Intelligent transportation systems

Different innovative concepts are aiming to improve last-mile urban logistics and reduce traffic congestion. Congested metropolitan cities are implementing last-mile delivery robots to make the delivery cheaper and faster. A key factor for the success of Automated Delivery Robots (ADRs) in the last-mile is its ability to meet the fluctuating demand for robots at each micro-hub. Delivery companies rent robots from micro-hubs scattered around the city, use them for deliveries, and return them at micro-hubs. This paper studies the dynamic assignment of the robots to satisfy their demands between the micro-hubs. A Mixed-Integer Linear Programming (MILP) model is developed, which minimizes the total transportation costs by determining the optimum required fleet size. The result determines the number of robots required for each planning period to meet all the demands. It provides algorithms to operate and schedule the robot-sharing system in the last leg of the delivery in dense urban areas.

Today transportation systems are facing big transitions all over the world. We created fly overs, roads under the ground, bridges over the river and ocean to get efficient access and to increase the road connectivity. Our transportation system is more intelligent than ever. Our traffic signaling system became adaptive. Our vehicles equipped with new gadgets and we developed new tools for more efficient analysis of traffic. Our research relies on existing traffic infrastructure to generate better understanding of traffic. More specifically, this research focused on traffic and UAV cameras to extract information about the traffic. Our first goal was to create an automatic system to count the cars using traffic cameras. To achieve this goal, we implemented Background Subtraction Method (BSM) and OverFeat Framework. BSM compares consecutive frames to detect the moving objects. Because BSM only works for ideal lab conditions, therefor we implemented a Convolutional Neural Network (CNN) based classification algorithm called OverFeat Framework. We created different segments on the road in various lanes to tabulate the number of passing cars. We achieved 96.55% accuracy for car counting irrespective of different visibility conditions of the day and night. Our second goal was to find out traffic density. We implemented two CNN based algorithms: Single Shot Detection (SSD) and MobileNet-SSD for vehicle detection. These algorithms are object detection algorithms. We used traffic cameras to detect vehicles on the roads. We utilized road markers and light pole distances to determine distances on the road. Using the distance and count information we calculated density. SSD is a more resource intense algorithm and it achieved 92.97% accuracy. MobileNet-SSD is a lighter algorithm and it achieved 79.30% accuracy. Finally, from a moving platform we estimated the velocity of multiple vehicles. There are a lot of roads where traffic cameras are not available, also traffic monitoring is necessary for special events. We implemented Faster R-CNN as a detection algorithm and Discriminative Correlation Filter (with Channel and Spatial Reliability Tracking) for tracking. We calculated the speed information from the tracking information in our study. Our framework achieved 96.80% speed accuracy compared to manual observation of speeds.

Freight transportation is a significant component of the nation’s economy. However, the augmented volume of the freight movements contributed to continuously increasing congestion on the urban road networks, that affects the timeliness and reliability of freight transportation. In addition, congestion has a negative impact on the transit operations as well. Various studies conducted on multi-modal corridors recognized the importance of the simultaneous performance of freight and transit operations. Thus, Intelligent Transportation System (ITS) components, such as Freight Signal Priority (FSP) and Transit Signal Priority (TSP), present traffic operations strategies "shaped" to give priority, reduce delay and travel time, and overall improve the performance of freight and transit movements, respectively. The primary objective of the thesis refers to evaluate possible improvements in freight mobility, while sustaining good transit services and minimizing congestion on the multi-modal corridor, through simultaneous implementation of the FSP and the TSP. The effectiveness of the newly established criteria was evaluated through real-world case study on a micro-simulation platform. The results showed significant improvements on all the vehicle movements.

The United States has been going through a road accident crisis for many
years. The National Safety Council estimates 40,000 people were killed and 4.57
million injured on U.S. roads in 2017. Direct and indirect loss from tra c congestion
only is more than $140 billion every year. Vehicular Ad-hoc Networks (VANETs) are
envisioned as the future of Intelligent Transportation Systems (ITSs). They have a
great potential to enable all kinds of applications that will enhance road safety and
transportation efficiency. In this dissertation, we have aggregated seven years of real-life tra c and
incidents data, obtained from the Florida Department of Transportation District 4.
We have studied and investigated the causes of road incidents by applying machine
learning approaches to this aggregated big dataset. A scalable, reliable, and automatic
system for predicting road incidents is an integral part of any e ective ITS. For this
purpose, we propose a cloud-based system for VANET that aims at preventing or at
least decreasing tra c congestions as well as crashes in real-time. We have created,
tested, and validated a VANET traffic dataset by applying the connected vehicle
behavioral changes to our aggregated dataset. To achieve the scalability, speed, and fault-tolerance in our developed system, we built our system in a lambda architecture
fashion using Apache Spark and Spark Streaming with Kafka.
We used our system in creating optimal and safe trajectories for autonomous
vehicles based on the user preferences. We extended the use of our developed system in
predicting the clearance time on the highway in real-time, as an important component
of the traffic incident management system. We implemented the time series analysis
and forecasting in our real-time system as a component for predicting traffic
flow.
Our system can be applied to use dedicated short communication (DSRC), cellular,
or hybrid communication schema to receive streaming data and send back the safety
messages.
The performance of the proposed system has been extensively tested on the
FAUs High Performance Computing Cluster (HPCC), as well as on a single node
virtual machine. Results and findings confirm the applicability of the proposed system
in predicting traffic incidents with low processing latency.

Macroscopic fundamental diagram is the concept of the highest importance in traffic flow theory used for development of network-wide control strategies. Previous studies showed that so called Arterial Fundamental Diagrams (AFDs) properly depict relationships between major macroscopic traffic variables on urban arterials. Most of these studies used detector’s occupancy as a surrogate measure to represent traffic density. Nevertheless, detector’s occupancy is not very often present in the field data. More frequently, field data from arterial streets provide performance metrics measured at the stop lines of traffic signals, which represent a hybrid of flow and occupancy. When such performance measures are used in lieu of density, the outcomes of the relationships between macroscopic fundamental variables can be confusing. This study investigates appropriateness of using degree of saturation, as a representative surrogate measure of traffic density, obtained from an adaptive traffic control system that utilizes stop-line detectors, for development of AFDs.

Traffic congestion is one of the most concerning issues in the transportation system. Recurrent congestion and non-recurrent congestion are explored in this research. This research will investigate one of the most concerning issues with the transportation system, congestion, using an overall delay analysis study. A developed fused database program was used to access and analyze the complete database data. Two online databases were used for obtaining traffic, incident and weather data. Eleven different scenarios such as peak-hours, rain scenario, incidents scenario, and work zone scenario were developed for the analysis. An overall delay study was performed on all
scenarios to find the impact recurring and non-recurring congestion on the highway. The results of this research were interesting for future adjustment and improvements on the two segments of highways selected.

This work presents the development of the Context-Aware Hybrid Data Dissemination
protocol for vehicular networks. The importance of developing vehicular networking data
dissemination protocols is exemplified by the recent announcement by the U.S. Department of Transportation (DOT) National Highway Traffic Safety Administration (NHTSA) to enable vehicle-to-vehicle (V2V) communication technology. With emphasis on safety, other useful applications of V2V communication include but are not limited to traffic and routing, weather, construction and road hazard alerts, as well as advertisement and entertainment. The core of V2V communication relies on the efficient dispersion of relevant data through wireless broadcast protocols for these varied applications. The challenges of vehicular networks demand an adaptive broadcast protocol capable of handling diverse applications. This research work illustrates the design of a wireless broadcast protocol that is context-aware and adaptive to vehicular environments taking into consideration vehicle density, road topology, and type of data to be disseminated. The context-aware hybrid data dissemination scheme combines store-and-forward and multi-hop broadcasts, capitalizing on the strengths of both these categories and mitigates the weaknesses to deliver data with maximum efficiency to a widest possible reach. This protocol is designed to work in both urban and highway mobility models. The behavior and performance of the hybrid data dissemination scheme is studied by varying the broadcast zone radius, aggregation ratio, data message size and frequency of the broadcast messages. Optimal parameters are determined and the protocol is then formulated to become adaptive to node density by keeping the field size constant and increasing the number of nodes. Adding message priority levels to propagate safety messages faster and farther than non-safety related messages is the next context we add to our adaptive protocol. We dynamically
set the broadcast region to use multi-hop which has lower latency to propagate
safety-related messages. Extensive simulation results have been obtained using realistic vehicular network scenarios. Results show that Context-Aware Hybrid Data Dissemination Protocol benefits from the low latency characteristics of multi-hop broadcast and low bandwidth consumption of store-and-forward. The protocol is adaptive to both urban and highway mobility models.

Highway Capacity Manual (HCM) 2010 methodology for freeway operations contain procedures for calculating traffic performance measures both for undersaturated and oversaturated flow conditions. However, one of the limitations regarding oversaturated freeway weaving segments is that the HCM procedures have not been extensively calibrated based on field observations on U.S. freeways. This study validates the HCM2010 methodology for oversaturated freeway weaving segment by comparing space mean speed and density obtained from HCM procedure to those generated by a microsimulation model. A VISSIM model is extensively calibrated and validated based on NGSIM field data for the US 101 Highway. Abundance of the NGSIM data is utilized to calibrate and validate the VISSIM model. Results show that HCM methodology has significant limitations and while in some cases it can reproduce density correctly, the study finds that speeds estimated by the HCM methodology significantly differ from those observed in the field.