In recent years, learning-based approaches have revolutionized motion planning. The data generation process for these methods involves caching a large number of high quality paths for different queries (start, goal pairs) in various environments. Conventionally, a uniform random strategy is used for sampling these queries. However, this leads to inclusion of "trivial paths" in the dataset (e.g.,, straight line paths in case of length-optimal planning), which can be solved efficiently if the planner has access to a steering function. This work proposes a "non-trivial" query sampling procedure to add more complex paths in the dataset. Numerical experiments show that a higher success rate can be attained for neural planners trained on such a non-trivial dataset.

翻译：近年来，基于学习的方法彻底改变了运动规划领域。这些方法的数据生成过程涉及在不同环境中为大量查询（起点-目标点对）缓存高质量路径。传统上，这些查询的采样采用均匀随机策略。然而，这会导致数据集中包含"平凡路径"（例如，在长度最优规划情况下的直线路径），若规划器具备转向函数，此类路径可被高效求解。本文提出一种"非平凡"查询采样方法，旨在向数据集中添加更复杂的路径。数值实验表明，基于此类非平凡数据集训练的神经规划器可获得更高的成功率。