用卫星图和驾驶轨迹训练越野自动驾驶全局路径规划模型
Learning Traversability-Aware Global Planners for Long Horizon Off-Road Navigation
- 从航拍数据学习连续可通行性地图，结合GPS轨迹与激光几何先验
- 实测路径长度仅比人类差3.66%，操作干预减少85%
- 适合长期野外自动驾驶，尤其依赖大范围地理信息的场景
在大型非结构化地形中实现自主导航仍具挑战。车载传感器仅能感知近距离环境，但安全高效的路径需考虑远超传感器范围的地形特征。卫星影像、航空LiDAR和矢量地图可弥补这一差距，但从中学习可通行性困难：大规模密集标签不可得，现有方法依赖短距离感知。本文提出一种高效方法，直接利用人类驾驶的GPS轨迹监督，结合LiDAR自监督几何先验，从高空数据中学习连续可通行性地图。同时发布一个公开数据集，包含299个场景，覆盖约1,244 km²多样地形，配以1,130 km的人类驾驶轨迹。在Clearpath Warthog上对七个路线、两个地点的实地测试显示，该方法生成路径长度仅比人类多3.66%，操作员干预减少约85%（相比仅使用局部规划器的自主系统）。
原文摘要 · Abstract (English)
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 self-supervised geometric priors from LiDAR. Alongside the model, we release a public dataset 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 $3.66\%$ of human path length and reduces operator interventions by $\sim\!85\%$ compared to local-planner-only autonomy.
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。