This study introduces a novel model known as the Parallel Scheduling Vehicle Routing Problem (PSVRP) in an endeavor to revolutionize package delivery by enhancing its efficiency, accessibility, and cost-effectiveness. The PSVRP represents a state-of-the-art approach to vehicle routing problems, incorporating a diversified fleet of innovative delivery modes. The multi-modal fleet of electric vans, ADVs, drones, and truck-drone systems works in unison to minimize operational costs in various settings. The model can also be adapted to different scenarios, such as variations in customer numbers and package weights, by strategically deploying the most suitable mode of transport.

Identification of travelers' transportation modes is a fundamental step for various problems that arise in the domain of transportation such as travel demand analysis, transport planning, and traffic management. In this paper, we aim to identify travelers' transportation modes purely based on their GPS trajectories. First, a segmentation process is developed to partition a user's trip into GPS segments with only one transportation mode. A majority of studies have proposed mode inference models based on hand-crafted features, which might be vulnerable to traffic and environmental conditions. Furthermore, the classification task in almost all models have been performed in a supervised fashion while a large amount of unlabeled GPS trajectories has remained unused. Accordingly, we propose a deep SEmi-Supervised Convolutional Autoencoder (SECA) architecture that can not only automatically extract relevant features from GPS segments but also exploit useful information in unlabeled data. The SECA integrates a convolutional-deconvolutional autoencoder and a convolutional neural network into a unified framework to concurrently perform supervised and unsupervised learning. The two components are simultaneously trained using both labeled and unlabeled GPS segments, which have already been converted into an efficient representation for the convolutional operation. An optimum schedule for varying the balancing parameters between reconstruction and classification errors are also implemented. The performance of the proposed SECA model, trip segmentation, the method for converting a raw trajectory into a new representation, the hyperparameter schedule, and the model configuration are evaluated by comparing to several baselines and alternatives for various amounts of labeled and unlabeled data. Our experimental results demonstrate the superiority of the proposed model over the state-of-the-art semi-supervised and supervised methods with respect to metrics such as accuracy and F-measure.

Emergency response vehicles' (ERVs) travel is risky, as non-ERV drivers are often unsure of the ERV's next maneuver and how to facilitate its movement. An integer linear program (ILP), introduced in this paper, facilitates the ERV's movement through a transportation link. Leveraging vehicle-to-vehicle communications, information is collected about vehicles on a link section. Then, the ILP finds the ERV's fastest intra-link path. To increase safety, the ILP assigns non-ERVs locations as far away from the ERV as possible while avoiding passing and weaving among vehicles. The ILP can be adapted to different ERV sizes, road types, and surrounding conditions. Sensitivity analysis indicated that scenarios with narrower road segments and higher numbers of non-ERVs led to ERV paths with lane changes and higher computation times. When compared with the current practice requiring non-ERVs to move to the nearest road edge when an ERV with lights and sirens is noticed, the proposed formulation improved the ERV speed while reducing the conflicts and confusion experienced by downstream vehicles.

Automated vehicles have the potential to revolutionize our nation's transportation systems as they promise to dramatically reduce congestion, accidents, and fuel usage. Namely, as it becomes possible to precisely exert control on and coordinate the movement and placement of vehicles along a stretch of highway, the separation distance between vehicles can be reduced, thus increasing flow and minimizing congestion. Precise and coordinated vehicle controls and placements also improve predictability, resulting in fewer instances of sudden braking, which reduce fuel usage and accidents. Most existing research has focused on the steady-state behaviors and operations of automated vehicles, such as platooning, and assumes complete knowledge of the system, e.g., the number of vehicles and their destinations and/or neglects dynamic or transition operations such as exiting a highway and lane changing. Uncoordinated lane-changing and exiting behaviors by automated vehicles can significantly reduce the flow of traffic as vehicles will require larger separations, are forced to slow down, or worse, collide. In this paper, we present a collision-free runtime approach to efficiently organize the departures of automated vehicles from a highway environment while maintaining highway capacity in extremely dynamic conditions. To maximize the number of safe departures, the key ideas are to: 1) determine when, and where to, an exiting vehicle should lane change in order to make a successful exit given current traffic conditions as provided by connected vehicle technology and 2) execute the actual lane-change operations using a reservation-based approach. Simulation results show that, by coordinating vehicles' behaviors, traffic flow can be improved by up to five times of today's typical flow while ensuring a 100% exit success rate in a collision-free manner.

Vehicles that are becoming more highly automated are revolutionizing the world's transportation systems for their promise of increased safety and efficiency. The advantage of vehicles incorporating automation is that they do not suffer from the same limitations as human drivers, such as being distracted or impaired. In order to realize the potential of these vehicles, which operate in highly dynamic environments, online techniques are needed. This paper presents such an algorithm to minimize the disruption of traffic flow by optimizing for the number of safe lane changes, thereby increasing throughput and reducing congestion. The proposed algorithm is distributed in nature and makes use of vehicle-to-vehicle and/or vehicle-to-infrastructure communication technologies to judiciously make local lane-change decisions while guaranteeing that no collisions will occur. In contrast to existing work, the proposed technique requires no assumption on the number of lanes, nor on the dynamic attributes of the vehicles such as velocity and acceleration. Simulation results show that the proposed algorithm is both efficient and effective in maximizing the number of lane changes on a given stretch of a highway.

In this work, we employ distance bounding (DB) and verifiable trilateration (VT) for secure localization in an intelligent transportation system (ITS). We first demonstrate several possible attack scenarios, and then establish an analytical framework to evaluate the security of these schemes. Results are derived in terms of the probability of a given position being spoofed by maliciously-controlled vehicles assuming randomly distributed colluding attackers. The results show that while VT outperforms DB, both methods have a high probability of being spoofed.

This work describes a new type of efficiency attack that can be used to degrade the performance of automated vehicular transportation systems. Next-generation transportation technologies will leverage increasing use of vehicle automation. Proposed vehicular automation systems include cooperative adaptive cruise control and vehicle platooning strategies which require cooperation and coordination among vehicles. These strategies are intended to optimize through-put and energy usage in future highway systems, but, as we demonstrate, they also introduce new vulnerabilities. In this work we show that a typical platooning system would allow a maliciously controlled vehicle to exert subtle influence on the motion of surrounding vehicles. This effect can be used to increase the energy expenditure of surrounding vehicles by 20% to 300%.