paper-with-me

홈 › Papers

UniPhys: Unified Planner and Controller with Diffusion for Flexible Physics-Based Character Control

2025-04-17 · Yan Wu, Korrawe Karunratanakul, Zhengyi Luo, Siyu Tang

Generating natural and physically plausible character motion remains challenging, particularly for long-horizon control with diverse guidance signals. While prior work combines high-level diffusion-based motion planners with low-level physics controllers, these systems suffer from domain gaps that degrade motion quality and require task-specific fine-tuning. To tackle this problem, we introduce UniPhys, a diffusion-based behavior cloning framework that unifies motion planning and control into a single model. UniPhys enables flexible, expressive character motion conditioned on multi-modal inputs such as text, trajectories, and goals. To address accumulated prediction errors over long sequences, UniPhys is trained with the Diffusion Forcing paradigm, learning to denoise noisy motion histories and handle discrepancies introduced by the physics simulator. This design allows UniPhys to robustly generate physically plausible, long-horizon motions. Through guided sampling, UniPhys generalizes to a wide range of control signals, including unseen ones, without requiring task-specific fine-tuning. Experiments show that UniPhys outperforms prior methods in motion naturalness, generalization, and robustness across diverse control tasks.

📄 PDF Abstract BibTeX arXiv:2504.12540

Code (0)

등록된 구현이 없습니다.

Tasks

Motion Planning

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Flexible Locomotion Learning with Diffusion Model Predictive Control

2025-10-05 · Runhan Huang, Haldun Balim, Heng Yang, Yilun Du arxiv

Legged locomotion demands controllers that are both robust and adaptable, while remaining compatible with task and safety considerations. However, model-free reinforcement learning (RL) methods often yield a fixed policy…

Reinforcement LearningTest-time Adaptation

Online Self-Training for Co-Adaptation in Hierarchical Diffusion Policies

2026-03-05 · Clemence Grislain, Mathilde Kappel, Olivier Sigaud, Mohamed Chetouani arxiv

Hierarchical policies decompose language-conditioned long-horizon robotic manipulation into a high-level planner and a low-level controller. However, effective coordination between HL and LL requires that both components…

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

2024-10-04 · Guy Tevet, Sigal Raab, Setareh Cohan, Daniele Reda 외

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,…

Motion GenerationReinforcement Learning (RL)

RoMoCo: Robotic Motion Control Toolbox for Reduced-Order Model-Based Locomotion on Bipedal and Humanoid Robots

2025-09-23 · Min Dai, Aaron D. Ames arxiv

We present RoMoCo, an open-source C++ toolbox for the synthesis and evaluation of reduced-order model-based planners and whole-body controllers for bipedal and humanoid robots. RoMoCo's modular architecture unifies state…

REFINE-DP: Diffusion Policy Fine-tuning for Humanoid Loco-manipulation via Reinforcement Learning

2026-03-14 · Zhaoyuan Gu, Yipu Chen, Zimeng Chai, Alfred Cueva 외 arxiv

Humanoid loco-manipulation requires coordinated task-space motion planning with stable loco-manipulation command tracking under complex robot-environment dynamics and long-horizon tasks. While diffusion policies (DPs) sh…

Reinforcement Learning