发表机构
Worcester Polytechnic Institute (WPI)（伍斯特理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对越野可通行性的方向依赖与车辆特异问题，提出自监督多任务框架DGT-MAP，生成方向性车辆条件化代价地图，在仿真中取得最高导航成功率。
AI 中文摘要
越野可通行性具有方向依赖性和车辆特异性，然而大多数全局地图为每个位置分配单一的各向同性代价。现有的学习型估计器也通常针对每辆车独立训练；这保留了车辆特定行为，但阻止了车辆共享共同的地形表示。DGT-MAP通过一个自监督框架解决了这两个局限性，该框架从RGB-D观测和运动信号中学习全局、方向性和车辆条件化的可通行性代价地图。一个共享的多任务骨干网络在训练车辆间学习共同的地形特征，而车辆特定的预测头则保留平台相关的响应。在推理时，DGT-MAP生成一个以航向为索引的代价地图，可供方向感知规划器使用。我们通过将DGT-MAP集成到混合A*导航栈中，并在具有挑战性的地形上测量下游任务成功率来在仿真中评估它，这些地形包括下坡可通行但上坡不可通行的斜坡，以及某些车辆可通行而其他车辆不可通行的山脊障碍物。在评估的任务中，与几何、二值和学习型方向无关的基线相比，DGT-MAP实现了最高或并列最高的导航成功率。
英文摘要
Off-road traversability is direction-dependent and vehicle specific, yet most global maps assign a single isotropic cost to each location. Existing learned estimators are also commonly trained independently for each vehicle; this preserves vehicle-specific behavior but prevents vehicles from sharing common terrain representations. DGT-MAP addresses both limitations through a self-supervised framework that learns global, directional, and vehicle-conditioned traversability costmaps from RGB-D observations and locomotion signals. A shared multi-task backbone learns common terrain features across training vehicles while vehicle-specific prediction heads preserve platform-dependent responses. At inference, DGT-MAP produces a heading-indexed costmap that can be used by a direction-aware planner. We evaluate DGT-MAP in simulation by integrating it into a Hybrid A* navigation stack and measuring downstream task success on challenging terrains, including slopes that are traversable downhill but not uphill and a ridge obstacle that is traversable by some vehicles, but not by others. Across evaluated tasks, DGT-MAP achieves the highest or tied-highest navigation success rate when compared against geometric, binary, and learned direction-agnostic baselines.
