Toward Understanding Key Estimation in Learning Robust Humanoid Locomotion
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917609660743680 |
|---|---|
| author | Wang, Zhicheng Wei, Wandi Yu, Ruiqi Wu, Jun Zhu, Qiuguo |
| author_facet | Wang, Zhicheng Wei, Wandi Yu, Ruiqi Wu, Jun Zhu, Qiuguo |
| contents | Accurate state estimation plays a critical role in ensuring the robust control of humanoid robots, particularly in the context of learning-based control policies for legged robots. However, there is a notable gap in analytical research concerning estimations. Therefore, we endeavor to further understand how various types of estimations influence the decision-making processes of policies. In this paper, we provide quantitative insight into the effectiveness of learned state estimations, employing saliency analysis to identify key estimation variables and optimize their combination for humanoid locomotion tasks. Evaluations assessing tracking precision and robustness are conducted on comparative groups of policies with varying estimation combinations in both simulated and real-world environments. Results validated that the proposed policy is capable of crossing the sim-to-real gap and demonstrating superior performance relative to alternative policy configurations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_05868 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Toward Understanding Key Estimation in Learning Robust Humanoid Locomotion Wang, Zhicheng Wei, Wandi Yu, Ruiqi Wu, Jun Zhu, Qiuguo Robotics Accurate state estimation plays a critical role in ensuring the robust control of humanoid robots, particularly in the context of learning-based control policies for legged robots. However, there is a notable gap in analytical research concerning estimations. Therefore, we endeavor to further understand how various types of estimations influence the decision-making processes of policies. In this paper, we provide quantitative insight into the effectiveness of learned state estimations, employing saliency analysis to identify key estimation variables and optimize their combination for humanoid locomotion tasks. Evaluations assessing tracking precision and robustness are conducted on comparative groups of policies with varying estimation combinations in both simulated and real-world environments. Results validated that the proposed policy is capable of crossing the sim-to-real gap and demonstrating superior performance relative to alternative policy configurations. |
| title | Toward Understanding Key Estimation in Learning Robust Humanoid Locomotion |
| topic | Robotics |
| url | https://arxiv.org/abs/2403.05868 |