From Experts to a Generalist: Toward General Whole-Body Control for Humanoid Robots

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Yuxuan, Yang, Ming, Ding, Ziluo, Zhang, Yu, Zeng, Weishuai, Xu, Xinrun, Jiang, Haobin, Lu, Zongqing
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911132664463360
author Wang, Yuxuan
Yang, Ming
Ding, Ziluo
Zhang, Yu
Zeng, Weishuai
Xu, Xinrun
Jiang, Haobin
Lu, Zongqing
author_facet Wang, Yuxuan
Yang, Ming
Ding, Ziluo
Zhang, Yu
Zeng, Weishuai
Xu, Xinrun
Jiang, Haobin
Lu, Zongqing
contents Achieving general agile whole-body control on humanoid robots remains a major challenge due to diverse motion demands and data conflicts. While existing frameworks excel in training single motion-specific policies, they struggle to generalize across highly varied behaviors due to conflicting control requirements and mismatched data distributions. In this work, we propose BumbleBee (BB), an expert-generalist learning framework that combines motion clustering and sim-to-real adaptation to overcome these challenges. BB first leverages an autoencoder-based clustering method to group behaviorally similar motions using motion features and motion descriptions. Expert policies are then trained within each cluster and refined with real-world data through iterative delta action modeling to bridge the sim-to-real gap. Finally, these experts are distilled into a unified generalist controller that preserves agility and robustness across all motion types. Experiments on two simulations and a real humanoid robot demonstrate that BB achieves state-of-the-art general whole-body control, setting a new benchmark for agile, robust, and generalizable humanoid performance in the real world. The project webpage is available at https://beingbeyond.github.io/BumbleBee/.
format Preprint
id arxiv_https___arxiv_org_abs_2506_12779
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle From Experts to a Generalist: Toward General Whole-Body Control for Humanoid Robots
Wang, Yuxuan
Yang, Ming
Ding, Ziluo
Zhang, Yu
Zeng, Weishuai
Xu, Xinrun
Jiang, Haobin
Lu, Zongqing
Robotics
Machine Learning
Achieving general agile whole-body control on humanoid robots remains a major challenge due to diverse motion demands and data conflicts. While existing frameworks excel in training single motion-specific policies, they struggle to generalize across highly varied behaviors due to conflicting control requirements and mismatched data distributions. In this work, we propose BumbleBee (BB), an expert-generalist learning framework that combines motion clustering and sim-to-real adaptation to overcome these challenges. BB first leverages an autoencoder-based clustering method to group behaviorally similar motions using motion features and motion descriptions. Expert policies are then trained within each cluster and refined with real-world data through iterative delta action modeling to bridge the sim-to-real gap. Finally, these experts are distilled into a unified generalist controller that preserves agility and robustness across all motion types. Experiments on two simulations and a real humanoid robot demonstrate that BB achieves state-of-the-art general whole-body control, setting a new benchmark for agile, robust, and generalizable humanoid performance in the real world. The project webpage is available at https://beingbeyond.github.io/BumbleBee/.
title From Experts to a Generalist: Toward General Whole-Body Control for Humanoid Robots
topic Robotics
Machine Learning
url https://arxiv.org/abs/2506.12779