The invention discloses a depth perception method for an unmanned engineering vehicle in a complex working environment, which relates to the field of automatic driving of vehicles and comprises the following steps of: 1, scanning the working environment by using a laser radar, and establishing a two-dimensional map of a working scene; 2, using a vehicle-mounted industrial camera to shoot the road in front of the vehicle, and recognizing the road type in combination with a machine vision algorithm; 3, acquiring vehicle dynamics parameters by using a vehicle-mounted sensor, inputting the vehicle dynamics parameters into the established vehicle dynamics model, and performing parameter identification; and 4, fusing the obtained machine vision road surface recognition result with the dynamics recognition result, and determining the type of the front road. According to the method, the map containing the road surface information of the engineering vehicle in a complex operation environment can be established, and deep perception of the environment is realized, so that a foundation is laid for automatic operation and automatic driving.
本发明公开了一种复杂作业环境下无人驾驶工程车辆的深度感知方法,涉及到车辆自动驾驶领域,其步骤包括:1使用激光雷达扫描作业环境,建立工作场景二维地图;2使用车载工业摄像机拍摄车辆前方道路,结合机器视觉算法识别道路类型;3使用车载传感器获取车辆动力学参数,输入建立的车辆动力学模型,进行参数辨识;4将获取到的机器视觉路面识别结果与动力学识别结果融合,确定前方道路类型。本发明能实现工程车辆在复杂作业环境下包含路面信息的地图建立,并实现对环境的深度感知,从而为自动作业与自动驾驶奠定基础。
Depth sensing method for unmanned engineering vehicle in complex working environment
一种复杂作业环境下无人驾驶工程车辆的深度感知方法
2023-12-26
Patent
Electronic Resource
Chinese
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 |
Navigation method and system for unmanned working vehicle and unmanned working vehicle
European Patent Office | 2023
|Environment sensing method and device and unmanned vehicle
European Patent Office | 2024
|Unmanned aerial vehicle depth image acquisition method and unmanned aerial vehicle
European Patent Office | 2016
|