发表机构
J. Mike Walker ’66 Department of Mechanical Engineering, Texas A&M University; DEVCOM Army Research laboratory（德克萨斯农工大学J. Mike Walker '66机械工程系; 陆军研究实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对大型越野环境自主导航难题，提出从高空数据学习连续可通行性地图的方法，由人类驾驶轨迹监督、激光雷达先验塑造，发布相关数据集，实地试验显示该方法能减少操作员干预，轨迹接近人类路径长度。
AI 中文摘要
在大型越野环境中的自主导航仍然是一个具有挑战性的问题。车载传感器只能感知周围环境，而安全高效的路线依赖于超出传感器视野的地形特征。地理空间数据源虽能弥补差距，但从它们中学习可通行性很困难。我们提出一种有效方法，从高空数据学习连续可通行性地图，由人类驾驶的GPS轨迹直接监督，并由激光雷达的自监督几何先验塑造。我们还发布了一个包含299个场景的公共数据集。在实地试验中，我们的方法与仅使用局部规划器的自主性相比，轨迹在人类路径长度的3.66%以内，减少了约85%的操作员干预。
英文摘要
Autonomous navigation across large off-road environments remains a challenging problem. Onboard sensors perceive only the immediate surroundings, yet safe and efficient routes depend on terrain features that extend well beyond the sensor horizon. Geo-spatial data sources such as satellite imagery, aerial LiDAR, and vector maps can close this gap, but learning traversability from them is difficult: dense labels are unavailable at scale, and existing methods rely on short-range sensing. We propose an efficient formulation that learns a continuous traversability map from overhead data, supervised directly by human-driven GPS trajectories and shaped by supervised geometric priors from LiDAR. Alongside the model, we release a dataset, curated from public sources, consisting of 299 scenes spanning $\sim\!1{,}244\,\mathrm{km}^{2}$ of diverse terrain, paired with $1{,}130\,\mathrm{km}$ of human driving. In field trials on a Clearpath Warthog across seven routes at two sites,our method achieves trajectories within $5.5\%$ of human path length and reduces operator interventions by $\sim\!85\%$ compared to local-planner-only autonomy.
