IntroducingRunway Robotics
The Runway Robotics platform brings GWM-1 to your robot learning pipeline. Run policy inference from camera observations, evaluate policies through photorealistic simulation, and augment training data — no specialized compute infrastructure required to get started.
A complete toolkit for robot learning.
From policy inference and evaluation to synthetic data generation, every component is powered by GWM-1, our state-of-the-art General World Model. Pick the surface you need — we'll work with you to fit it to your hardware.
Policy Model
Control your robot with Runway's General World Model. GWM-1 predicts actions from live observations — custom fine-tuned for your specific hardware, environment, and tasks.
Learn moreVideo Model Licensing
License GWM-1 as the diffusion backbone for training custom policy models. Deploy on your own infrastructure with full control over fine-tuning.
Learn moreOffline Policy Evaluation
Submit action sequences and camera observations to simulate policy rollouts in GWM-1. Surface failure modes before deploying to hardware.
Learn moreData Augmentation
Transform existing trajectories into new environments, lighting conditions, and object configurations. Expand your training distribution without collecting more data.
Learn more