ADAPT: Adaptive Dual-projection Architecture for Perceptive Traversal
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914401994407936 |
|---|---|
| author | Shao, Shuo Huang, Tianchen Gao, Wei Zhang, Shiwu |
| author_facet | Shao, Shuo Huang, Tianchen Gao, Wei Zhang, Shiwu |
| contents | Agile humanoid locomotion in complex 3D en- vironments requires balancing perceptual fidelity with com- putational efficiency, yet existing methods typically rely on rigid sensing configurations. We propose ADAPT (Adaptive dual-projection architecture for perceptive traversal), which represents the environment using a horizontal elevation map for terrain geometry and a vertical distance map for traversable- space constraints. ADAPT further treats its spatial sensing range as a learnable action, enabling the policy to expand its perceptual horizon during fast motion and contract it in cluttered scenes for finer local resolution. Compared with voxel-based baselines, ADAPT drastically reduces observation dimensionality and computational overhead while substantially accelerating training. Experimentally, it achieves successful zero-shot transfer to a Unitree G1 Humanoid and signifi- cantly outperforms fixed-range baselines, yielding highly robust traversal across diverse 3D environtmental challenges. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_16328 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ADAPT: Adaptive Dual-projection Architecture for Perceptive Traversal Shao, Shuo Huang, Tianchen Gao, Wei Zhang, Shiwu Robotics Agile humanoid locomotion in complex 3D en- vironments requires balancing perceptual fidelity with com- putational efficiency, yet existing methods typically rely on rigid sensing configurations. We propose ADAPT (Adaptive dual-projection architecture for perceptive traversal), which represents the environment using a horizontal elevation map for terrain geometry and a vertical distance map for traversable- space constraints. ADAPT further treats its spatial sensing range as a learnable action, enabling the policy to expand its perceptual horizon during fast motion and contract it in cluttered scenes for finer local resolution. Compared with voxel-based baselines, ADAPT drastically reduces observation dimensionality and computational overhead while substantially accelerating training. Experimentally, it achieves successful zero-shot transfer to a Unitree G1 Humanoid and signifi- cantly outperforms fixed-range baselines, yielding highly robust traversal across diverse 3D environtmental challenges. |
| title | ADAPT: Adaptive Dual-projection Architecture for Perceptive Traversal |
| topic | Robotics |
| url | https://arxiv.org/abs/2603.16328 |