-breakthrough-in-training-robots-entirely-in-simulation/99578/","domain":"roboticsandautomationnews.com"}],"translation":{"lang":"cs","id":806,"title":"Allen Institute vydal MolmoBot — roboti trénovaní čistě v simulaci fungují v reálném světě bez doladění","url":"https://techtools.cz/tools/news/clanek/806-allen-institute-vydal-molmobot-roboti-trenovani-ciste-v-simulaci-funguji-v","api_url":"https://techtools.cz/news-api/v1/articles/806?lang=cs"},"content":"The Allen Institute for AI (Ai2) has released MolmoBot, an open robotic manipulation model trained entirely on synthetic simulation data that transfers directly to real-world robots with zero fine-tuning. The breakthrough challenges a long-held assumption in robotics that virtual training alone is not sufficient for real-world performance.\n\nMolmoBot was trained on 1.8 million simulated robot trajectories spanning over 100,000 environments and 30,000 unique objects. In testing, the model successfully operated a Franka FR3 robotic arm and a Rainbow Robotics RB-Y1 mobile manipulator, performing manipulation tasks on unseen objects without any real-world data collection.\n\nAi2 has open-sourced the entire stack, including MolmoSpaces, a large-scale simulation ecosystem for embodied AI. The release could dramatically reduce the cost and time required to train capable robots, eliminating the expensive real-world data collection bottleneck that has slowed the robotics industry."}}