The invention relates to a vision and dynamics fused road adhesion coefficient estimation method. The method comprises the following steps of: S1, acquiring a road image in front of a vehicle in a driving process; S2, inputting the road image into a trained road classification model to acquire a front road type; S3, according to the front road type and the mapping relationship between the road type and a road adhesion coefficient, acquiring a road adhesion coefficient visual estimation value theta ximage; S4, acquiring dynamic information of tires in the vehicle driving process; S5, utilizinga road adhesion coefficient-tire longitudinal force estimator to acquire a current road peak adhesion coefficient estimation value theta x; and S6, combining the road adhesion coefficient visual estimation value theta image and the current road peak adhesion coefficient estimation value theta x, and acquiring a final road adhesion coefficient estimation value by utilizing a fuzzy reasoning rule. Compared with the prior art, the method has the advantages of high estimation precision, good real-time performance, strong robustness and the like.
本发明涉及一种视觉与动力学融合的路面附着系数估计方法,包括以下步骤:S1:获取车辆行驶过程中前方的路面图像;S2:将路面图像训练完成的路面分类模型,得到前方路面类型;S3:根据前方路面类型和路面类型与路面附着系数映射关系,获取路面附着系数视觉估计值θ;S4:获取车辆行驶过程中轮胎的动力学信息;S5:利用路面附着系数‑轮胎纵向力估计器,获取当前路面峰值附着系数估计值θ;S6:结合路面附着系数视觉估计值θ和当前路面峰值附着系数估计值θ,利用模糊推理规则得到最终路面附着系数估计值,与现有技术相比,本发明具有估计精度高、实时性好、鲁棒性强等优点。
Vision and dynamics fused road adhesion coefficient estimation method
一种视觉与动力学融合的路面附着系数估计方法
2020-09-22
Patent
Elektronische Ressource
Chinesisch
IPC: | 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 |
Image and vehicle dynamics fused road adhesion coefficient estimation method
Europäisches Patentamt | 2024
|Road adhesion coefficient interactive estimation method based on vision and dynamics
Europäisches Patentamt | 2020
|Road adhesion coefficient estimation method and system
Europäisches Patentamt | 2023
|