地形感知的四足侦察自主行星探索，用于外感受-本体感受建图
Terrain-Aware Autonomous Planetary Exploration for Exteroceptive-Proprioceptive Mapping with Quadruped Scouts
浏览论文内容
中文总结 AI 辅助
本文提出一种结合外感受与本体感受建图的地形感知探索框架，用于四足机器人在月球类似环境中的自主导航，仿真表明该方法能有效扩展地图并降低运输成本。
中文摘要 AI 辅助
自主行星探索要求机器人在未知、不平坦的地形中导航，同时评估风险、可通行性和能量消耗。四足侦察机器人非常适合这项任务，因为它们能够穿越不规则表面，并在运动过程中收集与移动性相关的信息。本文提出了一种地形感知的探索框架，该框架结合了外感受和本体感受建图，适用于月球类似环境中的四足机器人。机载RGB-D相机构建以机器人为中心的 elevation maps（高程图），估计几何可通行性，并推导出用于自主规划的导航成本。与此同时，本体感受测量提供交互感知的地形线索，补充基于几何的评估。局部地图被增量注册到全局多层表示中，探索模块利用该表示在未探索的兴趣区域中选择目标。目标由自主导航系统到达，该系统利用可用地图和成本层引导碰撞感知的运动。在NVIDIA Isaac Sim上的仿真结果显示，自主探索、地图扩展以及地形几何与机器人-地形交互之间的空间关联得以实现。随后利用这些信息进行导航，其平均运输成本（CoT）低于初始探索时的成本。
英文摘要
Autonomous planetary exploration requires robots to navigate unknown, uneven terrain while assessing risk, traversability, and energetic cost. Quadruped scouts are well suited for this task because they can traverse irregular surfaces and gather mobility-relevant information during locomotion. This paper presents a terrain-aware exploration framework that combines exteroceptive and proprioceptive mapping for a quadruped robot in lunar-like environments. An onboard RGB-D camera builds robot-centered elevation maps, estimates geometric traversability, and derives navigation costs for autonomous planning. In parallel, proprioceptive measurements provide interaction-aware terrain cues that complement geometry-based assessment. Local maps are incrementally registered into a global multi-layer representation, which is used by an exploration module to select targets in unexplored regions of interest. The targets are reached by an autonomous navigation system that guides collision-aware motion using the available map and cost layers. Simulation results on NVIDIA Isaac Sim show autonomous exploration, map expansion, and spatial association between terrain geometry and robot-terrain interaction. Subsequent navigation using this information exhibits lower average Cost of Transport (CoT) than initial exploration.
发表机构
- Istituto Italiano di Tecnologia (IIT)（意大利理工学院）
机构由 AI 辅助整理，请以论文原文为准。
