The paper addresses the Capacitated Vehicle Routing Problem (CVRP) in the context of fuel delivery to gas stations. The CVRP aims to minimize total travel distance for a fleet with limited capacity. Fuel delivery, however, introduces unique complexities within the CVRP framework. The study proposes integrating the Simulated Annealing (SA) algorithm with a customized CVRP model specifically designed for gas station networks. This model incorporates real-world constraints like vehicle capacity, fuel demands at each station, and road network distances. The paper outlines the design of the SA-based CVRP model for fuel delivery. It details the objective function (minimizing distance) and the SA’s exploration mechanism for generating candidate solutions. To assess its effectiveness, the proposed approach undergoes computational tests in Poland’s gas station network serviced by the Samat transportation company. The performance of the developed SA-based CVRP model is compared with the conventional Mixed Integer Programming model for CVRP powered by Gurobi. The results aim to demonstrate the efficacy of the proposed SA-based heuristic in finding efficient routes for fuel deliveries.
Autonomous self-driving vehicles are becoming more essential in research due to its features and implementation. Vehicle to Infrastructure (V2I) is a critical component in autonomous self-driving cars. With the proper implementation of V2I communication many road accidents can be prevented. The proposed work implements new cooperative algorithm that embeds road classification, lane marking detection and classification. The proposed algorithm uses Road Side Unit (RSU) and Dedicated Short Range Communication (DSRC) for V2I communication. This algorithm enhances the safety in lane changing with the incorporation of lane marking detection. The results clearly demonstrate the implementation of V2I communication with an acceptable efficiency of 99% that enhances the road safety.
This study investigates barriers to the adoption of Artificial Intelligence (AI) in the transportation and logistics sector within the context of Industry 5.0, emphasizing human centricity, sustainability, and system resilience. A qualitative expert-based research approach was applied using asynchronous email interviews with 54 experts representing transport operators, logistics service providers, SMEs, public sector institutions, technology providers, and academia from multiple countries. The analysis identified eight interrelated categories of barriers affecting AI implementation in transport systems, including data quality and integration issues, infrastructure limitations, financial constraints, lack of human competencies, managerial challenges, psychological resistance, ethical and safety concerns, and regulatory uncertainty. SME specific challenges were further examined using Latent Dirichlet Allocation, confirming the central role of data, competences and resource constraints. The findings indicate only partial alignment of current AI initiatives with Industry 5.0 values and provide implications for intelligent transport systems, transport safety, and policy development.
Mass decontamination in transport hubs is a time-critical emergency-response task following accidents involving hazardous goods, where operational effectiveness depends on rapid coordination, reliable control, and traceable execution. This paper proposes a telematics-enabled digital coordination framework for mobile emergency decontamination in transport-hub environments. The framework is formalised as a four-layer cyber-physical architecture integrating operator interaction, application-layer control, equipment-level execution, and persistent audit-oriented data management. Its operational logic is supported by a deterministic lifecycle model, algebraic preset validation, and role-based access control. The proposed approach was evaluated through scenario-based simulation and a transport-hub case study. The results confirmed functional correctness and operational feasibility of the framework, while the case study indicated a 42% reduction in mean response time and a 44% reduction in sustainability-related operational loss compared with conventional manual coordination. The study shows that mobile decontamination can be interpreted as a digitally coordinated safety service within transport hubs and that telematics-enabled orchestration can improve response readiness and operational resilience in disruption-sensitive environments.
This article presents the development of a real-time system simulator and discusses the results obtained through its application. The simulator is designed in accordance with the fundamental principles of real-time systems, incorporating traffic sources that generate both hard and soft data streams. Hard data streams demand stringent transmission conditions, such as minimal latency beyond what is required for essential operations to ensure accurate data transmission. Conversely, soft data streams allow for variations in transmission parameters. The simulator was developed using the event scheduling approach and implemented in the C++ programming language.
