From Experts to a Generalist: Toward General Whole-Body Control for Humanoid Robots
Lists
Only you see this
Abstract
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.
BibTeX
@inproceedings{wang2025from,
author = {Yuxuan Wang and Ming Yang and Weishuai Zeng and Yu Zhang and Xinrun Xu and Haobin Jiang and Ziluo Ding and Zongqing Lu},
title = {{From Experts to a Generalist: Toward General Whole-Body Control for Humanoid Robots}},
booktitle = {Advances in Neural Information Processing Systems},
year = {2025},
url = {https://openreview.net/forum?id=ZBSkyMwdEB},
}