基于感知区域覆盖的自动驾驶传感器布局优化方法

传感器是自动驾驶汽车感知环境的重要组成部分。为了提高传感器感知数据质量,文章提出了一种传感器布局优化方法,其以加权信息覆盖面积为优化模型的目标函数,以传感器的安装位置和安装角度为决策变量,构建了传感器布局优化数学模型;模型中引入计算几何理论和DSM技术,实现了多类型传感器感知区域归一化建模和感知对象建模,并借助三角形网格的离散化算法实现了感知区域判定。最后设计了一种粒子群优化算法对模型进行求解,仿真实验结果证明了该模型的正确性和优化方法的有效性。

Sensor-layout Optimization of Autonomous Vehicle Based on Perceptual Area Coverage

Sensors are an important part of the sensing environment of autonomous vehicles.In order to improve the sensor sensing data quality,this paper proposed a sensor-layout optimization method.It takes weighted information coverage area as objective function of the optimization model,and sensor installation location and installation angle as decision variables,and constructs a mathematical model for sensor layout optimization.In the model,computational geometry theory and DSM technology are introduced to realize the normalized modeling and perceptual object modeling of a multi-type sensor perceptual region,and the perceptual region determination is realized by using the idea of triangular mesh discretization.Finally,a particle swarm optimization algorithm was designed to solve the model,and the correctness of the model and the effectiveness of the optimization method were verified by computer experiment and simulation.