无人驾驶汽车中基于SLAM的环境感知与控制系统研究

打开文本图片集

中图分类号：U463.6 文献标识码：A 文章编号：1003-8639（2025）11-0058-03

Research on Environmental Perception and Control System Based on SLAM in Driverless Cars

Zhang Junyu

Henan Vocational College of Water Conservancy and Environment, Zhengzhou 45oo45, China

【Abstract】To addressthe limitations of single sensor perception and the strong coupling of motion control in unmanned vehicles in complex dynamic scenarios,this paper conducts research on an environmental perception and control system based on SLAM. Design a multi-sensor fusion SLAM architecture,achieve robust state estimation and high-precision map construction throughthetightcoupling of idar,camera and IMU,and introduce pointcloud denoising and time-sequence synchronization mechanisms to improve perceptionquality.A hierarchical path planning strategy is proposed,andatransverseandlongitudinalcooperativemotioncontrollrbasedonmodelpredictivecontrolisdesigned, fully considering the vehicledynamicconstraintsand road boundaries.Real vehicle tests showthatthesystemachieves centimeter-level positioning accuracy in complex scenarios,with a lateral tracking error of no more than 18.3cm ,which can provide reliable technical support for autonomous navigation of unmanned vehicles.

【Key words】driverless car;SLAM;environmental perception;path planning；motion control

随着人工智能与传感技术发展，无人驾驶汽车逐步落地，但现实驾驶环境存在高度不确定性，单一模态传感器易受干扰。（剩余5702字）