The invention discloses an automatic driving automobile environment complexity quantification method based on a viewpoint scene, and the method comprises the steps: S1, calculating a space-time environment complexity coefficient theta ST of a driving region of an automatic driving automobile according to an information entropy theory and time and space dimensions; s2, calculating static element complexity and dynamic element complexity based on a viewpoint scene by taking a driving viewpoint, namely a manned eye elliptical viewpoint, of the detected automatic driving automobile as a coordinate reference according to a potential field method theory, and finally, carrying out weighted summation on the static element complexity and the dynamic element complexity to obtain traffic environment element complexity CE; s3, multiplying the space-time environment complexity coefficient theta ST by the traffic environment element complexity CE to obtain the traffic environment complexity C of the driving area of the autonomous vehicle; the formula expression is C = thetaST * CE; and S4, rating the traffic environment complexity of the autonomous vehicle based on the traffic environment complexity C value.
本发明公开一种基于视点场景的自动驾驶汽车环境复杂度量化方法,包括:S1.依据信息熵理论,按照时间和空间维度,计算自动驾驶汽车所行驶区域的时空环境复杂度系数θST;S2.依据势场法理论,以被测自动驾驶汽车驾驶视点即有人驾驶眼椭圆视点为坐标基准,计算基于视点场景的静态要素复杂度和动态要素复杂度,最后将静态要素复杂度与动态要素复杂度进行加权求和得到交通环境要素的复杂度CE;S3.将上述时空环境复杂度系数θST与交通环境要素复杂度CE相乘,得自动驾驶汽车所行驶区域的交通环境复杂度C;公式表达为:C=θST×CE;S4.基于交通环境复杂度C值,对自动驾驶汽车的交通环境复杂度评级。
Self-driving automobile environment complexity quantification method based on viewpoint scene
一种基于视点场景的自动驾驶汽车环境复杂度量化方法
2022-12-27
Patent
Electronic Resource
Chinese
Method for predicting scene fitness of self-driving automobile
European Patent Office | 2023
|Automobile automatic driving system in self-adaptive multi-change scene
European Patent Office | 2023
|Scene complexity model construction method based on automatic driving
European Patent Office | 2023
|Automatic driving automobile decision control method based on scene matrix
European Patent Office | 2024
|Control method of self-driving automobile and self-driving automobile
European Patent Office | 2024
|