Automatic Driving Material Handling Vehicle Station Location and Scheduling Mathematical Modeling and Analysis

Traditional material handling vehicles often use internal combustion engines as their power source, which results in exhaust emissions that pollute the environment. In contrast, automated material handling vehicles have the advantages of zero emissions, low noise, and low vibration, thus avoiding exhaust pollution and providing a more comfortable working environment for operators. In order to achieve the goals of “peaking carbon emissions by 2030 and achieving carbon neutrality by 2060”, the use of environmentally friendly autonomous material handling vehicles for material transportation is an inevitable trend. To maximize the amount of transported materials, consider peak-to-valley electricity pricing, battery pack procurement, and the construction of charging and swapping stations while achieving “minimum daily transportation volume” and “lowest investment and operational cost over a 3-year settlement period” with the shortest overall travel distance for all material handling vehicles, this paper examines two different scenarios and establishes goal programming models. The appropriate locations for material handling vehicle swapping stations and vehicle battery pack scheduling schemes are then developed using the NSGA-II algorithm and ant colony optimization algorithm. The results show that, while ensuring a daily transportation volume of no less than 300 vehicles, the lowest investment and operational cost over a 3-year settlement period is approximately 24.1 million Yuan. The material handling vehicles follow the shortest path of 119.2653 km passing through the designated retrieval points and have two shortest routes. Furthermore, the advantages and disadvantages of the proposed models are analyzed, followed by an evaluation, deepening, and potential extension of the models. Finally, future research directions in this field are suggested.

Enhancing safety and efficiency in automated container terminals: Route planning for hazardous material AGV using LSTM neural network and Deep Q-Network

As the proliferation and development of automated container terminal continue,the issues of efficiency and safety become increasingly significant.The container yard is one of the most crucial cargo distribution centers in a terminal.Automated Guided Vehicles(AGVs)that carry materials of varying hazard levels through these yards without compromising on the safe transportation of hazardous materials,while also maximizing efficiency,is a complex challenge.This research introduces an algorithm that integrates Long Short-Term Memory(LSTM)neural network with reinforcement learning techniques,specifically Deep Q-Network(DQN),for routing an AGV carrying hazardous materials within a container yard.The objective is to ensure that the AGV carrying hazardous materials efficiently reaches its destination while effectively avoiding AGVs carrying non-hazardous materials.Utilizing real data from the Meishan Port in Ningbo,Zhejiang,China,the actual yard is first abstracted into an undirected graph.Since LSTM neural network can efficiently conveys and represents information in long time sequences and do not causes useful information before long time to be ignored,a two-layer LSTM neural network with 64 neurons per layer was constructed for predicting the motion trajectory of AGVs carrying non-hazardous materials,which are incorporated into the map as background AGVs.Subsequently,DQN is employed to plan the route for an AGV transporting hazardous materials,aiming to reach its destination swiftly while avoiding encounters with other AGVs.Experimental tests have shown that the route planning algorithm proposed in this study improves the level of avoidance of hazardous material AGV in relation to non-hazardous material AGVs.Compared to the method where hazardous material AGV follow the shortest path to their destination,the avoidance efficiency was enhanced by 3.11%.This improvement demonstrates potential strategies for balancing efficiency and safety in automated terminals.Additionally,it provides insights for designing avoidance schemes for autonomous driving AGVs,offering solutions for complex operational environments where safety and efficient navigation are paramount.

Bibliometric analysis and system review of vehicle routing optimization for emergency material distribution

Determining the optimal vehicle routing of emergency material distribution(VREMD)is one of the core issues of emergency management,which is strategically important to improve the effectiveness of emergency response and thus reduce the negative impact of large-scale emergency events.To summarize the latest research progress,we collected 511VREMD-related articles published from 2010 to the present from the Scopus database and conducted a bibliometric analysis using VOSviewer software.Subsequently,we cautiously selected 49 articles from these publications for system review;sorted out the latest research progress in model construction and solution algorithms;and summarized the evolution trend of keywords,research gaps,and future works.The results show that domestic scholars and research organizations held an unqualified advantage regarding the number of published papers.However,these organizations with the most publications performed poorly regarding the number of literature citations.China and the US have contributed the vast majority of the literature,and there are close collaborations between researchers from both countries.The optimization model of VREMD can be divided into single-,multi-,and joint-objective models.The shortest travel time is the most common optimization objective in the single-objective optimization model.Several scholars focus on multiobjective optimization models to consider conflicting objectives simultaneously.In recent literature,scholars have focused on the impact of uncertainty and special events(e.g.,COVID-19)on VREMD.Moreover,some scholars focus on joint optimization models to optimize vehicle routes and central locations(or material allocation)simultaneously.Solution algorithms can be divided into two primary categories,i.e.,mathematical planning methods and intelligent evolutionary algorithms.The branch and bound algorithm is the most dominant mathematical planning algorithm,while genetic algorithms and their enhancements are the most commonly used intelligent evolutionary algorithms.It is shown that the nondominated sorting genetic algorithmⅡ(NSGA-Ⅱ)can effectively solve the multiobjective model of VREMD.To further improve the algorithm’s performance,researchers have proposed improved hybrid intelligent algorithms that combine the advantages of NSGA-Ⅱand certain other algorithms.Scholars have also proposed a series of optimization algorithms for specific scenarios.With the development of new technologies and computation methods,it will be exciting to construct optimization models that consider uncertainty,heterogeneity,and temporality for large-scale real-world issues and develop generalized solution approaches rather than those applicable to specific scenarios.