The vehicle routing problem with drones (VRPD) involves determining the optimal routes for trucks and drones to collaboratively deliver parcels to customers, aiming to minimize total operational costs. While various heuristic algorithms have been developed to address the problem, existing solutions are built based on simplistic cost models, overlooking the temporal dynamics of the costs, which fluctuate depending on the dynamically changing traffic conditions. In this paper, we present a novel problem called the vehicle routing problem with drones under dynamically changing traffic conditions (Adapt-VRPD) to address the limitation of existing VRPD solutions. We design a novel cost model that factors in the actual travel distance and projected travel time, computed using a machine learning-driven travel time prediction algorithm. A variable neighborhood descent (VND) algorithm is developed to find the optimal truck-drone routes under the dynamics of traffic conditions through incorporation of the travel time prediction model. A simulation study was performed to compare our algorithm with a state-of-the-art VRPD heuristic. Our algorithm outperformed the benchmark, reducing the average and maximum discrepancies from the actual cost by 37.6% and 27.6%, respectively, across various delivery scenarios.

The Vehicle Routing Problem with Drones (VRPD) seeks to optimize the routing paths for both trucks and drones, where the trucks are responsible for delivering parcels to customer locations, and the drones are dispatched from these trucks for parcel delivery, subsequently being retrieved by the trucks. Given the NP-Hard complexity of VRPD, numerous heuristic approaches have been introduced. However, improving solution quality, the definition of which can vary depending on various heuristic approaches, e.g., the total operation time, remain significant challenges. In this paper, we conduct a comprehensive examination of heuristic methods designed for solving VRPD, distilling and standardizing them into core elements. We then develop a novel reinforcement learning (RL) framework that is seamlessly integrated with the heuristic solution components, establishing a set of universal principles for incorporating the RL framework with heuristic strategies in an aim to improve both the solution quality and computation speed, regardless of how the solution quality is defined. This integration has been applied to a state-of-the-art heuristic solution for VRPD, showcasing the substantial benefits of incorporating the RL framework. Our evaluation results demonstrated that the heuristic solution incorporated with our RL framework not only elevated the quality of solutions but also achieved rapid computation speeds, especially when dealing with extensive customer locations.

The pedestrian crossing intention prediction problem is to estimate whether or not the target pedestrian will cross the street. State-of-the-art techniques heavily depend on visual data acquired through the front camera of the ego-vehicle to make a prediction of the pedestrian's crossing intention. Hence, the efficiency of current methodologies tends to decrease notably in situations where visual input is imprecise, for instance, when the distance between the pedestrian and ego-vehicle is considerable or the illumination levels are inadequate. To address the limitation, in this paper, we present the design, implementation, and evaluation of the first-of-its-kind pedestrian crossing intention prediction model based on integration of motion sensor data gathered through the smartwatch (or smartphone) of the pedestrian. We propose an innovative machine learning framework that effectively integrates motion sensor data with visual input to enhance the predictive accuracy significantly, particularly in scenarios where visual data may be unreliable. Moreover, we perform an extensive data collection process and introduce the first pedestrian intention prediction dataset that features synchronized motion sensor data. The dataset comprises 255 video clips that encompass diverse distances and lighting conditions. We trained our model using the widely-used JAAD and our own datasets and compare the performance with a state-of-the-art model. The results demonstrate that our model outperforms the current state-of-the-art method, particularly in cases where the distance between the pedestrian and the observer is considerable (more than 70 meters) and the lighting conditions are inadequate.

Drone-based last-mile delivery is an emerging technology that uses drones loaded onto a truck to deliver parcels to customers. In this paper, we introduce a fully automated system for drone-based last-mile delivery through incorporation of autonomous vehicles (AVs). A novel problem called the autonomous vehicle routing problem with drones (A-VRPD) is defined. A-VRPD is to select AVs from a pool of available AVs based on crowd sourcing, assign selected AVs to customer groups, and schedule routes for selected AVs to optimize the total operational cost. We formulate A-VRPD as a Mixed Integer Linear Program (MILP) and propose an optimization framework to solve the problem. A greedy algorithm is also developed to significantly improve the running time for large-scale delivery scenarios. Extensive simulations were conducted taking into account real-world operational costs for different types of AVs, traveled distances calculated considering the real-time traffic conditions using Google Map API, and varying load capacities of AVs. We evaluated the performance in comparison with two different state-of-the-art solutions: an algorithm designed to address the traditional vehicle routing problem with drones (VRP-D), which involves human-operated trucks working in tandem with drones to deliver parcels, and an algorithm for the two echelon vehicle routing problem (2E-VRP), wherein parcels are first transported to satellite locations and subsequently delivered from those satellites to the customers. The results indicate a substantial increase in profits for both the delivery company and vehicle owners compared with the state-of-the-art algorithms.

Low-Power Wide-Area Network (LPWAN) is an emerging communication standard for Internet of Things (IoT) that has strong potential to support connectivity of a large number of roadside sensors with an extremely long communication range. However, the high operation cost to manage such a large-scale roadside sensor network remains as a significant challenge. In this article, we propose Low Operation-Cost LPWAN (LOC-LPWAN), a novel optimization framework that is designed to reduce the operation cost using the cross-technology communication (CTC). LOC-LPWAN allows roadside sensors to offload sensor data to passing vehicles that in turn forward the data to a LPWAN server using CTC aiming to reduce the data subscription cost. LOC-LPWAN finds the optimal communication schedule between sensors and vehicles to maximize the throughput given an available budget. Furthermore, LOC-LPWAN optimizes the fairness among sensors by preventing certain sensors from dominating the channel for data transmission. LOC-LPWAN can also be configured to ensure that data packets are received within a specific time bound. Extensive numerical analysis performed with real-world taxi data consisting of 40 vehicles with 24-hour trajectories demonstrate that LOC-LPWAN reduces the cost by 50% compared with the baseline approach where no vehicle is used to relay packets. The results also show that LOC-LPWAN improves the throughput by 72.6%, enhances the fairness by 65.7%, and reduces the delay by 28.8% compared with a greedy algorithm given the same amount of budget.