DynGMP: Graph Neural Network-Based Motion Planning in Unpredictable Dynamic Environments
DynGMP: Graph Neural Network-Based Motion Planning in Unpredictable Dynamic Environments
复制标题
DOI：
10.1109/iros55552.2023.10342326
复制
发表时间：
2023-10
期刊：
影响因子：
--
通讯作者：
Wenjin Zhang;Xiao Zang;Lingyi Huang;Yang Sui;Jingjin Yu;Yingying Chen;Bo Yuan
中科院分区：
文献类型：
--
作者：
Wenjin Zhang;Xiao Zang;Lingyi Huang;Yang Sui;Jingjin Yu;Yingying Chen;Bo Yuan
神经网络已经在解决运动规划问题方面表现出了吸引人的性能，特别是在静态和可预测的环境中。然而，有效的神经规划器，可以适应不可预测的动态环境，在许多实际应用中的高度需求的情况下，仍然是探索不足。为了填补这一研究空白，丰富现有的运动规划方法，本文提出了一种基于图神经网络（GNN）的运动规划器DynGMP，该规划器能够在不可预测的动态环境中提供高性能的规划解决方案。通过充分利用以往的勘探经验，最大限度地减少因环境变化而产生的重新规划成本，DynGMP同时实现了高规划性能和效率。在不同环境下的经验评估表明，DynGMP可以实现接近100%的成功率，快速规划速度和短路径成本。与现有的非学习和基于学习的同行相比，DynGMP显示出非常显着的规划性能改进，例如，在四种环境中，在低路径距离下，规划速度分别提高至少2.7倍、2.2倍、2.4倍和2倍。
Neural networks have already demonstrated attractive performance for solving motion planning problems, especially in static and predictable environments. However, efficient neural planners that can adapt to unpredictable dynamic environments, a highly demanded scenario in many practical applications, are still under-explored. To fill this research gap and enrich the existing motion planning approaches, in this pa-per, we propose DynGMP, a graph neural network (GNN)-based planner that provides high-performance planning solutions in unpredictable dynamic environments. By fully leveraging the prior exploration experience and minimizing the replanning cost incurred by environmental change, DynGMP achieves high planning performance and efficiency simultaneously. Empirical evaluations across different environments show that DynGMP can achieve close to 100% success rate with fast planning speed and short path cost. Compared with existing non-learning and learning-based counterparts, DynGMP shows very significant planning performance improvement, e.g., at least 2.7×, 2.2×, $2.4\times$ and $2\times$ faster planning speed with low path distance in four environments, respectively.