In view of the uncertainty and fuzziness of the intentions of other ships, an intelligent ships navigation decision-making method under uncertain conditions is proposed in this paper. Firstly, a Bayesian game model considering International Regulations for Preventing Collisions at Sea (COLREGs) is constructed. By defining the intention space and its probability distribution, the uncertainty of other ship intentions is described, and a dynamic belief update mechanism is introduced to achieve online learning. Secondly, a composite reward function that takes into account safety, economy, and rule compliance is designed, and a quantitative basis for solving Nash equilibrium is provided. Finally, the effectiveness and superiority of the proposed navigation decision-making method and game solving algorithm are verified through simulation experiments. The results indicate that the proposed decision-making method can effectively generate safe, compliant, and efficient navigation strategies, and that the proposed Nash equilibrium solving approach demonstrates good solution performance and robustness. This research can provide a reliable theoretical framework and algorithmic support for the autonomous decision-making of intelligent ships in uncertain scenarios.

Collecting a large number of dangerous omen scenarios from drivers' first-person perspective is of great significance for training and improving end-to-end autonomous driving models. In this study, we aim at capturing driver-perspective scenarios when recognizing dangerous omens. Firstly, through the design and implementation of vehicle and virtual driving experiments, the electroencephalogram, electrocardiogram and eye movement data of the subjects are collected. Statistical tests are conducted to analyze the characteristic differences among drivers across three distinct states. It also reveals that the driver can perceive and distinguish the dangerous omen clearly. Secondly, the evolution law of drivers' perception state is analyzed to accurately judge the time period of drivers' dangerous omen perception. Thirdly, the Hidden Markov Model is used to build the driver perception state transition model, and then the model is calibrated and verified. Finally, the model is utilized to identify drivers' dangerous omen perception states and extract the corresponding perspective objective scenarios, which can provide sufficient samples for training end-to-end autonomous driving models. This study is of great significance to enable the capability of vehicles to recognize dangerous omens, advancing end-to-end and other high-level autonomous driving technologies and further securing vehicle safety.

Car-following behavior is the result of combined effects of various types of factors in real transportation systems. However, there is no car-following model that comprehensively incorporates the combined impacts of micro and macro factors, as well as the differences in car-following behavior among diverse drivers under the same impacts, i.e., driver heterogeneity. This paper presents a panoramic situation expression-based car-following model. First, the micro factors (including the types and positions of the vehicles in the current lane and adjacent lanes) and the macro factor (including the density of traffic flow ahead) that affect car-following behavior are modeled as the panoramic situation, and based on nonlinear mechanics and phase-field coupling theory, the mathematized expression of panoramic situation is established to achieve a unified expression of the combined impacts. Second, a car-following behavior decision-making method is proposed to incorporate driver heterogeneity based on cumulative prospect theory and the “decision-execution” mechanism of car-following behavior. Third, intelligent driving model is employed as the execution framework and integrated with the decision-making method to establish a car-following model. Real and virtual vehicle driving experiments are conducted to collect data and complete calibration. The fitting capability, numerical along with behavioral soundness, and scenario robustness of the proposed model are tested, evaluated, and verified through comprehensive utilization of the collected data, NGSIM dataset, and data of supplemental driving experiments in 15 cases within 10 representative scenarios. The capability of the proposed model to capture heterogeneous drivers’ car-following behavior, the cognitive rationality of its outputs for heterogeneous drivers, and the contribution of each module in the model to performance improvement were also tested.

According to in-depth research on the perception ability of dangerous omens of excellent drivers, references can be provided for the development of brain-like intelligence and its transplantation, as well as applications in the field of autonomous driving, which will improve the active safety and intelligence level of vehicles. Previous studies have shown that there is indeed a dangerous omen before an accident occurs. However, current studies are still unclear about the bio-psychophysiological characteristics exhibited by drivers with high levels of sensory agility when they anticipate potential warning signs, and there is no method for screening such drivers who can perceive dangerous omens proposed by any research. To address the above issues, this paper conducts in-depth research. Firstly, through designing dangerous scenarios and conducting hazard perception tests, we collect physiological, psychological, and physical data, such as drivers' bioelectrical signals (electroencephalogram and electrocardiogram) and eye movements. Secondly, through playing back experimental videos, actively questioning drivers, and analyzing local changes in their electroencephalogram data, the driver's ability to identify a dangerous omen and the moment of perception are determined. Thirdly, based on techniques such as the Kolmogorov-Smirnov test and the Mann-Whitney U test, the differences in bioelectrical and eye movement characteristics between drivers who can perceive a dangerous omen and others can be further revealed. Finally, the driver's bioelectrical and eye movement characteristics are used as latent variables, and their corresponding data are utilized as observation indicators. We construct a structural equation model for screening drivers capable of perceiving a dangerous omen and conduct calibration and validation. This study provides inspirational ideas for empowering vehicles to identify potential hazards, advancing end-to-end and other higher-level autonomous driving technologies, and further enhancing road traffic safety.

With the continuous development of global intelligent shipping technology, in fields such as virtual testing of intelligent ships and crew training and assessment, there is an urgent need for a highly realistic model to reproduce the driver’s bumpy feeling of ship drivers. Due to the limited travel of the six-degree-of-freedom platform, the platform is unable to provide continuous acceleration during the simulation of the driver’s body sensation in the three degrees of freedom of the ship, namely, sway, surge, and yaw. To overcome the above problems, a six-degree-of-freedom motion model of ships is constructed under low sea conditions based on the MMG-separated ship motion model and the FFT wave simulation method. Secondly, the otolith model and the semicircular canal model are introduced to establish a human body perception deception mechanism. The gravity is transferred by using the deflection angles of roll and pitch to extend the acceleration sensation in the three degrees of freedom of sway, surge, and yaw. Finally, through the real ship rotation and Z-shaped test experiments, the simulation trajectory, real ship attitude, and platform motion data are compared to verify the effectiveness of the established method. To simplify the research, under the low sea conditions where the three degrees of freedom of heave, roll, and pitch are ignored, the virtual ship simulation trajectory based on the above method is basically consistent with the real ship, and the correlation between the platform and the real ship body-sensing data is at least 81.2%. Through scoring the simulation driving body-sensing reproduction experience, it is proven that the above method can achieve a better body-sensing reproduction effect on the six-degree-of-freedom platform.

Human factors are the most important factor in road traffic crashes. Human-caused traffic crashes can be reduced through the active safety system of vehicles. Road hypnosis is an unconscious driving state caused by the combination of external environmental factors and the driver’s psychological state. When drivers fall into a state of road hypnosis, they cannot clearly perceive the surrounding environment and make various reactions in time to complete the driving task, and driving safety is greatly affected. Therefore, road hypnosis identification is of great significance for the active safety of vehicles. A road hypnosis identification model based on XGBoost—Hidden Markov is proposed in this study. Driver data and vehicle data related to road hypnosis are collected through the design and conduct of vehicle driving experiments. Driver data, including eye movement data and EEG data, are collected with eye movement sensors and EEG sensors. A mobile phone with AutoNavi navigation is used as an on-board sensor to collect vehicle speed, acceleration, and other information. Power spectrum density analysis, the sliding window method, and the point-by-point calculation method are used to extract the dynamic characteristics of road hypnosis, respectively. Through normalization and standardization, the key features of the three types of data are integrated into unified feature vectors. Based on XGBoost and the Hidden Markov algorithm, a road hypnotic identification model is constructed. The model is verified and evaluated through visual analysis. The results show that the road hypnosis state can be effectively identified by the model. The extraction of road hypnosis-related features is realized in non-fixed driving routes in this study. A new research idea for road hypnosis and a technical scheme reference for the development of intelligent driving assistance systems are provided, and the life identification ability of the vehicle intelligent cockpit is also improved. It is of great significance for the active safety of vehicles.

Accurate and real-time recognition of right-of-way information transmitted by traffic lights is key to ensuring the safety of traffic participants. Existing deep learning-based traffic light detection and recognition (TLDR) models achieved high accuracy. However, these models require considerable computing power, which makes them difficult to be deployed on mobile platforms such as intelligent vehicles, urban low-speed unmanned work platforms, and visually impaired street-crossing assistance devices. In this paper, a mobile platform-friendly TLDR model HCEDSM (high computational cost-effectiveness and detection speed model) is proposed to achieve high accuracy, low latency, and strong deployment feasibility. First, a lightweight backbone network combined with EfficientViT and efficient multi-scale attention is introduced to reduce the quantity of computation and focus on small target features. Second, a cross-scale neck network is constructed to improve the feature fusion ability with lower computational cost. The open-source S2TLD dataset is used for training and testing, and the model is deployed on the NVIDIA Jetson Nano B01, which is a representative platform for low-computing-power devices. The results show that HCEDSM achieves a precision of 94.7

Automatic berthing is one of the key functions for autonomous navigation of unmanned ships, and it is an important technology that assists and ensures ships complete their voyage tasks. To enhance the robustness, scenario universality, and disturbance resistance of automatic berthing technology, an automatic berthing method based on weight optimal loop shaping is proposed in this paper. Firstly, to enhance the robust stability margins of the berthing controller, the concept of weight optimization is introduced to transform the frequency-domain dependent weight optimization into an optimization problem with a finite number of frequency-domain independent constraints. Secondly, to improve the continuity and scenario universality of the algorithm, a transformation model between berth and earth coordinates is constructed using Bézier curves, and a forward Euler signal tracking method is introduced to provide a differentiable reference trajectory for the control system. Finally, the proposed method is validated through the construction of various berthing scenarios. The validation results indicate that the proposed method can achieve automatic berthing in different scenarios with better stability and disturbance resistance, and a theoretical reference is provided for the development of autonomous berthing technology for unmanned ships.

The application of intelligent and connected technologies, such as vehicle-to-everything (V2X), profoundly influences car-following behavior and traffic flow characteristics. While empirical studies have demonstrated that the car-following behavior is affected by the vehicles in the adjacent lanes, there is no car-following model that comprehensively incorporates the leading and following neighboring vehicles, including those in the adjacent lanes. Under the conditions of intelligent and connected technologies penetration, the information regarding the aforementioned vehicles can be accessed and applied in the car-following process. However, the absence of the corresponding car-following model limits the understanding of traffic flow characteristics under this condition, particularly concerning critical stability characteristics. To address this research gap, a new car-following model is proposed, which integrates the neighboring leading vehicles in the current and adjacent lances, marked as the surrounding leading vehicle (SLV), and the rear vehicle in the current lane. The linear stability analysis and nonlinear analysis of the proposed model, as well as the numerical simulation of the propagation process of disturbance in the vehicle fleet, are conducted. Based on this, the stability and evolution characteristics of the traffic flow are explored. The results of theoretical and simulation analysis consistently suggest that the integration of the motion state information of the SLV and the rear vehicle can effectively stabilize the traffic flow, which means that traffic congestion can be alleviated and transportation efficiency will be improved. This research can provide references for the research fields including traffic flow theory and is of significant importance for alleviating and mitigating traffic congestion under the condition of intelligent and connected vehicle (CAV) penetration.

Driver factors are the main cause of road traffic accidents. For the research of automotive active safety, an identification method for road hypnosis of a driver of a car with dynamic human–vehicle heterogeneous data fusion calculation is proposed. Road hypnosis is an unconscious driving state formed by the combination of external environmental factors and the psychological state of the car driver. When drivers fall into a state of road hypnosis, they cannot clearly perceive the surrounding environment and make various reactions in time to complete the driving task. The safety of humans and cars is greatly affected. Therefore, the study of the identification of drivers’ road hypnosis is of great significance. Vehicle and virtual driving experiments are designed and carried out to collect human and vehicle data. Eye movement data and EEG data of human data are collected with eye movement sensors and EEG sensors. Vehicle speed and acceleration data are collected by a mobile phone with AutoNavi navigation, which serves as an onboard sensor. In order to screen the characteristics of human and vehicles related to the road hypnosis state, the characteristic parameters of the road hypnosis in the preprocessed data are selected by the method of independent sample T-test, the hidden Markov model (HMM) is constructed, and the identification of the road hypnosis of the Ridge Regression model is combined. In order to evaluate the identification performance of the model, six evaluation indicators are used and compared with multiple regression models. The results show that the hidden Markov-Ridge Regression model is the most superior in the identification accuracy and effect of the road hypnosis state. A new technical scheme reference for the development of intelligent driving assistance systems is provided by the proposed comprehensive road hypnosis state identification model based on human–vehicle data can provide, which can effectively improve the life recognition ability of automobile intelligent cockpits, enhance the active safety performance of automobiles, and further improve traffic safety.

The development of the Connected and Autonomous Vehicle (CAV) and Hybrid Electric Vehicle (HEV) provides a new effective means for the optimization of eco-driving strategies. However, the existing research has not effectively considered the cooperative speed optimization and power allocation problem of the Connected and Autonomous Plug-in Hybrid Electric Vehicle (CAPHEV) platoon. To this end, a hierarchical eco-driving strategy is proposed, which aims to enhance driving efficiency and fuel economy while ensuring the safety and comfort of the platoon. Firstly, an improved car-following model is proposed, which considers the motion states of multiple preceding vehicles. On this basis, a platoon cooperative car-following decision-making method based on model predictive control is designed. Secondly, a distributed energy management strategy is constructed, and a bionic optimization algorithm based on the behavior of nutcrackers is introduced to solve nonlinear problems, so as to solve the energy distribution and management problems of powertrain systems. Finally, the tests are conducted under the driving cycle of the Urban Dynamometer Driving Schedule (UDDS) and the Highway Fuel Economy Test (HWFET). The results show that the proposed strategy can ensure the driving safety of the CAPHEV platoon in different scenes, and has excellent tracking accuracy and driving comfort. Compared with the rule-based strategy, the equivalent energy consumption of UDDS and HWFET is reduced by 20.7% and 5.5% in the battery’s healthy charging range, respectively.

With the rapid development of intelligent mobile platforms, real-time and accurate Traffic Light Detection and Recognition (TLDR) is critical for ensuring traffic safety. However, existing TLDR methods fail to balance detection accuracy, speed, and deployment feasibility. To address this, we propose a high-precision lightweight TLDR model. First, an enhanced backbone network based on the EfficientViT architecture is proposed, incorporating an efficient multi-scale attention module to extract rich semantic features while reducing computational load. Second, a lightweight cross-scale feature fusion network is constructed to enhance information interaction between deep and shallow features. Finally, the model is trained and validated on the open-source S2TLD dataset. Experimental results demonstrate that the proposed model achieves a detection speed of 204 FPS, precision of 95.0%, and 2.1 GFLOPs. Compared to YOLOv5n, the proposed model improves detection speed by 35.1%, precision by 4.7%, and GFLOPs by 48.8%, respectively. This work provides technical support for constructing lightweight TLDR models and offers theoretical reference for deploying TLDR models on intelligent mobile platforms.

Accurate analysis of navigation complexity for ships in the busy port areas is crucial for ensuring safety and efficiency. However, there is a lack of an effective method to analyze the navigation situation in the port areas from the perspective of the coupling of multiple influencing factors. Therefore, a multi-factor coupled navigation situation complexity analysis method for unmanned ships is proposed in this paper. Firstly, the factors affecting ship navigation in port areas are considered comprehensively, and a coupled evaluation system is established. Secondly, the coupling coordination degree model is developed to quantify the interaction intensity between the influencing factors. Thirdly, the key interest perception region is abstracted as nodes, the coupling effect granularity is mapped to edge weights, and a complex network model of situation interaction is established. Finally, the method is validated using historical data, and the results show that the proposed model overcomes the limitations of traditional single-factor analysis, effectively identifies navigation influence areas with high coupling effects, determines the priorities of navigation areas of concern, and reveals their significant impact on ship safety.

A driver in road hypnosis has two different types of characteristics. One is the external characteristics, which are distinct and can be directly observed. The other is internal characteristics, which are indistinctive and cannot be directly observed. The eye movement characteristic, as a distinct external characteristic, is one of the typical characteristics of road hypnosis identification. The electroencephalogram (EEG) characteristic, as an internal feature, is a golden parameter of drivers’ life identification. This paper proposes an identification method for road hypnosis based on the fusion of human life parameters. Eye movement data and EEG data are collected through vehicle driving experiments and virtual driving experiments. The collected data are preprocessed with principal component analysis (PCA) and independent component analysis (ICA), respectively. Eye movement data can be trained with a self-attention model (SAM), and the EEG data can be trained with the deep belief network (DBN). The road hypnosis identification model can be constructed by combining the two trained models with the stacking method. Repeated Random Subsampling Cross-Validation (RRSCV) is used to validate models. The results show that road hypnosis can be effectively recognized using the constructed model. This study is of great significance to reveal the essential characteristics and mechanisms of road hypnosis. The effectiveness and accuracy of road hypnosis identification can also be improved through this study.

Global route planning has garnered global scholarly attention as a crucial technology for ensuring the safe navigation of intelligent ships. The comprehensive influence of time-varying factors such as water depth, prohibited areas, navigational tracks, and traffic separation scheme (TSS) on ship navigation in coastal global route planning has not been fully considered in existing research, and the study of route planning method from the perspective of practical application is still needed. In this paper, a global route planning method based on human-like thinking for coastal sailing scenarios is proposed. Based on the historical route’s information, and taking into full consideration those time-varying factors, an abnormal waypoint detection and correction method is proposed to make the planned route conform to relevant regulations of coastal navigation and the common practices of seafarers as much as possible, and better meet the coastal navigation needs of unmanned ships. Taking the global route planning of “ZHIFEI”, China’s first autonomous navigation container ship, as an example, the validity and reliability of the proposed method are verified. Experimental findings demonstrate the efficacy of the proposed method in global route planning for coastal navigation ships. The method offers a solid theoretical foundation and technical guidance for global route planning research of unmanned ship.

Risky driving behaviors, such as driving fatigue and distraction have recently received more attention. There is also much research about driving styles, driving emotions, older drivers, drugged driving, DUI (driving under the influence), and DWI (driving while intoxicated). Road hypnosis is a special behavior significantly impacting traffic safety. However, there is little research on this phenomenon. Road hypnosis, as an unconscious state, is can frequently occur while driving, particularly in highly predictable, monotonous, and familiar environments. In this paper, vehicle and virtual driving experiments are designed to collect the biological characteristics including eye movement and bioelectric parameters. Typical scenes in tunnels and highways are used as experimental scenes. LSTM (Long Short-Term Memory) and KNN (K-Nearest Neighbor) are employed as the base learners, while SVM (Support Vector Machine) serves as the meta-learner. A road hypnosis identification model is proposed based on ensemble learning, which integrates bioelectric and eye movement characteristics. The proposed model has good identification performance, as seen from the experimental results. In this study, alternative methods and technical support are provided for real-time and accurate identification of road hypnosis.

Precise comprehension about the impacts of drivers' rational and perceptual characteristics on their behavioral decisions is crucial for the accurate prediction of driving behavior. In the previous research on driving behavior, drivers were regarded as homogeneous and absolutely rational individuals. To overcome this limitation, the coupling effects of bounded rational cognition and diverse emotions are considered, and a driving behavior model is proposed based on Dynamics Psychology. There are two parts in this research. In Study 1, the information entropy theory is applied to describe the vehicle cluster situation, and a method is established to quantify the cognitive uncertainty of the vehicle cluster situation for drivers in diverse emotions. In Study 2, with consideration of bounded rational and emotional cognition, the impacts of the vehicle cluster situation and drivers' features, which are their demands for the driving goals including safety, efficiency and comfort, emotional states, and cognitive characteristics, on driving behavior are uniformly expressed as the behavioral driving force, and a prediction model for driving behavior is proposed based on Dynamics Psychology. The results of validation based on the virtual driving data show the prediction accuracy of the proposed model for various driving behaviors of drivers in diverse emotions is over 80%. The results of verification based on NGSIM data suggest that the prediction accuracy of the proposed model for the natural driving behaviors is 82.07%. The research results can contribute to the study on the intrinsic mechanism of driving behavior and provide theoretical support for the development of traffic simulation, personalized active safety systems, human-machine interaction, and brain-inspired autonomous driving.

With the rapid development of the shipping industry, the number of ships is continuously increasing, and maritime accidents happen frequently. In recent years, computer vision and drone flight control technology have continuously developed, making drones widely used in related fields such as maritime target detection. Compared to the cameras fixed on ships, a greater flexibility and a wider field of view is provided by cameras equipped on drones. However, there are still some challenges in high-altitude detection with drones. Firstly, from a top-down view, the shapes of ships are very different from ordinary views. Secondly, it is difficult to achieve faster detection speeds because of limited computing resources. To solve these problems, we propose YOLOv7-DyGSConv, a deep learning-based model for detecting ships in real-time videos captured by drones. The model is built on YOLOv7 with an attention mechanism, which enhances the ability to capture targets. Furthermore, the Conv in the Neck of the YOLOv7 model is replaced with the GSConv, which reduces the complexity of the model and improves the detection speed and detection accuracy. In addition, to compensate for the scarcity of ship datasets in top-down views, a ship detection dataset containing 2842 images taken by drones or with a top-down view is constructed in the research. We conducted experiments on our dataset, and the results showed that the proposed model reduced the parameters by 16.2%, the detection accuracy increased by 3.4%, and the detection speed increased by 13.3% compared with YOLOv7.