TTT-Parkour: Rapid Test-Time Training for Perceptive Robot Parkour
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915768918081536 |
|---|---|
| author | Zhu, Shaoting Ye, Baijun Wang, Jiaxuan Chen, Jiakang Zhuang, Ziwen Mou, Linzhan Huang, Runhan Zhao, Hang |
| author_facet | Zhu, Shaoting Ye, Baijun Wang, Jiaxuan Chen, Jiakang Zhuang, Ziwen Mou, Linzhan Huang, Runhan Zhao, Hang |
| contents | Achieving highly dynamic humanoid parkour on unseen, complex terrains remains a challenge in robotics. Although general locomotion policies demonstrate capabilities across broad terrain distributions, they often struggle with arbitrary and highly challenging environments. To overcome this limitation, we propose a real-to-sim-to-real framework that leverages rapid test-time training (TTT) on novel terrains, significantly enhancing the robot's capability to traverse extremely difficult geometries. We adopt a two-stage end-to-end learning paradigm: a policy is first pre-trained on diverse procedurally generated terrains, followed by rapid fine-tuning on high-fidelity meshes reconstructed from real-world captures. Specifically, we develop a feed-forward, efficient, and high-fidelity geometry reconstruction pipeline using RGB-D inputs, ensuring both speed and quality during test-time training. We demonstrate that TTT-Parkour empowers humanoid robots to master complex obstacles, including wedges, stakes, boxes, trapezoids, and narrow beams. The whole pipeline of capturing, reconstructing, and test-time training requires less than 10 minutes on most tested terrains. Extensive experiments show that the policy after test-time training exhibits robust zero-shot sim-to-real transfer capability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_02331 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TTT-Parkour: Rapid Test-Time Training for Perceptive Robot Parkour Zhu, Shaoting Ye, Baijun Wang, Jiaxuan Chen, Jiakang Zhuang, Ziwen Mou, Linzhan Huang, Runhan Zhao, Hang Robotics Artificial Intelligence Achieving highly dynamic humanoid parkour on unseen, complex terrains remains a challenge in robotics. Although general locomotion policies demonstrate capabilities across broad terrain distributions, they often struggle with arbitrary and highly challenging environments. To overcome this limitation, we propose a real-to-sim-to-real framework that leverages rapid test-time training (TTT) on novel terrains, significantly enhancing the robot's capability to traverse extremely difficult geometries. We adopt a two-stage end-to-end learning paradigm: a policy is first pre-trained on diverse procedurally generated terrains, followed by rapid fine-tuning on high-fidelity meshes reconstructed from real-world captures. Specifically, we develop a feed-forward, efficient, and high-fidelity geometry reconstruction pipeline using RGB-D inputs, ensuring both speed and quality during test-time training. We demonstrate that TTT-Parkour empowers humanoid robots to master complex obstacles, including wedges, stakes, boxes, trapezoids, and narrow beams. The whole pipeline of capturing, reconstructing, and test-time training requires less than 10 minutes on most tested terrains. Extensive experiments show that the policy after test-time training exhibits robust zero-shot sim-to-real transfer capability. |
| title | TTT-Parkour: Rapid Test-Time Training for Perceptive Robot Parkour |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2602.02331 |