Runway 开源 Praxis-1，把视频 AI 变成机器人控制器

Runway has released its robot model Praxis-1 with open weights and source code under the Apache 2.0 license. Trained on videos and robot data, the model processes camera images, text instructions, and position data to calculate matching robot movements. Praxis-1 can be adapted to new robot systems through additional training, according to Runway. The model does occasionally confuse similar-looking objects, though, and it can't yet reliably plan complex action sequences on its own. AI company Runway has released its robot model Praxis-1 with open weights and source code. The model uses what it learned from video to control robots and shows promising results in the company's own tests. Runway has released Praxis-1, its AI model for controlling robots. The company first introduced Praxis-1 in late September but initially gave access only to select partners. Alongside the release, Runway published a detailed research report with new performance tests. Runway's model weights and source code are available under the Apache 2.0 license, which allows commercial use. Ad Praxis-1 takes in camera images, text instructions, and information about a robot's position. From those inputs, it predicts how the environment will change and calculates the right robot movements. As new camera frames come in, the model continuously adjusts its control. Ad Praxis-1 builds on a video model that learned how objects move and interact from ordinary footage. Runway then fine-tuned it with videos of human actions and robot data. This approach could reduce the need for expensive robot-specific datasets, which have traditionally been collected just to train these kinds of systems. Runway is best known for generative video models like Gen-4.5 . With Praxis-1, the company is bringing its video research into robotics. Runway calls Praxis-1 a World Action Model that predicts how a scene will change and derives matching robot movements from those predictions. Since September, robotics companies Standard Bots, Noble Machines, and Ultra have been testing Praxis-1 on different systems, including a humanoid robot, an industrial robot arm, and a dual-arm warehouse robot. Ad Praxis-1 still needs some specialized robot data. To adapt it to a Franka robot arm, Runway used about 277 hours of recordings from the public DROID research dataset, according to its research report . Those recordings show robots grasping and moving objects, for example. For a dual-arm robot, the company used between 1,400 and 2,600 hours of training material. Runway had already used DROID data and data from other robot systems during earlier training stages. Whether the approach actually needs less robot data overall than comparable models without general video pretraining is still an open question. On Nvidia's RoboLab-120 leaderboard , Praxis-1 scores a 46.2 percent success rate. The benchmark tests how reliably robot models can sort, grasp, or stack objects across 120 tasks in simulation. FLUX 3 Action , also built as a World Action Model, scores 42.9 percent under the same test conditions. That puts Praxis-1 at the top of the World Action Model category. In the overall leaderboard, it ranks fifth behind two AI agents and two robot models with different architectures. Runway ran all the tests itself, and the results haven't been independently verified yet. Ad After fine-tuning on DROID data, Runway tested the model on a real Franka robot arm. Both models had to complete the same ten tasks, like placing a banana on a plate or closing a drawer. With ten attempts per task, Praxis-1 succeeded 88 times, while FLUX 3 Action managed 80. Ad