The invention relates to the field of artificial intelligence, in particular to an unmanned mine car driving road surface type identification method. The method comprises the following steps: collecting speed, acceleration and road surface image data of the unmanned mine car, processing the road surface image data into an attribute matrix, selecting an optimal characteristic attribute from the attribute matrix by applying a continuous projection algorithm, taking the selected characteristic attribute as input, and establishing a prediction model of a road surface type and a ground adhesion coefficient by adopting a support vector machine method. And completing the construction of the prediction model through training. And finally, the trained prediction model is utilized to predict the type and the ground adhesion coefficient of the driving road surface of the unmanned mine car. The method combines the feature selection of the continuous projection algorithm and the prediction capability of the support vector machine, selects the optimal feature, and improves the precision and robustness of surface mine pavement type recognition.
本发明涉及人工智能领域,具体涉及一种无人矿车行驶路面类型识别方法。该方法收集无人矿车的速度、加速度及路面图像数据,将路面图像数据处理为属性矩阵,应用连续投影算法从属性矩阵中选择出最优特征属性,以选出的特征属性作为输入,采用支持向量机方法建立路面类型和地面附着系数的预测模型。通过训练,完成预测模型的构建。最终利用训练好的预测模型,对无人矿车行驶路面进行类型及地面附着系数的预测。该方法结合连续投影算法的特征选择与支持向量机的预测能力,选取出最优特征,提高露天矿山路面类型识别的精度和鲁棒性。
Unmanned mine car driving road surface type identification method
一种无人矿车行驶路面类型识别方法
2024-03-12
Patent
Electronic Resource
Chinese
IPC: | G06V / B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion / G01C Messen von Entfernungen, Höhen, Neigungen oder Richtungen , MEASURING DISTANCES, LEVELS OR BEARINGS |
European Patent Office | 2022
|Unmanned driving control method for mine car of strip mine factory
European Patent Office | 2023
|Elevated road surface and unmanned automatic driving vehicle running on elevated road surface
European Patent Office | 2020
|