paper-with-me

홈 › Papers

PFM-HR: Pose Flow Matching for Humanoid Robots

2026-08-04 · Yukang Gao, Yi Gu, Yangchen Zhou, Xingyu Chen, Zhaorui Wang, Fanghai Zhang, Hanyang Cao, Zhengyang Shen, Ji Ma, Runhan Zhang, Lei Han, Renjing Xu arxiv

Motion priors improve reinforcement learning for physics-based humanoid tracking, but temporal priors require ordered motion clips, while pose priors provide limited guidance for policy-induced pose transitions. We present Pose Flow Matching for Humanoid Robots (PFM-HR), a reusable flow matching prior trained directly on large scale unordered pose data. PFM-HR introduces the Pose Geometry Score (PGS), which quantifies how joint coordinate changes during rollouts align with the local geometry of pose variation captured by the prior. Using PGS to modulate the tracking reward guides policy exploration toward structured pose changes while keeping the prior frozen across tracking tasks. Experiments demonstrate that PFM-HR improves both single motion and general motion tracking, especially for highly dynamic motions.

📄 PDF Abstract BibTeX arXiv:2608.03227

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

PhysiFlow: Physics-Aware Humanoid Whole-Body VLA via Multi-Brain Latent Flow Matching and Robust Tracking

2026-03-05 · Weikai Qin, Sichen Wu, Ci Chen, Mengfan Liu 외 arxiv

In the domain of humanoid robot control, the fusion of Vision-Language-Action (VLA) with whole-body control is essential for semantically guided execution of real-world tasks. However, existing methods encounter challeng…

Humanoid World Models: Open World Foundation Models for Humanoid Robotics

2025-06-01 · Muhammad Qasim Ali, Aditya Sridhar, Shahbuland Matiana, Alex Wong 외

Humanoid robots have the potential to perform complex tasks in human centered environments but require robust predictive models to reason about the outcomes of their actions. We introduce Humanoid World Models (HWM) a fa…

HAF: Adapting Generalist VLAs to Humanoid Whole-Body Loco-manipulation via Hierarchical Action Flow and Spectral Latent RL

2026-08-17 · Langzhe Gu, Chengkai Hou, Meng Li, Xinhua Wang 외 arxiv

Humanoid robots hold great promise as general-purpose agents in human-centered environments, yet generalist vision-language-action (VLA) foundation models are not readily applicable to humanoid whole-body loco-manipulati…

Dimensionality ReductionReinforcement Learning

Flow Policy Gradients for Robot Control

2026-02-02 · Brent Yi, Hongsuk Choi, Himanshu Gaurav Singh, Xiaoyu Huang 외 arxiv

Likelihood-based policy gradient methods are the dominant approach for training robot control policies from rewards. These methods rely on differentiable action likelihoods, which constrain policy outputs to simple distr…

SENTINEL: A Fully End-to-End Language-Action Model for Humanoid Whole Body Control

2025-11-24 · Yuxuan Wang, Haobin Jiang, Shiqing Yao, Ziluo Ding 외 arxiv

Existing humanoid control systems often rely on teleoperation or modular generation pipelines that separate language understanding from physical execution. However, the former is entirely human-driven, and the latter lac…