GBC: Generalized Behavior-Cloning Framework for Whole-Body Humanoid Imitation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911104086573056 |
|---|---|
| author | Yao, Yifei Luo, Chengyuan Du, Jiaheng He, Wentao Lu, Jun-Guo |
| author_facet | Yao, Yifei Luo, Chengyuan Du, Jiaheng He, Wentao Lu, Jun-Guo |
| contents | The creation of human-like humanoid robots is hindered by a fundamental fragmentation: data processing and learning algorithms are rarely universal across different robot morphologies. This paper introduces the Generalized Behavior Cloning (GBC) framework, a comprehensive and unified solution designed to solve this end-to-end challenge. GBC establishes a complete pathway from human motion to robot action through three synergistic innovations. First, an adaptive data pipeline leverages a differentiable IK network to automatically retarget any human MoCap data to any humanoid. Building on this foundation, our novel DAgger-MMPPO algorithm with its MMTransformer architecture learns robust, high-fidelity imitation policies. To complete the ecosystem, the entire framework is delivered as an efficient, open-source platform based on Isaac Lab, empowering the community to deploy the full workflow via simple configuration scripts. We validate the power and generality of GBC by training policies on multiple heterogeneous humanoids, demonstrating excellent performance and transfer to novel motions. This work establishes the first practical and unified pathway for creating truly generalized humanoid controllers. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_09960 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GBC: Generalized Behavior-Cloning Framework for Whole-Body Humanoid Imitation Yao, Yifei Luo, Chengyuan Du, Jiaheng He, Wentao Lu, Jun-Guo Robotics Artificial Intelligence Machine Learning The creation of human-like humanoid robots is hindered by a fundamental fragmentation: data processing and learning algorithms are rarely universal across different robot morphologies. This paper introduces the Generalized Behavior Cloning (GBC) framework, a comprehensive and unified solution designed to solve this end-to-end challenge. GBC establishes a complete pathway from human motion to robot action through three synergistic innovations. First, an adaptive data pipeline leverages a differentiable IK network to automatically retarget any human MoCap data to any humanoid. Building on this foundation, our novel DAgger-MMPPO algorithm with its MMTransformer architecture learns robust, high-fidelity imitation policies. To complete the ecosystem, the entire framework is delivered as an efficient, open-source platform based on Isaac Lab, empowering the community to deploy the full workflow via simple configuration scripts. We validate the power and generality of GBC by training policies on multiple heterogeneous humanoids, demonstrating excellent performance and transfer to novel motions. This work establishes the first practical and unified pathway for creating truly generalized humanoid controllers. |
| title | GBC: Generalized Behavior-Cloning Framework for Whole-Body Humanoid Imitation |
| topic | Robotics Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2508.09960 |