Back to Search Start Over

CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control

Authors :
Tevet, Guy
Raab, Sigal
Cohan, Setareh
Reda, Daniele
Luo, Zhengyi
Peng, Xue Bin
Bermano, Amit H.
van de Panne, Michiel
Publication Year :
2024

Abstract

Motion diffusion models and Reinforcement Learning (RL) based control for physics-based simulations have complementary strengths for human motion generation. The former is capable of generating a wide variety of motions, adhering to intuitive control such as text, while the latter offers physically plausible motion and direct interaction with the environment. In this work, we present a method that combines their respective strengths. CLoSD is a text-driven RL physics-based controller, guided by diffusion generation for various tasks. Our key insight is that motion diffusion can serve as an on-the-fly universal planner for a robust RL controller. To this end, CLoSD maintains a closed-loop interaction between two modules -- a Diffusion Planner (DiP), and a tracking controller. DiP is a fast-responding autoregressive diffusion model, controlled by textual prompts and target locations, and the controller is a simple and robust motion imitator that continuously receives motion plans from DiP and provides feedback from the environment. CLoSD is capable of seamlessly performing a sequence of different tasks, including navigation to a goal location, striking an object with a hand or foot as specified in a text prompt, sitting down, and getting up. https://guytevet.github.io/CLoSD-page/

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2410.03441
Document Type :
Working Paper