Learning Perceptive Humanoid Locomotion over Challenging Terrain
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910901332869120 |
|---|---|
| author | Sun, Wandong Cao, Baoshi Chen, Long Su, Yongbo Liu, Yang Xie, Zongwu Liu, Hong |
| author_facet | Sun, Wandong Cao, Baoshi Chen, Long Su, Yongbo Liu, Yang Xie, Zongwu Liu, Hong |
| contents | Humanoid robots are engineered to navigate terrains akin to those encountered by humans, which necessitates human-like locomotion and perceptual abilities. Currently, the most reliable controllers for humanoid motion rely exclusively on proprioception, a reliance that becomes both dangerous and unreliable when coping with rugged terrain. Although the integration of height maps into perception can enable proactive gait planning, robust utilization of this information remains a significant challenge, especially when exteroceptive perception is noisy. To surmount these challenges, we propose a solution based on a teacher-student distillation framework. In this paradigm, an oracle policy accesses noise-free data to establish an optimal reference policy, while the student policy not only imitates the teacher's actions but also simultaneously trains a world model with a variational information bottleneck for sensor denoising and state estimation. Extensive evaluations demonstrate that our approach markedly enhances performance in scenarios characterized by unreliable terrain estimations. Moreover, we conducted rigorous testing in both challenging urban settings and off-road environments, the model successfully traverse 2 km of varied terrain without external intervention. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_00692 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning Perceptive Humanoid Locomotion over Challenging Terrain Sun, Wandong Cao, Baoshi Chen, Long Su, Yongbo Liu, Yang Xie, Zongwu Liu, Hong Robotics Humanoid robots are engineered to navigate terrains akin to those encountered by humans, which necessitates human-like locomotion and perceptual abilities. Currently, the most reliable controllers for humanoid motion rely exclusively on proprioception, a reliance that becomes both dangerous and unreliable when coping with rugged terrain. Although the integration of height maps into perception can enable proactive gait planning, robust utilization of this information remains a significant challenge, especially when exteroceptive perception is noisy. To surmount these challenges, we propose a solution based on a teacher-student distillation framework. In this paradigm, an oracle policy accesses noise-free data to establish an optimal reference policy, while the student policy not only imitates the teacher's actions but also simultaneously trains a world model with a variational information bottleneck for sensor denoising and state estimation. Extensive evaluations demonstrate that our approach markedly enhances performance in scenarios characterized by unreliable terrain estimations. Moreover, we conducted rigorous testing in both challenging urban settings and off-road environments, the model successfully traverse 2 km of varied terrain without external intervention. |
| title | Learning Perceptive Humanoid Locomotion over Challenging Terrain |
| topic | Robotics |
| url | https://arxiv.org/abs/2503.00692 |