Search

Maritime autonomous surface ships (MASS) promise enhanced efficiency, reduced human errors, and to improve maritime traffic safety. However, MASS navigation in complex maritime traffic presents challenges, especially in collision avoidance strategy optimization (CASO). This paper proposes a novel risk-based CASO approach based on safe reinforcement learning (SRL) with a reliability and risk hierarchical critic network (SRL-R2HCN) approach. Key steps in developing the approach start with the formulation of collision risk assessment. This is followed by the construction of a hierarchical network structure, supplemented by the supporting reward function, multi-objective function, and reliability measurement to realize the SRL-R2HCN. Finally, simulation experiments are conducted in mixed obstacle scenarios, and the results are compared with traditional algorithms to showcase the advancement and fidelity of the new SRL-R2HCN method. The results demonstrate that the proposed method can accurately assess collision risks in mixed obstacle scenarios and generate safe, efficient, and reliable collision avoidance strategies. The outcomes of this research provide a sound theoretical basis for the future development of MASS navigation safety and significant potential to improve the safe and efficient operations of MASS. Furthermore, the methodology could also benefit maritime transportation and shipping management. [ABSTRACT FROM AUTHOR]

The COVID-19 pandemic has significantly affected the cruise shipping industry, disrupting ports and shipping. However, current research predominantly focuses on the impact on individual ports or vessels, leaving a gap in understanding how these disruptions propagate across cruise shipping networks. To address this gap, a novel vulnerability assessment methodology that offers a comprehensive perspective on the broader impact of COVID-19 on cruise shipping networks is developed. It first uses a new weight social network analysis approach to quantify the vulnerability of each cruise port in a shipping network and then combines the curie port local pandemic risk to generate a new index to reveal the COVID-19 impact on the whole cruise shipping network systematically. The new methodology is applied to analyse the ASEAN cruise shipping network. This real-world COVID-19 pandemic case study yields valuable insights that bridge theoretical and practical domains. Integrating local port-level vulnerabilities with shipping network-level vulnerabilities creates a unique index. This index quantifies the individual and collective influence of COVID-19 risks at different cruise ports on the entire regional cruise shipping network. The results directly impact cruise lines seeking to enhance their operations' resilience in the face of COVID-19 challenges. The vulnerability index explains how risk exposure at various ports shapes the network's dynamics. This insight empowers cruise lines to optimise ship deployment schedules, lowering the network's overall COVID-19 pandemic risk. The research method and outcomes offer a pioneering perspective on the vulnerability of cruise shipping networks to COVID-19 disruptions, and other possible disruptions (e.g., climate change) in a broad sense. By elucidating interconnected vulnerabilities, cruise lines are equipped with actionable insights to navigate the complexities of global challenges. [ABSTRACT FROM AUTHOR]

Abstract Seaports play a vital role in our everyday life: they handle 90% of our world trade goods. Improving seaports' efficiency means improving the efficiency of sending and receiving our goods. In seaports, one of the most important and most expensive operations is how to allocate vessels to berths. In this paper, we solve this problem by proposing a new meta-heuristic, which combines the nature-inspired Levy Flight random walk with local search, while taking into account tidal windows. With our algorithm, we meet the following goals: (i) to minimise the cost of all vessels while staying in the port, and (ii) to schedule available berths for the arriving vessels taking into account a multi-tidal planning horizon. In comparison with the state-of-the-art exact method using commercial solver and a competitive heuristic, the computational results prove our approach guarantees feasibility of solutions for all the problem instances and is able to find good solutions in a short amount of time, especially for large-scale instances. We also compare our results to an existing state-of-the-art Particle Swarm Optimisation and our work produces significantly better performances on all the test instances. [ABSTRACT FROM AUTHOR]

Seafarers are required to make quick decisions to avoid accidents in case of emergencies. However, officers with anxiety generally have a high probability of making wrong decisions that threaten safety and security during the voyage. With the help of a shiphandling simulator, this study aims to investigate the emotional changes of seafarers under simulated scenarios of emergencies. The State-Trait Anxiety Inventory (S-TAI) scale and electrocardiograph (ECG) signal are adopted to evaluate the emotions of the participant seafarers. To classify the anxiety state of the participants, a support vector machine-based method is applied to establish an anxiety recognition model. Classification results reveal that this proposed model can effectively identify different emotions of participants based on ECG features (cross-validation accuracy: 86.0%; test accuracy: 92.3%). The experimental results show that poor visibility could cause the greatest impact on the anxiety of seafarers. In addition, navigational officers and marine pilots react differently in case of emergencies. Seafarers tend to experience more anxiety when dealing with emergency situations, while marine pilots experience more anxiety during multi-ship encounter periods. Consequently, the findings of this study aid to effectively identify the scenarios that cause anxiety emotion of different professional seafarers, providing the corresponding reference for the training of seafarers. This could help prevent catastrophic accidents that pose a threat to oceans and coasts caused by human error. [ABSTRACT FROM AUTHOR]

Abstract Although extant literature has stressed importance of the use of ship management and identified the selection factors, relative evaluation of comprehensive selection factors is found to be lacking. This study aims to evaluate the overall performance and rank of the ship management firms by adopting an integrated model of Analytic Hierarchy Process (AHP) and Fuzzy Technique for Order Preference by Similarity to Ideal Solution (FTOPSIS) in order to support the critical decision making on SMF selection based on multiple criteria. This study contributes to enhancing the selection criteria of ship management firms by the ship-owners, and at the same time identifies the areas that the ship management firms require to improve their service standards. The result indicates that competency is the most important criterion, followed by cost, courtesy, organisation characteristics and image. [ABSTRACT FROM AUTHOR]

Human factors have been deemed to affect a variety of unsafe acts and hazardous conditions, with no exceptions in the maritime sector. With increasing applications of automation techniques in shipping, seafarers' roles are changing, and their competencies require to be assessed and assured for safety at sea accordingly. The studies on seafarer competencies have therefore been tightly bound with a human-machine system which consists of the interaction of seafarers and ship operational systems and sub-systems. To evaluate the seafarer competencies that fit automation systems in shipping, this paper aims to develop a new dynamic human-machine model in shipping that can be used to analyse human factors in a closed-loop system. Based on Crew Resource Management and the International Convention on Standards of Training, Certification and Watchkeeping for Seafarers, it reflects the input, process, and output phases of the human system and its interactions with machine sub-systems. A new tool to analyse seafarer competencies is proposed to rationalise human factor evaluation in the maritime closed-loop system and reflect the dynamic human-machine cooperation process. Two case studies have been conducted to illustrate the feasibility of the new model and in the meantime to investigate seafarer competencies in the dynamic human-machine system. It produces a new human factor analysis tool to investigate maritime accidents. The results and policy implications help explore the adjustment of maritime training to support ship automation and provide guidance on risk management for traditional and autonomous ships. [ABSTRACT FROM AUTHOR]

Psychological factors have been a critical cause of human errors in sectors such as health and aviation. However, there is little relevant research in the maritime industry, even though human errors significantly contribute to shipping accidents. It becomes even more worrisome given that seafarers are changing their roles onboard ships due to the growth of automation techniques in the sector. This research pioneers a conceptual framework for assessing seafarer psychological factors using neurophysiological analysis. It quantitatively enables the psychological factor assessment and hence can be used to test, verify, and train seafarers' behaviours for ship safety at sea and along coasts. A case study on ship collision avoidance in coastal waters demonstrates its feasibility using ship bridge simulation. An experimental framework incorporating neurophysiological data can be utilised to effectively evaluate the contribution of psychological factors to human behaviours and operational risks. Hence, it opens a new paradigm for human reliability analysis in a maritime setting. This framework provides insights for reforming and evaluating operators' behaviours on traditionally crewed ships and in remote-controlled centres within the context of autonomous ships. As a result, it will significantly improve maritime safety and prevention of catastrophic accidents that endanger oceans and coasts. [ABSTRACT FROM AUTHOR]

This study aims to propose a conceptual decision making framework for prioritising port performance improvement strategies. It can be achieved by the concepts of benchmarking-best practices using analytic hierarchy process (AHP) incorporating a fuzzy technique for order preference by similarity to ideal solution (FTOPSIS) method. The leading performer (i.e. Busan New Port) and the poor performer (i.e. Busan North Port) are analysed as real cases to demonstrate the feasibility of the proposed methodology. The findings from the case study reveal that the terminal operating company (TOC) 2 represents a strong desire to choose the given strategies to improve its performance, followed by TOC3, while TOC1 has the least intention to adopt the given strategies. Amongst the 30 strategies of a benefit feature, optimisation of yard stacking planning (S4) is ascertained as the most crucial one to be implemented, followed by optimisation of berth to yard operations (S27) and optimising crane availability (S2). On the other hand, the formal training/education programmes from external professionals (S7) is identified as the most useful strategy among the 8 cost items. The results yielded by the framework present the ranking of strategy options in terms of their preference to different TOCs, which enables decision makers to find optimal solutions to improve performance under their own dynamic business environments. [ABSTRACT FROM AUTHOR]

One of the biggest concerns in liner operations is punctuality of containerships. Managing the time factor has become a crucial issue in today's liner shipping operations. A statistic in 2015 showed that the overall punctuality for containerships only reached an on-time performance of 73%. However, vessel punctuality is affected by many factors such as the port and vessel conditions and knock-on effects of delays. As a result, this paper develops a model for analyzing and predicting the arrival punctuality of a liner vessel at ports of call under uncertain environments by using a hybrid decision-making technique, the Fuzzy Rule-Based Bayesian Network (FRBBN). In order to ensure the practicability of the model, two container vessels have been tested by using the proposed model. The results have shown that the differences between prediction values and real arrival times are only 4.2% and 6.6%, which can be considered as reasonable. This model is capable of helping liner shipping operators (LSOs) to predict the arrival punctuality of their vessel at a particular port of call. [ABSTRACT FROM AUTHOR]

Cybersecurity risks present a growing concern in the maritime industry, especially due to the fast development of digitalised technologies, also vis-à-vis autonomous shipping. Research on maritime cybersecurity is receiving increased attention. This paper aims to assess the cybersecurity risks in the maritime sector and improve safety at sea and in coastal areas. First, we identify all the concerned cyber threats in the sector based on literature review and expert opinion. A novel risk assessment framework of maritime cyber threats, which combines Failure Mode and Effects Analysis (FMEA) with a Rule-based Bayesian Network (RBN), is proposed and used to evaluate the risk levels of the identified threats and to better understand the threats that contribute the most to the overall maritime cybersecurity risk. The results can inform stakeholders about the most vulnerable parts in their cyber operations and stimulate the development of risk-based control measures. More specifically, the next step in managing cyber threats is to tackle the threats that are associated with unacceptable risk levels and identify cost-effective measures to manage them. To that extent, our findings provide a list of top threats – that is the areas where efforts should be focused on. As a result, this work can help the whole community to grow its resilience to cyber-attacks and improve the security of shipping operations. • Maritime cyber threats are identified and verified. • A novel maritime cybersecurity risk analysis method under high uncertainty is proposed. • Failure Mode and Effects Analysis (FMEA) with a Rule-based Bayesian Network (RBN) and a sensitivity analysis are utilised. • Quantitative analysis and prioritisation of the risk levels of maritime cyber threats are presented. • New solutions to enhancing maritime cybersecurity are discussed. [ABSTRACT FROM AUTHOR]

It is necessary to accurately calculate ship carbon emissions for shipping suitability. The state-of-the-art approaches could arguably not be able to estimate ship carbon emissions accurately due to the uncertainties of Ship Technical Specification Database (STSD) and the geographical and temporal breakpoints in Automatic Identification System (AIS) data, hence requiring a new methodology to be developed to address such defects and further improve the accuracy of emission estimation. Firstly, a novel STSD iterative repair model is proposed based on the random forest algorithm by the incorporation of13 ship technical parameters. The repair model is scalable and can substantially improve the quality of STSD. Secondly, a new ship AIS trajectory segmentation algorithm based on ST-DBSCAN is developed, which effectively eliminates the impact of geographical and temporal AIS breakpoints on emission estimation. It can accurately identify the ships' berthing and anchoring trajectories and reasonably segment the trajectories. Finally, based on this proposed framework, the ship carbon dioxide emissions within the scope of domestic emission control areas (DECA) along the coast of China are estimated. The experiment results indicate that the proposed STSD repair model is highly credible due to the significant connections between ship technical parameters. In addition, the emission analysis shows that, within the scope of China's DECA, the berthing period of ships is longer owing to the joint effects of coastal operation features and the strict quarantine measures under the COVID-19 pandemic, which highlights the emissions produced by ship auxiliary engines and boilers. The carbon intensity of most coastal provinces in China is relatively high, reflecting the urgent demand for the transformation and updates of the economic development models. Based on the theoretical models and results, this study recommends a five-stage decarbonization scheme for China's DECA to advance its decarbonization process. • An iteratively ship technical specifications database repair model based on the random forest algorithm is proposed. • A ship AIS trajectory segmentation algorithm based on DBSCAN is proposed. • The carbon emissions from maritime transport in 2019 and 2020 within the scope of domestic emission control areas along the coast of China are estimated. • Results indicate that carbon emissions did not show a significant decrease before and after the COVID-19 pandemic and the carbon intensity of most coastal provinces in China is relatively high. [ABSTRACT FROM AUTHOR]

This work aims to apply a novel approach to assess the risks of maritime supply chains (MSCs) within the context of the Maritime Silk Road (MSR) by employing fuzzy logic and evidential reasoning. Compared to traditional risk analysis methods, the novel approach has its superiorities in dealing with incomplete and vague data, synthesizing multiple data formats, and preventing the loss of important risk information. A case of the risk factors influencing MSCs along the MSR is analysed, and the assessment results reveal that the fuel price is the most significant risk factor. Sensitive analysis is applied to validate and illustrate the rationality and practicality of the proposed approach. The findings can provide the MSR stakeholders with important insights for the safety management of MSCs along MSR. • Use of a hybrid of the fuzzy-ER approach for effective risk assessment of MSRs within the context of the Maritime Silk Road. • A new risk model based fuzzy logic and the ER shows its superiorities in dealing with uncertainty in data. • Define risk parameters of risk events from multi-perspective to facilitate the modelling and understanding of risks in MSCs. • Investigate the MSC to analyse the risk and priorities risk events under uncertainties for decision-making. [ABSTRACT FROM AUTHOR]

A hostile microenvironment in tumor tissues disrupts endoplasmic reticulum homeostasis and induces the unfolded protein response (UPR). A chronic UPR in both cancer cells and tumor-infiltrating leukocytes could facilitate the evasion of immune surveillance. However, how the UPR in cancer cells cripples the anti-tumor immune response is unclear. Here, we demonstrate that, in cancer cells, the UPR component X-box binding protein 1 (XBP1) favors the synthesis and secretion of cholesterol, which activates myeloid-derived suppressor cells (MDSCs) and causes immunosuppression. Cholesterol is delivered in the form of small extracellular vesicles and internalized by MDSCs through macropinocytosis. Genetic or pharmacological depletion of XBP1 or reducing the tumor cholesterol content remarkably decreases MDSC abundance and triggers robust anti-tumor responses. Thus, our data unravel the cell-non-autonomous role of XBP1/cholesterol signaling in the regulation of tumor growth and suggest its inhibition as a useful strategy for improving the efficacy of cancer immunotherapy. [Display omitted] • XBP1 deficiency in tumor cells limits tumor growth by inducing anti-tumor immunity • XBP1 drives the production of cholesterol, which is secreted via tumor-derived sEVs • Cholesterol elicits immunosuppression by activating myeloid-derived suppressor cells • Pharmacologic or genetic inhibition of XBP1/cholesterol signaling reduces tumor growth Yang et al. demonstrate that tumor-intrinsic XBP1 dictates the production of cholesterol, which is secreted via small extracellular vesicles to drive immunosuppressive reprogramming by activating myeloid-derived suppressor cells. Blocking the IRE1α-XBP1-cholesterol axis reduces tumor growth. [ABSTRACT FROM AUTHOR]

Due to the development of ship sizes and the traffic increase in port, ships having long turnaround time in port often result in port congestion, which seriously affects the efficiency of the ship navigation and environmental sustainability of port, it has been evident that effective ship scheduling presents a solution of the fundamental and strategic importance to port congestion. In this paper, a mixed-integer linear programming mathematical model is proposed to realize the optimization of the ship scheduling in port to minimize the total time spent by ships in port. Its methodological novelty is gained by an innovative adaptive genetic simulated annealing algorithm based on a reinforcement learning algorithm (GSAA-RL) to support the developed mathematical model, in which the genetic algorithm is considered as the basic optimization algorithm, and Q-learning with a unique property of selecting suitable parameters dynamically is developed to adjust the parameters of crossover and mutation to improve the search ability of the algorithm. Meanwhile, the dynamic parameter turning process is formulated into a Markov decision process (MDP) model with well defining the state, action, and reward function in GSAA-RL. Specifically, the state sets are proposed by analyzing the key factors affecting the scheduling efficiency and a new reward mechanism that can reduce the objective value significantly based on the quality of selected parameters is designed. The annealing operation is performed on some excellent individuals to further expand the search scope. Simulation experiments demonstrate that the proposed GSAA-RL algorithm can significantly shorten the total time spent by ships in port compared to existing approaches. This study hence helps port operators/planners to improve operational efficiency and reduce port congestion, reduce ship fuel consumption, and deliver goods to cargo owners in a timely manner, which has important practical significance for achieving the "dual carbon" goal. [ABSTRACT FROM AUTHOR]

In a 2019 European Commission report, the Blue Economy (BE) within the United Kingdom (UK) represented 22% of the European Union's (EU) BE Gross Value Added (GVA) at approximately €39 billion. Coupled with the clear value of the BE to the UK, there is an urgent need to innovate and develop technologies to decarbonise and advance the sector. A deeper understanding of the current position for multiple stakeholders must be considered before any major governmental or long-term strategy decisions can be made. This paper presents the perspective of academic, industrial and governmental stakeholders analysis of how the UK can move forward with developing innovations within the BE. Utilising a questionnaire and round table discussions, specialists from all stakeholders gave their opinions on industry-academia-governmental working relationships and technology transfer readiness. Reasonably high satisfaction was found with key aspects that enable a successful collaborative project between academia and industry towards technology commercialisation; however, there is still room for improvement. This paper offers an analysis of how to further enhance and foster technology development within the UK BE. A collaborative approach is proposed to ensure best practices, and a 'triple helix' (TH) collaboration strategy to be used as a tool for those engaging in these types of working relationships. Future directions on enhancing technology transfer innovation within the UK BE are also suggested. [ABSTRACT FROM AUTHOR]

Compared to cargo terminals, performance evaluation of cruise terminals sits in a backseat in the current port performance studies, particularly in the Northeast Asia. This paper aims to evaluate the performance of major cruise terminals in Asia, taking into account the important dimensions and criteria influencing cruise terminal development, and using primary data by experts' responses to a questionnaire survey. Complementary data are also acquired by field trips and interviews to find the hidden information that is not revealed from the set questions in the questionnaire survey. To tackle the multiplicity and uncertainty in the collected data, the hybrid of Preference Ranking Organization Method for Enrichment Evaluations (PROMETHEE) and Consistent Fuzzy Preference Relation (CFPR) is employed to evaluate cruise terminal performance and highlight visual illustration of the test results. The findings provide useful insights for guiding cruise lines' terminal selection and for aiding cruise terminals to benchmark their performance to effectively improve their service and maximize their overall performance. • This paper evaluates performance of major cruise terminals in Asia, taking into account important dimensions and criteria influencing cruise terminal operation and development. • To tackle the multiplicity and uncertainty in the collected data, this paper applies the hybrid of PROMETHEE and Consistent Fuzzy Preference Relation. • This paper provides cruise terminal performance and highlights visual illustration of the test results. • The findings provide useful insights and managerial implications for guiding cruise lines' terminal selection and for impoving their terminal performance. [ABSTRACT FROM AUTHOR]

Abstract: Being nodal points along supply chains, ports affected by climate change would create substantial costs to the global economy and welfare, and thus it is extremely important to ensure that ports can develop effective adaptation strategies. However, there are many uncertainties, as the dynamics between climate change and ports can diversify between different regions. Against this background, through exploratory case studies of four ports in Australia, this paper investigates climate change and the adaptation strategies of ports, with a special focus on port infrastructures and the day-to-day operational impacts. Research findings indicate that, while port managers recognize climate change as an issue which requires closer attention, adaptation strategies have remained segregated and piecemeal. This highlights the fact that effective adaptation solutions are not just about physical layouts and engineering projects, but the need to fundamentally transform the current management and planning practices of ports. It is a timely reminder to port policymakers and managers on the need to refine how effective decisions should be made for the challenges posed by climate changes in the future. In this regard, further research on this topic is urgently required. [Copyright &y& Elsevier]

Rapid development of maritime transportation networks meets international trade demands while rendering them in high risk and disruption concerns particularly at ports being the bottlenecks of the whole flows. Port operations calls for an effective approach to assess ports vulnerability and to ensure the resilience of their associated maritime supply chains (MSC). However, traditional quantitative risk analysis reveals challenges due to data incompleteness and ambiguity, and operational and environmental uncertainty when being applied in ports vulnerability analysis. This paper aims to develop a novel port vulnerability assessment (PVA) framework, which can guide and realise a standardised vulnerability analysis process for the ports from different geographies involving in the same MSC and hence the resources can be better managed from a global network level for optimal resilience of the chain. It is especially important for the shipping and port industries which are in nature international and desires strong international uniform standardization. The fuzzy theory, evidential reasoning (ER) approach, and expected utility theory are combined in a holistic way to form the proposed PVA framework. The new framework is validated and demonstrated by using a case study in which five key ports along an established MSC in China are investigated. The findings can be used as a stand along method to compare the vulnerability levels of the ports in an MSC and/or integrated with decision optimisation methods for rational safety resource distribution from a supply chain perspective. • Use of a hybrid of the fuzzy theory and ER methods for port vulnerability assessment from a supply chain perspective. • Provide a standardised process and a novel PVA framework incorporating a centrality estimate for the first time. • Define different types of vulnerability measures considering the internal risk and external safety impact in the framework. • Investigate five key ports to analyse the vulnerability and prioritise their vulnerable levels for resource rationalisation. [ABSTRACT FROM AUTHOR]

Climate change is the most threating environmental issue and the biggest challenge that humanity has ever faced. While acting as the key nodes of globalisation and international business, seaports are exposed to the vulnerability of climate impacts, mainly because of their locations, including low-lying areas, coastal zones, and deltas. The paper is to develop a Climate Change Risk Indicator (CCRI) framework for climate risk assessment of seaports, enabling research-informed policymaking on such a demanding topic. Due to the increasing number of extreme weather events (EWEs), climate change adaptation is becoming an essential and necessary issue to be addressed by seaport stakeholders. Climate risk analysis aids rational adaptation planning. Many climate assessments have been done for measuring climate vulnerabilities, and various climate adaptation measures have been proposed for reducing climate risks. However, few of them used quantitative approaches for climate risk evaluations in seaports and fewer on the provisions of CCRIs for comparing climate risks of different locations and timeframes to guide rational policy making. Furthermore , climate change is a dynamic issue, requiring big objective data to support the analysis (e.g. monthly climate data on CCRIs) of climate threats and vulnerabilities. In this paper, Evidence Reasoning (ER) is employed to evaluate the climate risks in seaports by tackling the incomplete data. The findings reveal the quantitative measures of climate change risks in different locations and in different months. Furthermore, the risk levels of seaports in the future are assessed for observing the changes and informing policy making. The main contributions of this study include the visualisation of the comprehensive climate risk levels and provision of a new climate risk analysis framework through the comparison of climate change risks with respect to different locations and timeframes. Suitable climate adaptation measures can be chosen to implement, and seaports can cooperate on climate resilience issues (e.g. seaport network service and pre-disaster relief logistics). • Propose an Evidential reasoning (ER) approach to integrate all Climate Change Risk Indicators (CCRI) and establish a CCRI framework for seaports. • Assess twelve seaports in the United Kingdom (UK) as a demonstration. • Observe the monthly and seasonal climate changes. • Forecast the future climate risks for the seaports in the UK. • Comparing the climate risks with respect to location and timeframe for informing policymaking. [ABSTRACT FROM AUTHOR]

Traffic congestion has become one of the most serious contemporary city issues as it leads to unnecessary high energy consumption, air pollution and extra traveling time. During the past decade, many optimization algorithms have been designed to achieve the optimal usage of existing roadway capacity in cities to leverage the problem. However, it is still a challenging task for the vehicles to interact with the complex city environment in a real time manner. In this paper, we propose a deep reinforcement learning (DRL) method to build a real-time intelligent vehicle routing and navigation system by formulating the task as a sequence of decisions. In addition, an integrated framework is provided to facilitate the intelligent vehicle navigation research by embedding smart agents into the SUMO simulator. Nine realistic traffic scenarios are simulated to test the proposed navigation method. The experimental results have demonstrated the efficient convergence of the vehicle navigation agents and their effectiveness to make optimal decisions under the volatile traffic conditions. The results also show that the proposed method provides a better navigation solution comparing to the benchmark routing optimization algorithms. The performance has been further validated by using the Wilcoxon test. It is found that the achieved improvement of our proposed method becomes more significant under the maps with more edges (roads) and more complicated traffics comparing to the state-of-the-art navigation methods. • A novel deep reinforcement learning method for real-time vehicle navigation. • Smart agents are embedded into SUMO simulator in a dynamic transportation system. • Performance is validated by nine realistic road and traffic combined conditions. [ABSTRACT FROM AUTHOR]