摘要
交叉路口因其交通参与者类型复杂、交通行为随机性大等特点成为城市交通事故常发的典型场景。本文总结14种典型交叉路口冲突场景,通过事故案例及自然驾驶数据分析单车多传感器信息融合感知技术在交叉路口下的潜在风险,并提出交叉路口自动驾驶感知技术方案构想,为提升城市交叉路口交通安全提供参考。
Due to complex types of traffic participants and large randomness of traffic behaviors,intersection scene has become a typical scene of urban traffic accident and a severe challenge for the application of automatic driving urbanization.This paper extracts 14typical intersection conflict scenarios and analyzes the potential risks of multi-sensor information fusion technology of single automobile at intersection scene,and finally puts forward a technical scheme of automatic driving perception at intersection scene.Suggestions for promoting traffic safety at urban intersections are provided.
作者
周建华
宋瑞
刘名洋
邹志亮
Zhou Jianhua;Song Rui;Liu Mingyang;Zou Zhiliang(CATARC Automotive Test Center(Guangzhou)Co.,Ltd.,Guangzhou 511340;Chang'an University,Xi'an 710064;China Automotive Technology and Research Center Co.,Ltd.,Tianjin 300300)
出处
《中国汽车》
2022年第5期32-38,共7页
China Auto
关键词
交叉路口
交通冲突
融合感知
自动驾驶
intersection
traffic conflict
multi-source information fusion
automatic driving