Graph search planning algorithms for navigation typically rely heavily on heuristics to efficiently plan paths. As a result, while such approaches require no training phase and can directly plan long horizon paths, they often require careful hand designing of informative heuristic functions. Recent works have started bypassing hand designed heuristics by using machine learning to learn heuristic functions that guide the search algorithm. While these methods can learn complex heuristic functions from raw input, they i) require a significant training phase and ii) do not generalize well to new maps and longer horizon paths. Our contribution is showing that instead of learning a global heuristic estimate, we can define and learn local heuristics which results in a significantly smaller learning problem and improves generalization. We show that using such local heuristics can reduce node expansions by 2-20x while maintaining bounded suboptimality, are easy to train, and generalize to new maps & long horizon plans.

翻译：图搜索导航规划算法通常严重依赖启发式方法来实现高效路径规划。因此，尽管这类方法无需训练阶段且能直接规划长距离路径，但它们往往需要人工精心设计信息丰富的启发式函数。近期研究开始通过机器学习学习指导搜索算法的启发式函数，从而绕过人工设计的启发式方法。虽然这些方法能从原始输入中学习复杂的启发式函数，但存在以下问题：i) 需要大量训练阶段；ii) 难以泛化到新地图和更长距离路径。我们的贡献在于证明：与其学习全局启发式估计，不如定义并学习局部启发式——这能显著缩小学习问题的规模并提升泛化能力。实验表明，采用此类局部启发式可在保持有界次优性的同时将节点扩展量减少2-20倍，且易于训练，能有效泛化到新地图及长距离规划任务。