Interterminal Truck Routing Optimization Using Cooperative Multiagent Deep Reinforcement Learning

Many ports worldwide continue to expand their capacity by developing a multiterminal system to catch up with the global containerized trade demand. However, this expansion strategy increases the demand for container exchange between terminals and their logistics facilities within a port, known as interterminal transport (ITT). ITT forms a complex transportation network in a large port, which must be managed efficiently given the economic and environmental implications. The use of trucks in ITT operations leads to the interterminal truck routing problem (ITTRP), which has been attracting increasing attention from researchers. One of the objectives of truck routing optimization in ITT is the minimization of empty-truck trips. Selection of the transport order (TO) based on the current truck location is critical in minimizing empty-truck trips. However, ITT entails not only transporting containers between terminals operated 24 h: in cases where containers need to be transported to a logistics facility within operating hours, empty-truck trip cost (ETTC) minimization must also consider the operational times of the transport origin and destination. Otherwise, truck waiting time might be incurred because the truck may arrive before the opening time of the facility. Truck waiting time seems trivial, but it is not, since thousands of containers move between locations within a port every day. So, truck waiting time can be a source of ITT-related costs if it is not managed wisely. Minimization of empty-truck trips and truck waiting time is considered a multiobjective optimization problem. This paper proposes a method of cooperative multiagent deep reinforcement learning (RL) to produce TO truck routes that minimize ETTC and truck waiting time. Two standard algorithms, simulated annealing (SA) and tabu search (TS) were chosen to assess the performance of the proposed method. The experimental results show that the proposed method represents a considerable improvement over the other algorithms.

An Exact Algorithm for Heterogeneous Drone-Truck Routing Problem

Recently, there are attempts to utilize drones in the logistic application. We consider the case in which there are multiple drones with different characteristics, such as speed and battery capacity. The truck and drone collaborate the delivery to serve all customers, while the drones are carried by and dispatched from the truck. The multiple drones can be deployed simultaneously; however, the truck must wait until all drones return. Therefore, the goal is to minimize the total sum of truck travel and waiting times for drones to return after deliveries. We call the proposed model a heterogeneous drone-truck routing problem (HDTRP), and a mixed-integer programming formulation for the problem is presented. We develop an exact algorithm based on the logic-based Benders decomposition approach, which outperforms the state-of-the-art solvers.

Truck routing cut and fill problem in roadworks using integer programming

Planejar as atividades de distribuição de materiais em obras de terraplenagem pode representar um ganho na obra como um todo. Uma das formas de fazer isso é minimizar a distância total percorrida pelos veículos, por exemplo caminhões na movimentação de terra entre as zonas de corte e aterro. Há muitos estudos e trabalhos que focam a otimização da distribuição de materiais entre zonas de corte e aterro, porém poucos aplicaram em projetos reais com a consideração de múltiplos equipamentos, além de não terem feito uma análise baseada na distância entre estacas. Este artigo tem como objetivo desenvolver um modelo de Programação Inteira que minimize a distância percorrida pelos caminhões basculantes em atividades de distribuição de materiais na terraplenagem. O modelo elaborado com princípios da Programação Linear Inteira foi baseado no problema de roteamento, cujo objetivo é minimizar o caminho percorrido. O modelo foi aplicado em dois estudo de casos cujos resultados destacam ganhos significativos, em termos de flexibilidade do processo de planejamento. Engenheiros, planejadores e analistas têm uma importante ferramenta computacional que facilitará a tomada de decisão.

AN INTEGER PROGRAMMING APPROACH FOR SINGLE TRUCK ROUTING-AND-SCHEDULING PROBLEMS TO ISLANDS WITH TIME-VARYING FERRY SCHEDULES

This study aims to develop a solving model for the single trucks routing-and-scheduling problems to islands with variations in ferry schedules. In this problem, the travel time is asymmetric and the truck routing is based on the sequence of island visits, known and unknown. The models are developed using an integer programming approach. Integer non-linear programming is formulated to solve problems where the sequence is unknown, whereas integer linear programming for the sequence is known. Besides, a delivery day scenario is built to determine the optimal route and schedule with minimum total travel time on each departure day. Numerical experiments were carried out on the case of a small distribution of a small industry in Central Moluccas, Indonesia. The results showed that the model developed could provide solutions to solve problems.

Hyperpath Truck Routing in an Online Freight Exchange Platform

Online freight exchange (OFEX) platforms serve the purpose of matching demand and supply for freight in real time. This paper studies a truck routing problem that aims to leverage the power of an OFEX platform. The OFEX routing problem is formulated as a Markov decision problem, which we solve by finding the bidding strategy at each possible location and time along the route that maximizes the expected profit. At the core of the OFEX routing problem is a combined pricing and bidding model that simultaneously (1) considers the probability of winning a load at a given bid price and current market competition, (2) anticipates the future profit corresponding to the current decision, and (3) prioritizes the bidding order among possible load options. Results from numerical experiments constructed using real-world data from a Chinese OFEX platform indicate that the proposed routing model could (1) improve a truck’s expected profit substantially, compared with the benchmark solutions built to represent the state of the practice, and (2) enhance the robustness of the overall profitability against the impact of market competition and spatial variations.

Interterminal Truck Routing Optimization Using Deep Reinforcement Learning

The continued growth of the volume of global containerized transport necessitates that most of the major ports in the world improve port productivity by investing in more interconnected terminals. The development of the multiterminal system escalates the complexity of the container transport process and increases the demand for container exchange between different terminals within a port, known as interterminal transport (ITT). Trucks are still the primary modes of freight transportation to transport containers among most terminals. A trucking company needs to consider proper truck routing planning because, based on several studies, it played an essential role in coordinating ITT flows. Furthermore, optimal truck routing in the context of ITT significantly affects port productivity and efficiency. The study of deep reinforcement learning in truck routing optimization is still limited. In this study, we propose deep reinforcement learning to provide truck routes of a given container transport order by considering several significant factors such as order origin, destination, time window, and due date. To assess its performance, we compared between the proposed method and two approaches that are used to solve truck routing problems. The experiment results showed that the proposed method obtains considerably better results compared to the other algorithms.