Search

The rapid development of high techniques in recent years has made the operation of intelligent ships a possible option in foreseeable future. This will inevitably change the navigation environment of ships. Both conventional and intelligent ships will sail in the same channels and water areas. This research proposed a framework to meet the needs of future waterway transportation safety in such a mixed environment. The proposed framework can model and assess the risk of inland waterway transportation in a mixed traffic environment of remote-control and conventional ships. It defined four stages of the mixed traffic scenario in inland rivers, including perception, cognition, decision, and control stage. On this basis, we explored the risk factors under mixed traffic scenario, and construct the system dynamics model of transportation risk accordingly. A case study of risk modelling and assessment of inland waterway transportation systems in continuous bridge areas under the mixed environment was conducted to validate the proposed method. The results showed that the proposed framework can identify the main stages and key factors affecting inland waterway transportation system safety under the mixed traffic environment. This research provides a theoretical basis for the safety supervision of remotely controlled ship operations in future. [ABSTRACT FROM AUTHOR]

Compared to maritime vessel traffic accidents, there is a scarcity of available, and only incomplete, accident data for inland waterway accidents. Additionally, the characteristics of different waterway segments vary significantly, and the factors affecting navigation safety risks and their mechanisms may also differ. Meanwhile, in recent years, extreme weather events have been frequent in inland waterways, and there has been a clear trend towards larger vessels, bringing about new safety hazards and management challenges. Currently, research on inland waterway navigation safety risks mainly focuses on risk assessment, with scarce quantitative studies on risk mitigation measures. This paper proposes a new method for improving inland waterway traffic safety, based on a cost-effectiveness trade-off approach to mitigate the risk of vessel traffic accidents. The method links the effectiveness and cost of measures and constructs a comprehensive cost-benefit evaluation model using fuzzy Bayesian and quantification conversion techniques, considering the reduction effects of risk mitigation measures under uncertain conditions and the various costs they may incur. Taking the upper, middle, and lower reaches of the Yangtze River as examples, this research evaluates key risk mitigation measures for different waterway segments and provides the most cost-effective strategies. Findings reveal that, even if different waterways share the same key risk sources, the most cost-effective measures vary due to environmental differences. Moreover, there is no inherent correlation between the best-performing measures in terms of benefits and the lowest-cost measures, nor are they necessarily recommended. The proposed method and case studies provide theoretical support for scientifically formulating risk mitigation measures in complex environments and offer guidance for inland waterway management departments to determine future key work directions. [ABSTRACT FROM AUTHOR]

In recent years, the construction of lane-level road maps has received extensive attention from industry and academia. It has been widely studied because this kind of map provides the foundation for much research, such as high-precision navigation, driving behavior analysis, and traffic analysis. Trajectory-based crowd-mapping is an emerging approach to lane-level map construction. However, the major problem is that existing methods neglect modeling the trajectory distribution in the longitudinal direction of the road, which significantly impacts precision. Thus, this article proposes a two-stage method based on vehicle lane-changing behavior to model the road's lateral and longitudinal trajectory distributions simultaneously. In the first stage, lane-changing behaviors are extracted from vehicle trajectories. In the second stage, the lane extraction model is established using the weighted constrained Gaussian mixture model and hidden Markov model to estimate lane parameters (e.g., lane counts and lane centerline) on each road cross section. Then accurate and continuous lane centerlines can be constructed accordingly. The proposed method is verified using vehicle trajectory data collected from the crowdsourced platform named Mapillary. The results show that the proposed method can construct lane-level road information satisfactorily., Author(s): Liang Fan [1,2]; Jinfen Zhang [1,2]; Chengpeng Wan [1,2]; Zhongliang Fu [3]; Shiwei Shao (corresponding author) [4] 1. Introduction Lane-level road maps are the core of automatic driverless systems [...]