Sampling-based path planning is a widely used method in robotics, particularly in high-dimensional state space. Among the whole process of the path planning, collision detection is the most time-consuming operation. In this paper, we propose a learning-based path planning method that aims to reduce the number of collision detection. We develop an efficient neural network model based on Graph Neural Networks (GNN) and use the environment map as input. The model outputs weights for each neighbor based on the input and current vertex information, which are used to guide the planner in avoiding obstacles. We evaluate the proposed method's efficiency through simulated random worlds and real-world experiments, respectively. The results demonstrate that the proposed method significantly reduces the number of collision detection and improves the path planning speed in high-dimensional environments.

翻译：基于采样的路径规划是机器人领域中广泛应用的方法，尤其适用于高维状态空间。在路径规划的整个过程中，碰撞检测是最耗时的操作。本文提出一种基于学习的路径规划方法，旨在减少碰撞检测次数。我们开发了一种基于图神经网络的高效神经网络模型，并将环境地图作为输入。该模型根据输入和当前顶点信息为每个邻居输出权重，用于引导规划器避开障碍物。通过仿真随机环境与实际实验分别评估了所提方法的效率。结果表明，该方法能显著减少碰撞检测次数，并提升高维环境中的路径规划速度。