PPF: Pre-training and Preservative Fine-tuning of Humanoid Locomotion via Model-Assumption-based Regularization
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915555949150208 |
|---|---|
| author | Jung, Hyunyoung Gu, Zhaoyuan Zhao, Ye Park, Hae-Won Ha, Sehoon |
| author_facet | Jung, Hyunyoung Gu, Zhaoyuan Zhao, Ye Park, Hae-Won Ha, Sehoon |
| contents | Humanoid locomotion is a challenging task due to its inherent complexity and high-dimensional dynamics, as well as the need to adapt to diverse and unpredictable environments. In this work, we introduce a novel learning framework for effectively training a humanoid locomotion policy that imitates the behavior of a model-based controller while extending its capabilities to handle more complex locomotion tasks, such as more challenging terrain and higher velocity commands. Our framework consists of three key components: pre-training through imitation of the model-based controller, fine-tuning via reinforcement learning, and model-assumption-based regularization (MAR) during fine-tuning. In particular, MAR aligns the policy with actions from the model-based controller only in states where the model assumption holds to prevent catastrophic forgetting. We evaluate the proposed framework through comprehensive simulation tests and hardware experiments on a full-size humanoid robot, Digit, demonstrating a forward speed of 1.5 m/s and robust locomotion across diverse terrains, including slippery, sloped, uneven, and sandy terrains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_09833 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PPF: Pre-training and Preservative Fine-tuning of Humanoid Locomotion via Model-Assumption-based Regularization Jung, Hyunyoung Gu, Zhaoyuan Zhao, Ye Park, Hae-Won Ha, Sehoon Robotics Humanoid locomotion is a challenging task due to its inherent complexity and high-dimensional dynamics, as well as the need to adapt to diverse and unpredictable environments. In this work, we introduce a novel learning framework for effectively training a humanoid locomotion policy that imitates the behavior of a model-based controller while extending its capabilities to handle more complex locomotion tasks, such as more challenging terrain and higher velocity commands. Our framework consists of three key components: pre-training through imitation of the model-based controller, fine-tuning via reinforcement learning, and model-assumption-based regularization (MAR) during fine-tuning. In particular, MAR aligns the policy with actions from the model-based controller only in states where the model assumption holds to prevent catastrophic forgetting. We evaluate the proposed framework through comprehensive simulation tests and hardware experiments on a full-size humanoid robot, Digit, demonstrating a forward speed of 1.5 m/s and robust locomotion across diverse terrains, including slippery, sloped, uneven, and sandy terrains. |
| title | PPF: Pre-training and Preservative Fine-tuning of Humanoid Locomotion via Model-Assumption-based Regularization |
| topic | Robotics |
| url | https://arxiv.org/abs/2504.09833 |