Get the latest tech news
Diffuse-CLoC: Guided Diffusion for Physics-Based Character Look-Ahead Control
A guided diffusion framework for physics-based look-ahead control that enables intuitive, steerable, and physically realistic motion generation through joint state-action modeling.
We present Diffuse-CLoC, a guided diffusion framework for physics-based look-ahead control that enables intuitive, steerable, and physically realistic motion generation. In contrast, recent diffusion-based control policies have shown promise in generating physically realizable motion sequences, but the lack of kinematics prediction limits their steerability. Our method handles a diverse set of unseen long-horizon downstream tasks through a single pre-trained model, including static and dynamic obstacle avoidance, motion in-betweening, and task-space control.
Or read this on Hacker News
