Human-Like Decision Making of Artificial Drivers in Intelligent Transportation Systems: An End-to-End Driving Behavior Prediction Approach

2021 ◽  
pp. 2-18
Author(s):  
Guofa Li ◽  
Liang Yang ◽  
Shen Li ◽  
Xiao Luo ◽  
Xingda Qu ◽  
...  
Keyword(s):  
Decision Making ◽  
Intelligent Transportation Systems ◽  
Intelligent Transportation ◽  
Driving Behavior ◽  
Transportation Systems ◽  
Behavior Prediction ◽  
End To End ◽  
Prediction Approach

scholarly journals End-to-End Joint Multi-Object Detection and Tracking for Intelligent Transportation Systems

2021 ◽  
Author(s):  
Qing Xu ◽  
Xuewu Lin ◽  
Mengchi CAI ◽  
Yu-ang Guo ◽  
Chuang Zhang ◽  
...  
Keyword(s):  
Object Detection ◽  
Intelligent Transportation Systems ◽  
Data Association ◽  
Intelligent Transportation ◽  
Transportation Systems ◽  
Detection Methods ◽  
Absolute Size ◽  
Detection And Tracking ◽  
Global Correlation ◽  
End To End

Abstract Environment perception is one of the most critical technology of intelligent transportation systems (ITS). Motion interaction between multiple vehicles in ITS makes it important to perform multi-object tracking (MOT). However, most existing MOT algorithms follow the tracking-by-detection framework, which separates detection and tracking into two independent segments and limit the global efficiency. Recently, a few algorithms have combined feature extraction into one network; however, the tracking portion continues to rely on data association, and requires complex post-processing for life cycle management. Those methods do not combine detection and tracking efficiently. This paper presents a novel network to realize joint multiobject detection and tracking in an end-to-end manner for ITS, named as global correlation network (GCNet). Unlike most object detection methods, GCNet introduces a global correlation layer for regression of absolute size and coordinates of bounding boxes, instead of offsetting predictions. The pipeline of detection and tracking in GCNet is conceptually simple, and does not require complicated tracking strategies such as non-maximum suppression and data association. GCNet was evaluated on a multi-vehicle tracking dataset, UA-DETRAC, demonstrating promising performance compared to state-of-the-art detectors and trackers.

scholarly journals Development of a Decision Making Algorithm for Traffic Jams Reduction Applied to Intelligent Transportation Systems

2016 ◽  
Vol 2016 ◽  
pp. 1-16
Author(s):  
David Gómez ◽  
José-Fernán Martínez ◽  
Juana Sendra ◽  
Gregorio Rubio
Keyword(s):  
Decision Making ◽  
Intelligent Transportation Systems ◽  
Traffic Management ◽  
Intelligent Transportation ◽  
Transportation Systems ◽  
Analytic Hierarchy ◽  
Traffic Jams ◽  
Traffic Management System ◽  
Smart Traffic ◽  
Hierarchy Process

This paper is aimed at developing a decision making algorithm for traffic jams reduction that can be applied to Intelligent Transportation Systems. To do so, these algorithms must address two main challenges that arise in this context. On one hand, there are uncertainties in the data received from sensor networks produced by incomplete information or because the information loses some of the precision during information processing and display. On the other hand, there is the variability of the context in which these types of systems are operating. More specifically, Analytic Hierarchy Process (AHP) algorithm has been adapted to ITS, taking into account the mentioned challenges. After explaining the proposed decision making method, it is validated in a specific scenario: a smart traffic management system.

Multicriteria Project Portfolio Selection: Case Study for Intelligent Transportation Systems

2003 ◽  
Vol 1848 (1) ◽  
pp. 125-131 ◽  
Author(s):  
M. Reza Ghaeli ◽  
John Vavrik ◽  
Glenyth Nasvadi
Keyword(s):  
Decision Making ◽  
Portfolio Selection ◽  
Intelligent Transportation Systems ◽  
New Technologies ◽  
Intelligent Transportation ◽  
Transportation Systems ◽  
Public Image ◽  
Project Portfolio ◽  
Project Portfolio Selection

Transportation strategies encompass a portfolio of projects in which choices must be made between competing alternatives. An appropriate portfolio of projects is essential for the success and growth of transportation agencies. The introduction and implementation of emerging technologies such as intelligent transportation systems (ITS) increase the need for more effective decision-making approaches and project selection in the coming years. Transportation projects, particularly, have a broad impact on the public and are multicriteria in nature. The projects also involve several elements of risk, such as project success, public acceptance, or public image. Traditional methods of project evaluation such as benefit–cost analysis focus mainly on the financial rewards of projects and do not sufficiently consider multicriteria and risk evaluations in an integrated framework. Development of an objective and systematic methodology that could address the multicriteria nature of the projects and also deal with their risks and rewards is necessary for both private and public agencies. This need is important particularly when new technologies are implemented, information on project impacts is insufficient, and resources are constrained. An integrated project portfolio selection model is introduced based on the well-established methodologies used for multicriteria evaluation and proven concepts used for portfolio selection in the finance discipline. The new methodology significantly facilitates decision making by integrating both the risk and the value of projects. A case study for selecting ITS projects in a public agency is demonstrated. Guidance is provided in nontechnical language for interpreting the outputs of the methodology.

Sign in / Sign up

Export Citation Format

Share Document