无道路环境车辆支承通过性全遥感反演方法

Remote Sensing-Based Inversion Method for Vehicle Trafficability in Off-Road Environments

  • 摘要: 面向野外无道路环境下车辆的机动导航需求,实现软地面车辆支承通过性计算,对国防建设和国民经济发展具有重要的价值。针对经典通过性方法依赖原位测量,陌生大范围地域无道路环境车辆支承通过性难以计算的问题,提出车辆支承通过性遥感反演方法,并在漳州和滁州两个试验区进行验证。构建遥感土壤含水量梯度提升树反演模型,经星地同步试验,均方根误差(root mean square error, RMSE)分别为6.3 cm³/cm³和4.9 cm³/cm³,实现了浅地表土壤含水量高精度反演;构建土壤统一土壤分类体系(unified soil classification system, USCS)类型知识蒸馏反演模型,经原位测量验证,分类一致性为75.0%,实现了土壤USCS类型有效反演;集成基于土壤力学原理的土壤力学参数反演模型和车辆动力学模型,实现数字路网路段上履带/轮式车辆的沉陷和车速反演计算。经实装验证,车辙深度精度优于2 cm,车速精度优于90%。所提出的车辆支承通过性全遥感反演方法可有效计算最大车速,支持导航机动路径筹划与车辆引导的实际需求,拓展了遥感的新应用领域。

     

    Abstract:
    Objectives To address the challenges of vehicle trafficability assessment in roadless environments, this study proposes a remote sensing inversion method for evaluating vehicle support mobility on soft terrain, validated in Zhangzhou and Chuzhou test areas.
    Methods A gradient boosting tree model was developed to invert shallow soil moisture using remote sensing data, supported by satellite-ground synchronous experiments. A knowledge distillation model was constructed to classify soil unified soil classification system (USCS) types, verified through in situ measurements. Soil mechanical parameters and vehicle dynamics models were integrated to predict sinkage and speed for tracked/wheeled vehicles on digital road networks.
    Results The soil moisture inversion achieved root mean square error (RMSE) values of 6.3% and 4.9%, respectively, demonstrating high accuracy. The USCS classification model showed 75.0% consistency with field data. Vehicle sinkage predictions exhibited errors below 2 cm, and speed estimation accuracy exceeded 90% in practical validations.
    Conclusions The proposed full remote sensing inversion method enables efficient calculation of maximum vehicle speeds, supporting navigation path planning and vehicle guidance in unstructured environments. This approach demonstrates a novel and valuable application of remote sensing technology in mobility assessment and analysis.

     

/

返回文章
返回