让机器人自适应调整感知范围，高效穿越复杂环境
ADAPT: Adaptive Dual-projection Architecture for Perceptive Traversal
- 用水平高程图和垂直距离图双重表征环境
- 感知范围可学习，快走时扩展、拥挤时收缩
- 训练快、部署强，零样本迁移至真实人形机器人
在复杂3D环境中实现敏捷人形机器人行走，需平衡感知精度与计算效率，现有方法多依赖固定感知配置。本文提出ADAPT（自适应双投影架构），以水平高程图表征地形几何，以垂直距离图捕捉可通行空间约束。该架构将感知范围设为可学习动作，使策略在快速运动时扩展感知视野，在复杂场景中收缩以获得更高局部分辨率。相比基于体素的基线方法，ADAPT显著降低观测维度与计算开销，大幅加速训练过程。实验表明，其成功实现零样本迁移至Unitree G1人形机器人，在多种3D环境挑战下表现卓越，显著优于固定感知范围的基线模型。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。