论文标题
使用神经a*搜索的路径计划
Path Planning using Neural A* Search
论文作者
论文摘要
我们提出神经A*，这是一种新颖的数据驱动搜索方法，用于路径计划问题。尽管最近对数据驱动的路径计划的关注越来越多，但由于搜索算法的离散性质，基于搜索的计划的机器学习方法仍然具有挑战性。在这项工作中，我们重新将规范的A*搜索算法与众不同，并将其与卷积编码器相结合，以形成端到端可训练的神经网络计划者。 Neural A*通过将问题实例编码到指导图，然后使用指导图执行可区分的A*来解决路径计划问题。通过学习将搜索结果与专家提供的基础真相路径相匹配，神经a*可以准确有效地产生与地面真相一致的路径。我们的广泛实验证实，就搜索最佳性和效率折衷而言，神经A*的表现优于最先进的数据驱动计划者。此外，神经A*通过直接对自然图像输入进行基于搜索的计划，成功地预测了现实的人类轨迹。项目页面：https：//omron-sinicx.github.io/neural-astar/
We present Neural A*, a novel data-driven search method for path planning problems. Despite the recent increasing attention to data-driven path planning, machine learning approaches to search-based planning are still challenging due to the discrete nature of search algorithms. In this work, we reformulate a canonical A* search algorithm to be differentiable and couple it with a convolutional encoder to form an end-to-end trainable neural network planner. Neural A* solves a path planning problem by encoding a problem instance to a guidance map and then performing the differentiable A* search with the guidance map. By learning to match the search results with ground-truth paths provided by experts, Neural A* can produce a path consistent with the ground truth accurately and efficiently. Our extensive experiments confirmed that Neural A* outperformed state-of-the-art data-driven planners in terms of the search optimality and efficiency trade-off. Furthermore, Neural A* successfully predicted realistic human trajectories by directly performing search-based planning on natural image inputs. Project page: https://omron-sinicx.github.io/neural-astar/
