%0 Journal Article
%T 基于深度学习的智能网联汽车无人驾驶障碍物检测研究<br>Research on Obstacle Detection for Intelligent Connected Autonomous Vehicles Based on Deep Learning
%A 何东益
%A 汪晓攀
%A 张瑾
%J Journal of Sensor Technology and Application
%P 38-47
%@ 2331-0243
%D 2025
%I Hans Publishing
%R 10.12677/jsta.2025.131006
%X 在智能网联汽车技术领域&#65292;由于无人驾驶技术的飞速进步&#65292;障碍物识别技术已经变成了确保驾驶安全的核心环节。这项研究成功地开发了一个基于深度学习技术的障碍物检测系统&#65292;该系统是基于精心构建的卷积神经网络(CNN)框架&#65292;并融合了多种传感器的数据信息&#65292;以期达到有效&#65292;准确地识别多变道路环境下障碍物。通过试验数据验证&#65292;本系统无论从辨识的精度&#65292;响应速度还是稳定性上都超过传统方法&#65292;从而为无人驾驶技术发展提供坚实技术支撑。<br>In the field of intelligent connected vehicle technology, due to the rapid advancement of autonomous driving technology, obstacle detection has become a crucial aspect of ensuring driving safety. This study successfully developed an obstacle detection system based on deep learning technology. This system is built upon a meticulously constructed Convolutional Neural Network (CNN) framework and integrates data from multiple sensors to effectively and accurately identify obstacles in diverse road environments. Experimental data validation has shown that this system surpasses traditional methods in terms of recognition accuracy, response speed, and stability, thereby providing solid technical support for the development of autonomous driving technology.
%K 深度学习&#65292
%K 智能网联汽车无人驾驶&#65292
%K 障碍物检测&#65292
%K 卷积神经网络<br>Deep Learning
%K Intelligent Connected Autonomous Vehicles
%K Obstacle Detection
%K Convolutional Neural Network
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=105678