新一代人工智能交通信号控制器架构研究  

Architecture of a New Generation of Artificial Intelligence Traffic Signal Controller

作　　者：张立立[1] 王力[1] ZHANG Lili;WANG Li(Beijing Key laboratory of Urban Road Traffic Intelligent Control Technology,North China University of Technology,Beijing 100144,P.R.China)

机构地区：[1]北方工业大学城市道路交通智能控制技术北京重点实验室

出　　处：《重庆交通大学学报（自然科学版）》2019年第11期6-13,共8页Journal of Chongqing Jiaotong University(Natural Science)

基　　金：国家自然科学基金项目(61603004);北京市自然科学基金项目(4174088);北京市科技新星计划交叉学科合作课题(XXJC201709)

摘　　要：针对口前基于传统交通控制理论设计的信号控制器存在的问题,提出基于边缘计算、场景骡动和交通控制资源化的新一代人工智能交通信号控制器的架构和设计理念。首先,以人工智能感知、决策需求为基础,提出场景驱动、交通控制资源化的全新概念,以此实现人工智能与交通信号控制的有效结合,并通过引入边缘计算重新构建智能交通信号控制器的技术架构;其次,利用边缘计算技术和SD(scene driven,software defined)技术,研究和设计交通信号控制器的软硬件结构;最后,针对下一步需要着力解决的理论和技术难题进行详细阐述。研究结果可为人工智能在城市交通控制领域的应用提供基础支撐和研究思路。Aiming at the existing problems of signal controller based on traditional traffic control theory,the architecture and design concept of a new generation artificial intelligence traffic signal controller based on edge computing,scene driving and traffic control resourcing were proposed.Firstly,a new concept of scene driving and traffic control resourcing based on artificial intelligence perception and decision making needs was proposed,so as to realize the effective combination of artificial intelligence and traffic signal control.The technical architecture of the intelligent traffic signal controller was reconstructed by introducing edge computing technology.Secondly,the hardware and software structure of traffic signal controllers were studied and designed by edge computing technology and SD(scene driven,software defined)technology.Finally,the theoretical and technical problems that needed to be solved in the next step were elaborated in detail.The research results provide basic support and research ideas for the application of artificial intelligence in the field of urban traffic control.

关 键 词：交通运输工程 交通信号控制器 人工智能 边缘计算 场景驱动 交通控制资源化 

分 类 号：U491.3[交通运输工程—交通运输规划与管理]