Search

Online ride-hailing services provide additional transportation capability by recruiting private vehicles to meet people's growing travel demand. To ensure the profitability of drivers and platforms, pick-up efficiency and frequency must be maintained at high levels. Therefore, consistency between the spatial distribution of drivers and that of travel demand becomes a key issue to address. This paper proposes a prediction-based iterative Kuhn-Munkres approach for service vehicle reallocation in the context of large-scale online ride-hailing. Firstly, preliminaries are formally defined and a novel mathematical model for the problem is proposed. Secondly, a deep spatio-temporal residual perception network is designed to accurately predict travel demand. Thirdly, an iterative Kuhn-Munkres approach combined with an improved A-Star algorithm is developed to reallocate service vehicles to spatial locations according to their distinct travel demand densities. Finally, extensive experiments are conducted to evaluate and verify the performance of the proposed approach. [ABSTRACT FROM AUTHOR]

We propose to use information regarding the fab's future state for Overhead Hoist Transport (OHT) dispatching, which is named as 'predictive dispatching' in this paper. Unlike conventional dispatching methods, two kinds of information are additionally considered in our proposed methods: the expected arrival time of jobs in the near future and the time needed for occupied vehicles to become idle. We firstly develop Basic Predictive Dispatching (BPD) under the assumption that job arrival time prediction is error-free. We demonstrate that BPD consistently surpasses conventional benchmark dispatching methods, even when job arrival time prediction contains a certain level of error. However, as the level of error increases, the performance of BPD deteriorates. To improve BPD's performance in the environment with prediction error, we take the certainty level of job arrival time prediction into consideration in our second method called Certainty Weighted Predictive Dispatching (CWPD). Both BPD and CWPD formulate the OHT dispatching problem as a linear assignment problem, but two different matching cost functions are employed separately. By conducting experiments on a sample semiconductor fab, we validate the effectiveness of our proposed approaches. The superiority of CWPD over BPD in the environment with prediction error is also verified. [ABSTRACT FROM AUTHOR]

Forecasting transportation demands can aid online car-hailing platforms to dispatch their service vehicles in advance to areas with more potential orders. This results in a reduction in passengers' waiting time and better utilisation of transportation resources. However, the complexity and dynamics of multi-dimensional influential factors make the forecasting and dispatching procedures challenging. This paper addresses these issues by using machine learning techniques and an effective probabilistic dispatching strategy. Multiple influential factors were identified in spatial, temporal, and meteorological dimensions, and effective machine learning algorithms were applied to predict the number of passenger orders. The fusion of the multi-dimensional features enables the proposed algorithms to better reveal the spatiotemporal characteristics and their correlations. A sensing-area-based strategy was introduced to dispatch available service vehicles to high demand-intensity regions efficiently with respect to the global demand-supply-balance and the individual probability of receiving orders. Finally, extensive experiments with large-scale real-world datasets were conducted to evaluate the performance of the machine learning algorithms and the effectiveness of the dispatching strategy. Overall, this paper extensively studies the forecasting of the spatiotemporal demand in multiple cities using point-of-interest data and the dispatching of available service vehicles based on such information for online car-hailing platforms. [ABSTRACT FROM AUTHOR]

With the development of information and control technology, fully automatic operation system (FAO) has been widely adopted in the construction of new subway lines. Since the main line operating vehicles under FAO mode do not have driver posts, the dispatchers at the control center need to monitor the running status of all trains on the line in real time to ensure the correct operation of the trains. According to the characteristics of FAO mode , this paper designs a train dispatching system based on big data architecture. The system collects status data of train subsystems and processes and analyzes them based on big data framework,which realizes real-time status monitoring of vehicles on the whole line; and provides human-computer interaction interface for remote control, which meets the requirements of metro operation dispatcher for vehicle running status monitoring. The system has been verified by the third party security assessment, and its stability and availability meet the FAO line operation requirements.

A critical part of Automated Material Handling Systems (AMHS) is the task allocation and dispatching strategy employed. In order to better understand and investigate this component, we here present an extensive experimental evaluation of three different approaches with randomly generated, as well as custom designed, environment configurations. While previous studies typically focused on use cases based on highly constrained navigation capabilities (e.g., overhead hoist transport systems), our evaluation is built around highly mobile, free-ranging vehicles, i.e., Autonomous Mobile Robots (AMR) that are gaining popularity in a broad range of applications. Consequently, our experiments are conducted using a microscopic agent-based simulation, instead of the more common discrete-event simulation model. Dispatching methods often are built around the assumption of the asynchronous evaluation of an event-based model, i.e., vehicles trigger a cascade of individual dispatching decisions, e.g., when reaching intersections. We find that this does not translate very well to a fleet of highly mobile systems that can change direction at any time. With this in mind, we present formulations of well known dispatching approaches that are better suited for a synchronous evaluation of the dispatching decisions. The formulations are based on the Stable Marriage Problem (SMP) and the Linear Sum Assignment Problem (LSAP). We use matching and assignment algorithms to compute the actual dispatching decisions. The selected algorithms are evaluated in a multi-agent simulation environment. To integrate a centralised fleet management, a digital twin concept is proposed and implemented. By this approach, the fleet management is independent of the implementation of the specific agents, allowing to quickly adapt to other simulation-based or real application scenarios. For the experimental evaluation, two new performance measures related to the efficiency of a material handling system are proposed, Travel Efficiency and Throughput Effort. The experimental evaluation indicates that reassignment mechanisms in the dispatching method can help to increase the overall efficiency of the fleet. We did not find significant differences in absolute performance in terms of throughput rate. Additionally, the difference in performance between SMP- and LSAP-based dispatching with reassignment seems negligible. We conclude with a discussion, where we consider potential confounding factors and relate the findings to previously reported results found in the literature. [ABSTRACT FROM AUTHOR]

The demand-responsive public transport system with multi-vehicles has the potential to efficiently meet real-time and high-volume transportation needs through effective scheduling. This paper focuses on studying the real-time vehicle scheduling problem, which involves dispatching and controlling different model vehicles uniformly based on generated vehicle number tasks at a given point in time. By considering the immediacy of real-time itinerary tasks, this paper optimizes the vehicle scheduling problem at a single time point. The objective function is to minimize the total operating cost of the system while satisfying constraints such as passenger capacity and vehicle transfer time. To achieve this, a vehicle scheduling optimization model is constructed, and a solution approach is proposed by integrating bipartite graph optimal matching theory and the Kuhn–Munkres algorithm. The effectiveness of the proposed approach is demonstrated by comparing it with a traditional greedy algorithm using the same calculation example. The results show that the optimization method has higher solution efficiency and can generate a scheduling scheme that effectively reduces operating costs, improves transportation efficiency, and optimizes the operation organization process for demand-responsive buses. [ABSTRACT FROM AUTHOR]

Aiming at the problem that multi lane unsignalized intersections are prone to congestion at high traffic flow, this paper proposes a solution suitable for connected automated vehicle(CAV) at intersections, which decouples the problem into two problems: sequential decision-making and distributed control. Vehicle scheduling is the key point in the scheme, which has a great impact on traffic efficiency, and the complexity of the problem is exponential. this paper proposes a decision method named queue evaluation spanning tree(QEST) to solve this problem based on queue evaluation model, and establishes a cost function based on traffic efficiency and vehicle delay, so as to evaluate the queue, and continuously select the best queue, optimize the traffic sequence of vehicles at intersections and effectively improve the traffic efficiency. For the second problem, this paper proposes a distributed control framework to make vehicles pass through intersections in a predetermined order. The results show that the scheme can effectively improve the traffic efficiency and reduce vehicle delay and energy consumption at intersections with medium and high traffic flow. [ABSTRACT FROM AUTHOR]

A critical part of Automated Material Handling Systems (AMHS) is the task allocation and dispatching strategy employed. In order to better understand and investigate this component, we here present an extensive experimental evaluation of three different approaches with randomly generated, as well as custom designed, environment configurations. While previous studies typically focused on use cases based on highly constrained navigation capabilities (e.g., overhead hoist transport systems), our evaluation is built around highly mobile, free-ranging vehicles, i.e., Autonomous Mobile Robots (AMR) that are gaining popularity in a broad range of applications. Consequently, our experiments are conducted using a microscopic agent-based simulation, instead of the more common discrete-event simulation model. Dispatching methods often are built around the assumption of the asynchronous evaluation of an event-based model, i.e., vehicles trigger a cascade of individual dispatching decisions, e.g., when reaching intersections. We find that this does not translate very well to a fleet of highly mobile systems that can change direction at any time. With this in mind, we present formulations of well known dispatching approaches that are better suited for a synchronous evaluation of the dispatching decisions. The formulations are based on the Stable Marriage Problem (SMP) and the Linear Sum Assignment Problem (LSAP). We use matching and assignment algorithms to compute the actual dispatching decisions. The selected algorithms are evaluated in a multi-agent simulation environment. To integrate a centralised fleet management, a digital twin concept is proposed and implemented. By this approach, the fleet management is independent of the implementation of the specific agents, allowing to quickly adapt to other simulation-based or real application scenarios. For the experimental evaluation, two new performance measures related to the efficiency of a material handling system are proposed, Travel Efficiency and Throughput Effort. The experimental evaluation indicates that reassignment mechanisms in the dispatching method can help to increase the overall efficiency of the fleet. We did not find significant differences in absolute performance in terms of throughput rate. Additionally, the difference in performance between SMP- and LSAP-based dispatching with reassignment seems negligible. We conclude with a discussion, where we consider potential confounding factors and relate the findings to previously reported results found in the literature.

Since some fuel buses have not yet reached their retirement age, many cities still have a mix of fuel buses and electric buses (EBs) operating. This study focuses on multiple bus routes with fuel-electric mixed fleet. To address operation problems arising from separately scheduling vehicles and crews (known as the two-stage method) of each route, we propose a collaborative approach to optimize the vehicle dispatching plan and crew scheduling plan. Initially, we establish a nonlinear programming model by minimizing the overall operating costs of bus companies, encompassing vehicle purchase costs, EB charging costs, fuel bus refueling costs, and driver labor costs. Next, we devise an improved simulated annealing algorithm to solve the model. The proposed method is validated through a case study involving three real-world routes. A comparison with the traditional two-stage method reveals promising outcomes. Results indicate that the proposed method can decrease the number of vehicle changes by 21.43 %, driver labor costs by 2.04 %, and daily operating costs for the bus company by 0.82 %. • A vehicle-crew scheduling method is proposed for fuel-electric mixed bus fleet. • Optimization model is established to minimize the energy costs of multiple routes. • An improved simulated annealing algorithm is developed to solve the model. • Numerical experimentation is conducted using real bus routes. [ABSTRACT FROM AUTHOR]

Online ride-hailing platforms can gather travel requests and allocate service vehicles to balance transportation demands and supplies, which may result in an increase in the utilization rate of service resources and improve the transportation efficiency and social welfare. An effective and flexible dispatching strategy can significantly reduce the waiting time of passengers and increase the profit of service vehicles. In this paper, we propose a real-time service vehicle dispatching framework in the context of large-scale online ride-hailing, which considers all the main issues involved in the problem in a unified and integrated way. Firstly, we formally define the problem and introduce a novel mathematical model based on the spatiotemporal thermo to guide the dispatching process so as to achieve a better balance of demands and supplies. Secondly, we propose an effective machine learning method to predict the spatiotemporal thermo based on the historical data of multi-dimensional factors. Afterward, decision rules to dynamically segment timeframes and a Kuhn-Munkres based algorithm are developed to solve the dispatching problem. Finally, extensive experiments on large-scale real-world instances are conducted to verify the effectiveness of the proposed framework.

The integrated development of city clusters has given rise to an increasing demand for intercity travel. Intercity ride-pooling service exhibits considerable potential in upgrading traditional intercity bus services by implementing demand-responsive enhancements. Nevertheless, its online operations suffer the inherent complexities due to the coupling of vehicle resource allocation among cities and pooled-ride vehicle routing. To tackle these challenges, this study proposes a two-level framework designed to facilitate online fleet management. Specifically, a novel multi-agent feudal reinforcement learning model is proposed at the upper level of the framework to cooperatively assign idle vehicles to different intercity lines, while the lower level updates the routes of vehicles using an adaptive large neighborhood search heuristic. Numerical studies based on the realistic dataset of Xiamen and its surrounding cities in China show that the proposed framework effectively mitigates the supply and demand imbalances, and achieves significant improvement in both the average daily system profit and order fulfillment ratio. • Investigate online fleet operation problem for on-demand intercity ride-pooling services. • Propose a bi-level framework for the coupling problem of vehicle allocation and routing. • Develop a multi-agent feudal network for fleet assignment to enhance agent cooperation. • Verify the performance under various network topologies and supply-demand fluctuations. • Conduct experiments based on realistic operational data to provide managerial insights. [ABSTRACT FROM AUTHOR]

The automation of unified automated material handling system (UAMHS) in 300mm semiconductor wafer fabrication system (SWFS) is complex due to complicated product mixes, numerous and dynamic transportation demands, transportation deadlock, and vehicle blockages. Vehicle dispatching has become one of crucial means to improve the overall operating efficiency of UAMHS. Currently, many vehicle dispatching studies have been devoted to the optimization of the performance indexes of UAMHS. However, more important performance indexes related to SWFS, such as cycle time, throughput, and due date satisfaction, were seldom considered. To bridge this gap, a fuzzy logical and Hungarian algorithm-based (FLHA) vehicle dispatching approach is proposed to obtain better comprehensive performance of UAMHS and SWFS simultaneously. In the proposed approach, candidate wafer lots' transport priority is identified and sorted by fuzzy logic method firstly. Then the wafer lots with higher priority are selected as candidate lots, and it is assigned to the idle transport vehicles based on Hungarian method. After the optimized assigning solution is found, a greedy vehicle transport policy is design to execute it, which can reduce temporary transportation deadlock and vehicles' waste movement effectively. With experimental data from an UAMHS of 300 mm SWFS and running simulation experiments, the results demonstrated that the proposed approach is feasible and effective. Further comparisons with other traditional vehicle dispatching approaches show that the proposed approach has better comprehensive performance in terms of cycle time, throughput, due date satisfaction, delivery time, transport time, and OHT vehicle utilization.

Copyright of Tunnel Construction / Suidao Jianshe (Zhong-Yingwen Ban) is the property of Tunnel Construction Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

A highly desirable performance of a factory is achieving a laminar flow of parts within the factory. This paper proposes new automatic guided vehicle (AGV) dispatching algorithms with the objective of load balancing among the factory work centres by choosing the dispatch decision, which contributes the most to the laminar flow of the factory. The Kullback–Leibler directed divergence measure is applied to compare a dispatch decision with a balanced factory. Simulation experiments are conducted to study the effectiveness of suggested algorithms. [ABSTRACT FROM PUBLISHER]

In this paper, the control problem of multiple-load automated guided vehicles (AGVs) is studied. A control process that identifies four problems faced by multiple-load AGVs is proposed. The first problem is the task-determination problem, in which a multiple-load AGV determines whether its next task is a pickup task or a delivery task. The second problem is the delivery-dispatching problem, in which a multiple-load AGV determines which delivery point it should visit next if its next task is a delivery task. The third problem is the pickup-dispatching problem, in which a multiple-load AGV determines which pickup point it should visit next if its next task is a pickup task. Finally, the fourth problem is the load-selection problem, which requires a multiple-load AGV to determine which load it should pick up from the output queue of a pickup point. This paper focuses on the first and second problems. Different task-determination rules and delivery-dispatching rules are proposed for these two problems. For the problems that are not the main focus of this study, rules found in the literature or real systems are adopted in this study. The objective of this study is twofold. First, we need to understand how well the proposed rules will perform in different performance measures, e.g. the system's throughput and the mean lateness of parts. Second, we need to understand the mutual effects that different types of rules have on each other, so that the best combination of rules can be identified. Computer simulations were conducted to test the performance of the proposed rules. It is hoped the knowledge learned from this study can be beneficial to real multiple-load AGV systems similar to the one studied here. [ABSTRACT FROM AUTHOR]

This study focuses on optimizing resource allocation problems in complex dynamic environments, specifically vehicle dispatching in closed bipartite queuing networks. We present a novel curriculum-driven reinforcement learning (RL) approach that seamlessly incorporates domain knowledge and environmental feedback, effectively addressing the challenges associated with sparse reward scenarios in RL applications. This approach involves a scalable reinforcement learning framework for dynamic vehicle fleet size. We design dense artificial rewards using domain knowledge and incorporate artificial action–reward pairs into the original experience sequence forming the basic structure of the training instances. A difficulty momentum boosting strategy is proposed to produce a series of training instances with progressively increasing difficulty, ensuring that the RL agent learns decision strategies in an organized and smooth manner. Experimental results demonstrate that the proposed method significantly surpasses existing approaches in enhancing productivity and model learning efficiency for transport tasks in open-pit mines, while confirming the superiority of a flexible and automated curriculum learning process over a rigid setting. This approach has vast potential for application in dynamic resource allocation problems across industries, such as manufacturing and logistics. • The integration of expert knowledge and environmental feedback is enabled by curriculum learning. • Smooth and automated training process control can be achieved through model learning feedback. • A scalable reinforcement learning framework for dynamic vehicle fleet dispatching is proposed. • The proposed approach is validated for its effectiveness in the large-scale open-pit mine scenario. [ABSTRACT FROM AUTHOR]

The ride-hailing behaviors of customers are often impacted by various factors including time, geographic distance between locations and weather conditions, causing imbalance between the supply and demand of on-demand ride-hailing dispatch. An effective on-demand ride-hailing dispatching management approach can dispatch idle vehicles and utilize traffic resources more reasonably, increase drivers' income, and improve customers' satisfaction and experience. In order to overcome the disadvantages in on-demand ride-hailing systems, we propose a three-in-one multi-agent reinforcement learning based online algorithm for ride-hailing demand prediction, called ERPM, which can achieve intelligent prediction in an effective and efficient fashion. ERPM tackles the problem that the training phase of traditional reinforcement learning models is difficult to converge due to the high dimensions of input and output data after partitioning the areas that provide platform services into grids, and uses the Actor–Critic strategy to perform on-demand ride-hailing dispatching actions, which are evaluated and optimized to intelligently predict the demand of ride-hailing in the grid areas. In addition, ERPM achieves intelligent parameter update by applying newly designed loss function, learning rate and optimization algorithm, and design an accurate on-demand ride-hailing prediction algorithm on the basis of maximizing the GMV (gross merchandise volume), i.e., the revenues of all on-demand ride-hailing orders served. Compared with traditional machine learning models, the proposed ERPM model is proved to be capable of capturing more complex features of supply and demand from the high dimensions to obtain higher prediction accuracy. Empirical studies are performed on the real Didi Chuxing data, by evaluating the results from extensive experiments, it can be observed that ERPM achieves the highest accuracy of demand prediction on daily GMV and a higher order response rate than the commonly-used famous methods, i.e., for GMV, ERPM outperforms DQN by 9.7% and the Naive model by 14.8%, for the order response rate of ERPM is 1.4% and 4.1% higher than that of DQN and Naive, MAPE (Mean Absolute Percentage Error) of DQN and Naive is 1.61 and 5.94 times higher than that of ERPM, and R 2 of ERPM is improved by 8.70% and 64.8% when compared to that of DQN and Naive, respectively. • Effective on-demand ride-hailing dispatching management approach. • Multi-agent reinforcement learning. • Analyze the impacts of time and geographic locations. • Achieve intelligent parameter update. [ABSTRACT FROM AUTHOR]

In this study, the problem of integration of ready-mixed concrete (RMC) production scheduling and truck and pump dispatching in an RMC plant with multiple mixers is focused upon. A time-space network model, which combines RMC production and vehicle dispatching, is proposed. A heuristic algorithm with eight sets of conjoint priority rules for production scheduling, truck and pump dispatching, and mixer scheduling is developed to solve the problem. Computational experiments are conducted on actual cases collected from an RMC company; these cases are classified into four types based on the quantity of orders from construction sites and the discrete degree of construction sites. The advantages and disadvantages of adopting various conjoint-rules in the various types of cases are determined. The experimental results demonstrate that this heuristic solution is capable of enabling managers of RMC plants to develop more suitable schedules in various types of practical cases. [ABSTRACT FROM AUTHOR]

This study addresses the integration of Vehicle dispatching and container storage location problem with consideration of loading and unloading activities simultaneously. A MIP model is formulated to describe the interrelation between vehicle scheduling, yard crane scheduling and container storage location. A tree structure is used to represent the whole solution space. This representation has a good property as it captures the neighborhood structure and enhances the performance of local search and adaptive searching algorithms. Three variants of tree based searching approaches are developed, namely, the Nested Partitions method (NP), the Beam Search method (BS), and Stochastic Beam Search method (SBS). Extensive experiments show that these proposed methods can find a promising solution in matter of seconds for a practical problem and the Stochastic Beam Search method (SBS) method performs nearly as well as Nested Partitions method (NP) while gaining great computational efficiency. Due to this merit, SBS method is suggested to solve real time integrated vehicle dispatching problem in a relative large scale and may applied in other real time complex system scheduling. [ABSTRACT FROM AUTHOR]

The paper presents the usage of the intelligent processing methods in vehicles to increase an active safety without any interference with a driving process. We are taking into account three aspects. The main goal of the first one is overtaking driver's reactions. The system – based on the soft computing methodology working “on-line”– analyses pictures in front of the vehicle and recognises road events The second aspect – the monitoring devices are able to use automatic number plate recognition techniques to capture and store the various parameters for vehicles recognized in automatic way by the video detection techniques. Data from the monitoring devices are used to analyse the travel time of vehicles – elements of the transportation system. We build the travel time model taking into account the real road situation. The final safety aspect is based on intelligent dispatching method. [ABSTRACT FROM AUTHOR]

As a new logistics technology, self-driving electric vehicles not only improve freight efficiency but also promote energy saving and emissions reductions. Aiming at logistics technologies based on self-driving electric vehicles, planning the vehicle scheduling scheme as a whole reduces energy consumption and improves economic and environmental benefits. Targeting an actual freight problem based on a two-way single-lane road connecting the pickup and delivery points and including electric charging stations, this paper proposes a method for optimizing the scheduling scenario and parameters of self-driving vehicles through computer simulations. An optimization model based on dynamic programming is established, and an optimization simulation algorithm is designed to solve the model, effectively solving the overall planning problem of vehicle scheduling. The experimental results show that the model and algorithm have good universality. After specifying an appropriate road length, total number of vehicles, number of spare vehicle batteries, duration of freight transportation, and other necessary information, the simulation algorithm is executed and the optimal scheduling scheme and the total amount of freight transported are output. The efficiency of the algorithm is extremely high, requiring only 1.5 s to complete the whole simulation process of scheduling 150 vehicles for 1000 h over a road with a length of 10 km.

This paper proposes an online preference learning algorithm named OnPL that can dynamically adapt the policy for dispatching AGVs to changing situations in an automated container terminal. The policy is based on a pairwise preference function that can be repeatedly applied to multiple candidate jobs to sort out the best one. An adaptation of the policy is therefore made by updating this preference function. After every dispatching decision, each of all the candidate jobs considered for the decision is evaluated by running a simulation of a short look-ahead horizon. The best job is then paired with each of the remaining jobs to make training examples of positive preferences, and the inversions of these pairs are each used to generate examples of negative preferences. These new training examples, together with some additional recent examples in the reserve pool, are used to relearn the preference function implemented by an artificial neural network. The experimental results show that OnPL can relearn its policy in real time, and can thus adapt to changing situations seamlessly. In comparison to OnPL, other methods cannot adapt well enough or are not applicable in real time owing to the very long computation time required. [ABSTRACT FROM AUTHOR]

• Abstracting the vehicle dispatching problem as a load balancing problem. • Solving the challenge of concurrent requests with the help of recommendation system. • Designing the DRL method based on the data of a real ride-hailing platform. The vehicle dispatching system is one of the most critical problems in online ride-hailing platforms, which requires adapting the operation and management strategy to the dynamics of demand and supply. In this paper, we propose a single-agent deep reinforcement learning approach for the vehicle dispatching problem called deep dispatching, by reallocating vacant vehicles to regions with a large demand gap in advance. The simulator and the vehicle dispatching algorithm are designed based on industrial-scale real-world data and the workflow of online ride-hailing platforms, ensuring the practical value of our approach. Besides, the vehicle dispatching problem is translated in analogy with the load balancing problem in computer networks. Inspired by the recommendation system, the problem of high concurrency of dispatching requests is addressed by sorting the actions as a recommendation list, whereby matching action with requests. Experiments demonstrate that the proposed approach is superior to existing benchmarks. It is also worth noting that the proposed approach won first place in the vehicle dispatching task of KDD Cup 2020. [ABSTRACT FROM AUTHOR]

Semiconductor Wafer Fabrication System (SWFS) is one of the most complicate discrete processing systems in the world. As the wafer size grows from 200 to 300 mm and then to 450 mm in recent years, the interbay automated material handling system (AMHS) has been widely adopted. How to improve the overall efficiency of interbay material handling has therefore become a critical and urgent problem to be solved. However, the large-scale, dynamic and stochastic production environment significantly substantiates the complexity of the scheduling problem. Aiming to meet the demands of adaptive adjusting, efficient scheduling and multiple-objective optimization, a dynamic dispatching method based on modified Hungarian algorithm is proposed. The system parameters, including cassette due date, cassette waiting time, and system load are simultaneously considered, and furthermore the multi-parameters' weight coefficients are adjusted dynamically by using the fuzzy-logic-based control. Discrete event simulation models are constructed with the eM-Plant software to evaluate the proposed approach. Experimental results show that the proposed dynamic dispatching method improves the system efficiency in terms of mean delivery time, mean waiting time and so on. Meanwhile, the proposed dispatching method has a better comprehensive performance such as the robustness compared to conventional vehicle dispatching approaches. [ABSTRACT FROM AUTHOR]

Automated Guided Vehicles (AGVs) are driverless carriers that automatically navigate along planned paths by means of several guidance and control methods. This paper proposes an approach for solving the dispatching problem in an AGV system. The problem is modelled through a network by relying on the formulation of a Minimum Cost Flow Problem. In the defined graph, the nodes represent transportation tasks and AGVs while the arcs consider, through the associated weights, several system's aspects such as pick, drop, and travel times, battery recharging, capacity constraints, congestion and error issues. Two objectives can be achieved: (i) minimisation of the average time for carrying out transportation tasks or (ii) maximisation of the utilisation degree of AGVs. The modelling and solution approach adopted has provided a novel Vehicle-Initiated dispatching rule and parameters settings for the dynamic assignments of transportation missions to AGVs. The decision making process concurrently and dynamically considers several factors. The results show a relevant reduction in the average time for transportation order fulfilment and a decrease in its variability. The proposed approach has been exploited for optimising the AGVs performance in a pharmaceutical production system. [ABSTRACT FROM AUTHOR]

This paper seeks to address the dispatching problem for vehicles (or prime movers) in a transshipment hub by considering the quay cranes and yard cranes capacity. The objective of this paper is to minimize the makespan time at the quay side. This issue is particularly important for a port which uses information technology in making real time decision because the port can exploit information technology to make full use of the data in making good decision. A mixed integer programming (MIP) model is developed to formulate the problem. As the existing solver cannot solve the MIP model in reasonable time, we develop two heuristics to tackle the problem. The first method is based on the neighborhood search, while the second method is based on genetic algorithm (GA) and minimum cost flow (MCF) network model. Unlike the typical GA which usually represents the chromosome using job sequence, we use the ready time for jobs as the representation of the chromosome, and MCF model is then used to decode the chromosome to determine the job sequence for prime movers. The experiment results indicate the superiority of the GA–MCF-based algorithm over the neighborhood search algorithm. [ABSTRACT FROM AUTHOR]

• A reservation system for autonomous taxi taxi ride-sharing is designed. • Autonomous taxi ride-sharing schedule and depot location are optimized. • Effectiveness in reduction of vehicle usage and energy consumption is analyzed. Taxi ride-sharing based on autonomous vehicles (AVs) is seen as a new and promising mode of urban mobility to promise a huge social and environmental benefits, such as conserving fuel, mitigating traffic congestions, reducing air pollution. Although a number of studies have focused on taxipooling or taxi ride-sharing, majority of these studies just concerned about the vehicle routing problem. Limited studies were conducted to excavate and understand the potential benefits of this new mobility mode through a comprehensively designed taxi ride-sharing system. To fill this gap, this study tries to design an autonomous taxi ride-sharing system for commuting trips from the perspective of energy consumption, in which schedule (i.e., taxi type, taxi path, feet size) and depot location are optimized within a unified model. Based on this, we further evaluate its effectiveness in reductions of energy consumption and vehicle usage, and analyze the influences of several key factors on the system efficiency. Case studies show that the taxi ride-sharing service mode needs fewer vehicles than the private car travel mode, and outperforms the traditional taxi service mode in terms of fuel consumption. Moreover, it is found that trip density is an important influence factor on the benefits of taxi ride-sharing system. This study aims to provide transportation managers a good understanding of the energy benefits of well-designed autonomous taxi ride-sharing system. [ABSTRACT FROM AUTHOR]

Abstract: Incident response measures are continuously being developed to deal with each incident in an effective and timely manner. One critical component in incident response actions is to deploy appropriate response units to the incident scene and clear the incidence as quickly as possible. This paper presents a novel approach for dispatching response units, which incorporates an optimization process for multiple incident response management. An incident response management tool (IRMT) has been developed by integrating Geographic Information System (GIS) with traffic simulation and optimization engines. GIS is employed to provide the primary user interface, process network data, derive the shortest-time path, and visualize the results. The traffic simulation engine is used to simulate incidents in a network, gather link travel times at regular intervals and transmit this time dependent information to GIS. Finally, the optimization engine is used to derive an optimal dispatching strategy by minimizing the total travel time of all the response units. Upon comparison with conventional strategies based on location proximity, the IRMT is found to considerably reduce response time and facilitate resource optimization. [Copyright &y& Elsevier]

In this paper, we aim to develop an integrated Markov model for fleet management decisions such as fleet sizing, vehicle leasing, loaded vehicle dispatching and empty vehicle repositioning in a two-terminal shuttle service, where vehicles are moving between terminals to satisfy random customer demands. The problem is approached in two stages. In the first stage, the optimal vehicle dispatching policy (including vehicle leasing) is derived with fixed fleet size. In the second stage, the fleet size is optimised. The model provides a framework to examine the detailed control structure of the optimal vehicle dispatching policy, which can lead to much simpler near-optimal policies that are easy to interpret and implement for terminal managers. Numerical examples are given to demonstrate the results. [ABSTRACT FROM AUTHOR]

Abstract: Under high load, the automated dispatching of service vehicles for the German Automobile Association (ADAC) must reoptimize a dispatch for 100–150 vehicles and 400 requests in about 10s to near optimality. In the presence of service contractors, this can be achieved by the column generation algorithm ZIBDIP. In metropolitan areas, however, service contractors cannot be dispatched automatically because they may decline. The problem: a model without contractors yields larger optimality gaps within 10s. One way out are simplified reoptimization models. These compute a short-term dispatch containing only some of the requests: unknown future requests will influence future service anyway. The simpler the models the better the gaps, but also the larger the model error. What is more significant: reoptimization gap or reoptimization model error? We answer this question in simulations on real-world ADAC data: only the new models ShadowPrice and can keep up with ZIBDIP. [Copyright &y& Elsevier]

Abstract: This paper proposes neighborhood search heuristics to optimize the planned routes of vehicles in a context where new requests, with a pick-up and a delivery location, occur in real-time. Within this framework, new solutions are explored through a neighborhood structure based on ejection chains. Numerical results show the benefits of these procedures in a real-time context. The impact of a master–slave parallelization scheme, using an increasing number of processors, is also investigated. [Copyright &y& Elsevier]

An important, but seldom investigated, issue in the field of dynamic vehicle routing and dispatching is how to exploit information about future events to improve decision making. In this paper, we address this issue in a real-time setting with a strategy based on probabilistic knowledge about future request arrivals to better manage the fleet of vehicles. More precisely, the new strategy introduces dummy customers (representing forecasted requests) in vehicle routes to provide a good coverage of the territory. This strategy is assessed through computational experiments performed in a simulated environment. [ABSTRACT FROM AUTHOR]

We consider a container terminal discharging and uploading containers to and from ships. The discharged containers are stored at prespecified storage locations in the terminal yard. Containers are moved between the ship area and the yard using a fleet of vehicles, each of which can carry one container at a time. The problem is to dispatch vehicles to the containers so as to minimize the total time it takes to serve a ship, which is the total time it takes to discharge all containers from the ship and upload new containers onto the ship. We develop easily implementable heuristic algorithms and identify both the absolute and asymptotic worst-case performance ratios of these heuristics. In simple settings, most of these algorithms are optimal, while in more general settings, we show, through numerical experiments, that these algorithms obtain near-optimal results for the dispatching problem. [ABSTRACT FROM AUTHOR]

Semiconductor wafer fabrication lines can be characterized by re-entrant product flow, long production lead-time, large variety of production processes, and large capital investment. These distinctive characteristics make the flow control in the fab very complicated. Throughput rate and lead-time are among the most important performance measures. The throughput rate is usually determined by a bottleneck resource, and the lead-time depends on the machine utilization level and the amount of variability in the system. Due to the high efficiency of material handling and reduced particles, automated material handling systems such as automatic guided vehicles (AGVs), overhead hoist transporters (OHTs), and overhead shuttles (OHSs) are being widely used in wafer fabrication lines (wafer fabs) instead of human operators. Although a material handling system itself is seldom a bottleneck of production in a fab, it is important for that to effectively support the bottleneck machines to maximize the throughput and reduce production lead-time. This paper presents a vehicle dispatching procedure based on the concept of theory of constraints, in which vehicle dispatching decisions are made to utilize the bottleneck machines at the maximum level. Simulation experiments have been performed to compare the proposed vehicle dispatching procedure with existing ones under different levels of machine utilization, vehicle utilization, and local buffer capacity. [ABSTRACT FROM AUTHOR]

This research finds the minimum number of vehicles needed in an automated guided vehicle system (AGVS), considering the impact of vehicle dispatching rules, such that the chance of a vehicle-initiated situation occurring is less than a given very small threshold specified by the system designer. Under these conditions, the probability of load requests waiting will be very small and the impact of the vehicle-initiated dispatching rule on the system performance will be negligible. As a result, this research considers only the workcentre-initiated dispatching rule. A model using queuing theory and Markovian processes to represent the relationships among empty-vehicle traveltime, number of vehicles, and the various types of workcentre-initiated dispatching rules is used to formulate a dispatching-rule-based algorithm (DRBA) minimum number of vehicles. Also, given the number of vehicles required in the system, this research investigates the to determine the impact of the nearest-vehicle and farthest-vehicle dispatching rules on the steady-state system performance.This research is able to provide AGVS designers with insights into the system behaviour, e.g. the average waiting time of the load request, in the initial design stage, and to significantly reduce the state space for a more detailed simulation study. [ABSTRACT FROM AUTHOR]