Saved in:
Bibliographic Details
Main Authors: Jing, Tan, Chen, Shiting, Li, Yangfan, Xu, Weisheng, Xu, Renjing
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.19926
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908506152501248
author Jing, Tan
Chen, Shiting
Li, Yangfan
Xu, Weisheng
Xu, Renjing
author_facet Jing, Tan
Chen, Shiting
Li, Yangfan
Xu, Weisheng
Xu, Renjing
contents Unified physics-based humanoid controllers are pivotal for robotics and character animation, yet models that excel on gentle, everyday motions still stumble on explosive actions, hampering real-world deployment. We bridge this gap with FARM (Frame-Accelerated Augmentation and Residual Mixture-of-Experts), an end-to-end framework composed of frame-accelerated augmentation, a robust base controller, and a residual mixture-of-experts (MoE). Frame-accelerated augmentation exposes the model to high-velocity pose changes by widening inter-frame gaps. The base controller reliably tracks everyday low-dynamic motions, while the residual MoE adaptively allocates additional network capacity to handle challenging high-dynamic actions, significantly enhancing tracking accuracy. In the absence of a public benchmark, we curate the High-Dynamic Humanoid Motion (HDHM) dataset, comprising 3593 physically plausible clips. On HDHM, FARM reduces the tracking failure rate by 42.8\% and lowers global mean per-joint position error by 14.6\% relative to the baseline, while preserving near-perfect accuracy on low-dynamic motions. These results establish FARM as a new baseline for high-dynamic humanoid control and introduce the first open benchmark dedicated to this challenge. The code and dataset will be released at https://github.com/Colin-Jing/FARM.
format Preprint
id arxiv_https___arxiv_org_abs_2508_19926
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FARM: Frame-Accelerated Augmentation and Residual Mixture-of-Experts for Physics-Based High-Dynamic Humanoid Control
Jing, Tan
Chen, Shiting
Li, Yangfan
Xu, Weisheng
Xu, Renjing
Robotics
Unified physics-based humanoid controllers are pivotal for robotics and character animation, yet models that excel on gentle, everyday motions still stumble on explosive actions, hampering real-world deployment. We bridge this gap with FARM (Frame-Accelerated Augmentation and Residual Mixture-of-Experts), an end-to-end framework composed of frame-accelerated augmentation, a robust base controller, and a residual mixture-of-experts (MoE). Frame-accelerated augmentation exposes the model to high-velocity pose changes by widening inter-frame gaps. The base controller reliably tracks everyday low-dynamic motions, while the residual MoE adaptively allocates additional network capacity to handle challenging high-dynamic actions, significantly enhancing tracking accuracy. In the absence of a public benchmark, we curate the High-Dynamic Humanoid Motion (HDHM) dataset, comprising 3593 physically plausible clips. On HDHM, FARM reduces the tracking failure rate by 42.8\% and lowers global mean per-joint position error by 14.6\% relative to the baseline, while preserving near-perfect accuracy on low-dynamic motions. These results establish FARM as a new baseline for high-dynamic humanoid control and introduce the first open benchmark dedicated to this challenge. The code and dataset will be released at https://github.com/Colin-Jing/FARM.
title FARM: Frame-Accelerated Augmentation and Residual Mixture-of-Experts for Physics-Based High-Dynamic Humanoid Control
topic Robotics
url https://arxiv.org/abs/2508.19926