Diffuse-CLoC: Guided Diffusion for Physics-based Character Look-ahead Control

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Huang, Xiaoyu, Truong, Takara, Zhang, Yunbo, Yu, Fangzhou, Sleiman, Jean Pierre, Hodgins, Jessica, Sreenath, Koushil, Farshidian, Farbod
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912519307657216
author Huang, Xiaoyu
Truong, Takara
Zhang, Yunbo
Yu, Fangzhou
Sleiman, Jean Pierre
Hodgins, Jessica
Sreenath, Koushil
Farshidian, Farbod
author_facet Huang, Xiaoyu
Truong, Takara
Zhang, Yunbo
Yu, Fangzhou
Sleiman, Jean Pierre
Hodgins, Jessica
Sreenath, Koushil
Farshidian, Farbod
contents We present Diffuse-CLoC, a guided diffusion framework for physics-based look-ahead control that enables intuitive, steerable, and physically realistic motion generation. While existing kinematics motion generation with diffusion models offer intuitive steering capabilities with inference-time conditioning, they often fail to produce physically viable motions. 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. Diffuse-CLoC addresses these challenges through a key insight: modeling the joint distribution of states and actions within a single diffusion model makes action generation steerable by conditioning it on the predicted states. This approach allows us to leverage established conditioning techniques from kinematic motion generation while producing physically realistic motions. As a result, we achieve planning capabilities without the need for a high-level planner. 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. Experimental results show that our method significantly outperforms the traditional hierarchical framework of high-level motion diffusion and low-level tracking.
format Preprint
id arxiv_https___arxiv_org_abs_2503_11801
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Diffuse-CLoC: Guided Diffusion for Physics-based Character Look-ahead Control
Huang, Xiaoyu
Truong, Takara
Zhang, Yunbo
Yu, Fangzhou
Sleiman, Jean Pierre
Hodgins, Jessica
Sreenath, Koushil
Farshidian, Farbod
Graphics
Machine Learning
Robotics
We present Diffuse-CLoC, a guided diffusion framework for physics-based look-ahead control that enables intuitive, steerable, and physically realistic motion generation. While existing kinematics motion generation with diffusion models offer intuitive steering capabilities with inference-time conditioning, they often fail to produce physically viable motions. 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. Diffuse-CLoC addresses these challenges through a key insight: modeling the joint distribution of states and actions within a single diffusion model makes action generation steerable by conditioning it on the predicted states. This approach allows us to leverage established conditioning techniques from kinematic motion generation while producing physically realistic motions. As a result, we achieve planning capabilities without the need for a high-level planner. 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. Experimental results show that our method significantly outperforms the traditional hierarchical framework of high-level motion diffusion and low-level tracking.
title Diffuse-CLoC: Guided Diffusion for Physics-based Character Look-ahead Control
topic Graphics
Machine Learning
Robotics
url https://arxiv.org/abs/2503.11801