Skip to content
Paper

4D Flight Trajectory Prediction using a Hybrid Deep Learning Prediction Method Based on ADS-B Technology: A Case Study of Hartsfield–Jackson Atlanta International Airport (ATL)

 
Download PDF  (1.56 MB)
Publication: Transportation Research Part C: Emerging Technologies
Volume: 144
Publication Date: 2022
Summary:

At the core of any flight schedule is the four dimensional (4D) trajectories which are comprised of three spatial dimensions with time added as the fourth dimension. Each trajectory contains spatial and temporal features that are associated with uncertainties that make the prediction process complex. Because of the increasing demand for air transportation, airports and airlines must have optimized schedules to best use the airports’ infrastructure potential. This is possible using advanced trajectory prediction methods. This paper proposes a novel hybrid deep learning model to extract spatial and temporal features considering the uncertainty for Hartsfield–Jackson

Atlanta International Airport (ATL). Automatic Dependent Surveillance-Broadcast (ADS–B) with a vast amount of spatial and temporal flight attribute data, are used in this paper as input to the models. This research is conducted in three steps: (a) data preprocessing; (b) prediction by a hybrid Convolutional Neural Network and Gated Recurrent Unit (CNN-GRU) along with a three dimensional (3D-CNN) model; (c) The third and last step is the comparison of the model’s performance with the proposed model by examining the experimental results. The deep model uncertainty is considered using Mont-Carlo dropout (MC-Dropout). Mont-Carlo dropouts are added

to the network layers to enhance the model’s prediction performance by a robust approach of switching off between different neurons. The results show that the proposed model has low error measurements compared to the other models (i.e., 3D CNN, CNN-GRU). The model with MCdropout reduces the error further by an average of 21 %.

Authors: Amelia Regan, Hesam Shafienya
Recommended Citation:
Shafienya, H., & Regan, A. C. (2022). 4D flight trajectory prediction using a hybrid Deep Learning prediction method based on ADS-B technology: A case study of Hartsfield–Jackson Atlanta International Airport (ATL). Transportation Research Part C: Emerging Technologies, 144, 103878. https://doi.org/10.1016/j.trc.2022.103878
Paper

The Automated Driver as a New Road User

 
Download PDF  (2.40 MB)
Publication: Transport Reviews
Pages: 23-Jan
Publication Date: 2020
Summary:

Although road infrastructure has been designed to accommodate human drivers’ physiology and psychology for over a century, human error has always been the main cause of traffic accidents. Consequently, Advanced Driver Assistance Systems (ADAS) have been developed to mitigate human shortcomings. These automated functions are becoming more sophisticated allowing for Automated Driving Systems (ADS) to drive under an increasing number of road conditions. Due to this evolution, a new automated road user has become increasingly relevant for both road owners and the vehicle industry alike. While this automated driver is currently operating on roads designed for human drivers, in the future, infrastructure policies may be designed specifically to accommodate automated drivers. However, the current literature on ADSs does not cover all driving processes. A unified framework for human and automated driver, covering all driving processes, is therefore presented. The unified driving framework, based on theoretical models of human driving and robotics, highlights the importance of sensory input in all driving processes. How human and automated drivers sense their environment is therefore compared to uncover differences between the two road users relevant to adapt road design and maintenance to include the automated driver. The main differences identified between human and automated drivers are that (1) the automated driver has a much greater range of electromagnetic sensitivity and larger field of view, and (2) that the two road users interpret sensory input in different ways. Based on these findings, future research directions for road design and maintenance are suggested.

Authors: Dr. Ed McCormack, Ane Dalsnes Storsaeter, Kelly Pitera
Recommended Citation:
Storsæter, A. D., Pitera, K., & McCormack, E. D. (2020). The automated driver as a new road user. Transport Reviews, 1–23. https://doi.org/10.1080/01441647.2020.1861124
Paper

GPS Truck Data Performance Measures Program in Washington State

 
Download PDF  (1.12 MB)
Publication: Washington State Transportation Center (TRAC)
Publication Date: 2011
Summary:

The Washington State Department of Transportation (WSDOT), Transportation Northwest at the University of Washington (UW), and the Washington Trucking Associations (WTA) have partnered on a research effort to collect and analyze global positioning systems (GPS) truck data from commercial, invehicle, truck fleet management systems. This effort was funded by the Washington State Legislature, and its purpose is to develop a statewide freight performance measures program for use by WSDOT. This document reviews the program’s previous phases and provides details about the latest phase of the program. The report also provides references to the technical documents that support the program.

Authors: Dr. Ed McCormack, Wenjuan Zhao
Recommended Citation:
McCormack, E. D., Zhao, W., & Tabat, D. (2011). GPS Truck Data Performance Measures Program in Washington State. Washington State Department of Transportation, Office of Research.
Paper

Developing Design Guidelines for Commercial Vehicle Envelopes on Urban Streets (Paper)

 
Download PDF  (0.39 MB)
Publication: International Journal of Transport Development and Integration
Volume: 3:02
Pages: 132 - 143
Publication Date: 2019
Summary:

Commercial heavy vehicles using urban curbside loading zones are not typically provided with an envelope, or space adjacent to the vehicle, allocated for loading and unloading activities. While completing loading and unloading activities, couriers are required to walk around the vehicle, extend ramps and handling equipment and maneuver goods; these activities require space around the vehicle. But the unique space needs of delivery trucks are not commonly acknowledged by or incorporated into current urban design practices in either North America or Europe. Because of this lack of a truck envelope, couriers of commercial vehicles are observed using pedestrian pathways and bicycling infrastructure for unloading activities, as well as walking in traffic lanes. These actions put them and other road users in direct conflict and potentially in harm’s way.

This article presents our research to improve our understanding of curb space and delivery needs in urban areas. The research approach involved the observation of delivery operations to determine vehicle type, loading actions, door locations and accessories used. Once common practices had been identified by observing 25 deliveries, simulated loading activities were measured to quantify different types of loading space requirements around commercial vehicles. This resulted in a robust measurement of the operating envelope required to reduce conflicts between truck loading and unloading activities with adjacent pedestrian, bicycle, and motor vehicle activities. From these results, commercial loading zone design recommendations can be developed that will allow our urban street system to operate more efficiently, safely and reliably for all users.

Recommended Citation:
McCormack, Edward, Anne Goodchild, Manali Sheth, and David Hurwitz. Developing Design Guidelines for Commercial Vehicle Envelopes on Urban Streets. International Journal of Transport Development and Integration, 3(2), 132–143. https://doi.org/10.2495/TDI-V3-N2-132-143
Paper

Smart Growth and Goods Movement: Emerging Research Agendas

Publication: Journal Urbanism: International Research on Placemaking and Urban Sustainability
Volume: 2-Aug
Pages: 115-132
Publication Date: 2015
Summary:

While recent urban planning efforts have focused on the management of growth into developed areas, the research community has not examined the impacts of these development patterns on urban goods movement. Successful implementation of growth strategies has multiple environmental and social benefits but also raises the demand for intra-urban goods movement, potentially increasing conflicts between modes of travel and worsening air quality. Because urban goods movement is critical for economic vitality, understanding the relation between smart growth and goods movement is necessary in the development of appropriate policies.

This paper reviews the academic literature and summarizes the results of six focus groups to identify gaps in the state of knowledge and suggest important future research topics in five sub-areas of smart growth related to goods movement: (1) access, parking, and loading zones; (2) road channelization and bicycle and pedestrian facilities; (3) land use; (4) logistics; and (5) network system management.

Authors: Dr. Anne GoodchildDr. Ed McCormack, Erica Wygonik, Alon Bassok, Daniel Carlson
Recommended Citation:
Wygonik, Erica, Alon Bassok, Anne Goodchild, Edward McCormack, and Daniel Carlson. "Smart Growth and Goods Movement: Emerging Research Agendas." Journal of Urbanism: International Research on Placemaking and Urban Sustainability 8, no. 2 (2015): 115-132.
Paper

Reducing Train Turn Times with Double Cycling in New Terminal Designs

 
Download PDF  (0.79 MB)
Publication: Transportation Research Record: Journal of the Transportation Research Board
Volume: 2238
Pages: 14-Aug
Publication Date: 2011
Summary:

North American rail terminals need productivity improvements to handle increasing rail volumes and improve terminal performance. This paper examines the benefits of double cycling in wide-span gantry terminals that use automated transfer management systems. The authors demonstrate that the use of double cycling rather than the currently practiced single cycling in these terminals can reduce the number of cycles required to turn a train by almost 50% in most cases and reduce train turn time by almost 40%. This change can provide significant productivity improvements in rail terminals, increasing both efficiency and competitiveness.

Authors: Dr. Anne Goodchild, J. G. McCall, John Zumerchik, Jack Lanigan
Recommended Citation:
Goodchild, Anne, J. G. McCall, John Zumerchik, and Jack Lanigan Sr. "Reducing Train Turn Times with Double Cycling in New Terminal Designs." Transportation Research Record 2238, no. 1 (2011): 8-14.
Paper

Freeway Truck Travel Time Prediction for Freight Planning Using Truck Probe GPS Data

 
Download PDF  (0.41 MB)
Publication: European Journal of Transport and Infrastructure Research.
Volume: 16
Pages: 76-94
Publication Date: 2016
Summary:

Predicting truck (heavy vehicle) travel time is a principal component of freight project prioritization and planning. However, most existing travel time prediction models are designed for passenger vehicles and fail to make truck specific forecasts or use truck specific data. Little is known about the impact of this limitation, or how truck travel time prediction could be improved in response to freight investments with an improved methodology. In light of this, this paper proposes a pragmatic multi-regime speed-density relationship based approach to predict freeway truck travel time using empirical truck probe GPS data (which is increasingly available in North American and Europe) and loop detector data. Traffic regimes are segmented using a cluster analysis approach. Two case studies are presented to illustrate the approach. The travel time estimates are compared with the Bureau of Public Roads (BPR) model and the Akçelik model outputs. It is found that the proposed method is able to estimate more accurate travel times than traditional methods. The predicted travel time can support freight prioritization and planning.

Recommended Citation:
Wang, Zun, Anne V. Goodchild, and Edward McCormack. "Freeway truck travel time prediction for freight planning using truck probe GPS data." European Journal of Transport and Infrastructure Research 16, no. 1 (2016).