Next Generation Simulation (NGSIM)

Traffic Analysis Tools: Next Generation Simulation - FHWA Operationshttps://ops.fhwa.dot.gov/trafficanalysistools/ngsim.htm

Goal

To develop a core of open behavioral algorithms in support of traffic simulation with a primary focus on microscopic modeling, including supporting documentation and validation data sets that describe the interactions of multimodal travelers, vehicles and highway systems, and interactions presented to them from traffic control devices, delineation, congestion, and other features of the environment.

Objectives

1. To ensure that NGSIM research meets the needs of stakeholders, addresses existing gaps, and that its products are openly distributed and made freely available to the simulation community.
2. To collect data sets for the research, development, and validation of behavioral algorithms and for use by the simulation community.
3. To develop new behavioral algorithms and improve existing algorithms in order to incorporate previously ignored influencing factors and to improve the trustworthiness of existing models.

The NGSIM data sets, algorithms, and reports are freely available for download at the U.S. DOT Intelligent Transportation Systems (ITS) Public Data Hub. Access the NGSIM data directly here.

Additional Resources

• A Model Endeavor - An article by Vassili Alexiadis, James Colyar, and John Halkias: A public-private partnership is working to improve traffic microsimulation technology. (FHWA Public Roads January/February 2007)
• Next Generation SIMulation Fact Sheets
  • NGSIM Overview
  • Freeway Lane Selection Algorithm
  • Interstate 80 Freeway Dataset
  • Lankershim Boulevard Dataset
  • US Highway 101 Dataset

Figure 1 shows the implementation of the overall NGSIM program. Through the NGSIM program, FHWA will develop several driver behavioral algorithms, along with supporting documentation and validation datasets, which represent the fundamental logic within microscopic traffic simulation models. These algorithms will describe the interactions of multimodal travelers, vehicles, and highway systems and the influence posed by traffic control devices, delineation, congestion, and other features of the environment. FHWA will openly distribute NGSIM products and make them freely available to the transportation community through the NGSIM Web site at http://ops.fhwa.dot.gov/trafficanalysistools/ngsim.htm. These products include:

• Real-world datasets and their corresponding data descriptions. These datasets consist of detailed vehicle trajectory, wide-area detector, and supporting data for researching driver behavior. The vehicle trajectory data, which were collected using digital video cameras like the one shown in figure 2, are particularly valuable due to the unprecedented level of detail and accuracy: the precise location of each vehicle on a 0.5- to 1.0-kilometer section of roadway is recorded every one-tenth of a second.
• Core simulation algorithms, which are mathematical models that replicate fundamental driver behavior logic, such as how drivers follow each other or how and when drivers choose to change lanes, which are the foundational logic within traffic simulation models. The algorithms developed and validated under the NGSIM program are based on collected real-world datasets and are intended to fill the gaps and limitations of current simulation models.
• Documentation of the core algorithms, including the theory and logic behind the algorithms, and documentation of the validation datasets.

              Figure 1. This flowchart depicts the implementation of the NGSIM program.

---

 数据集覆盖了结构化道路的路口，高速上下闸道等车路协同研究的热点区域。该项目的研究人员对原始的视频信息做了后处理，生成了交通流中每辆车的行驶轨迹数据。数据集采集于美国的四个不同地区，分别是加州南向的US 101号公路，加州洛杉矶的Lankershim Boulevard地图, 加州埃默里维尔的东向的 I-80号公路，以及佐治亚州亚特拉大的Peachtree Street。

NGSIM数据集可导出为csv格式表单。该表单第一行字段含义如下:

字段	说明	备注
Vehicle_ID	车辆编号	有可能会出现重复
Frame_ID	数据帧号	与该路径点产生的时间相关
Total_Frame	数据总帧	某辆车被跟踪的生命周期（存在长度）
Global_Time	UTC时间	13位的标准UTC时间，精确到ms
Local_X/ Local_Y	采集区域坐标系的X/Y值	局部坐标系下的位置值，常用
v_Vel / v_Acc	车辆的行进方向的速度和加速度	即运动方向的速度及加速度
Lane_ID	车辆所在的车道编号	见图2和图3中的1，2，3等
O_Zone	驶入研究区域的路口，编号从101到111。	表明车辆是从哪个路口驶入这片区域的
D_Zone	驶离研究区域的路口，编号从201到211。	表明车辆是从哪个路口驶离这片区域的
Int_ID	路口编号	共四个，由南向北序号递增

---

Ref:

GitHub - LongshengJiang/NGSIM-tools: This repository collects a set of tools for extracting, visualizing, and simulating Next Generation Simulation (NGSIM) dataset. The tools are originally developed by Stanford Intelligent Systems Laboratory. 
https://github.com/sisl

车路协同路端系统的数据集NGSIM介绍 - 知乎

 NGSIM数据集解析及python处理 - 简书