Gallant：面向三维受限地形的基于体素栅格的人形机器人运动与局部导航
Gallant: Voxel Grid-based Humanoid Locomotion and Local-navigation across 3-D Constrained Terrains
用体素化激光雷达点云替代深度图/高程图作为策略输入，并配 z 分组 2D CNN 处理体素栅格，为视觉感知驱动的具身控制提供了更完整的三维感知表征与可扩展的激光雷达仿真训练管线。
原文依据 It leverages voxelized LiDAR data as a lightweight and structured perceptual representation, and employs a z-grouped 2D CNN
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论鲁棒的人形机器人运动需要对周围三维环境进行准确且全局一致的感知。然而，现有的感知模块主要基于深度图像或高程图，只能提供环境的部分且局部平坦化的视图，无法捕捉完整的三维结构。本文提出 Gallant，一个面向三维受限地形中人形机器人运动与局部导航的基于体素栅格的框架。它利用体素化的激光雷达数据作为一种轻量且结构化的感知表征，并采用 z 分组二维 CNN 将该表征映射到控制策略，从而实现完全端到端的优化。为支持可扩展的、基于激光雷达的训练并确保仿真到现实的一致性，本文开发了一种能够动态生成真实观测的高保真激光雷达仿真。实验结果表明，Gallant 更广的感知覆盖范围使得单一策略能够超越此前方法仅限于地面高度障碍的局限，扩展到侧向杂物、头顶约束、多层结构和狭窄通道。通过改进的端到端优化，Gallant 还首次在爬楼梯和踏上高台等挑战性场景中实现了超过 90% 的成功率。网站：https://gallantloco.github.io/。
英文原文摘要 1343 字符
Robust humanoid locomotion requires accurate and globally consistent perception of the surrounding 3D environment. However, existing perception modules, mainly based on depth images or elevation maps, offer only partial and locally flattened views of the environment, failing to capture the full 3D structure. This paper presents Gallant, a voxel-grid-based framework for humanoid locomotion and local navigation in 3D constrained terrains. It leverages voxelized LiDAR data as a lightweight and structured perceptual representation, and employs a z-grouped 2D CNN to map this representation to the control policy, enabling fully end-to-end optimization. A high-fidelity LiDAR simulation that dynamically generates realistic observations is developed to support scalable, LiDAR-based training and ensure sim-to-real consistency. Experimental results show that Gallant's broader perceptual coverage facilitates the use of a single policy that goes beyond the limitations of previous methods confined to ground-level obstacles, extending to lateral clutter, overhead constraints, multi-level structures, and narrow passages. Gallant also firstly achieves over-90% success rates in challenging scenarios such as stair climbing and stepping onto elevated platforms through improved end-to-end optimization. Website: https://gallantloco.github.io/.