Reduce Collision Risk Research Articles

Enhancing Tram Safety in Mixed-Traffic Systems: A Case Study of Melbournes Tram Collision Factors and Improvement Strategies

Abstract: Trams, a vital component of public transportation, operate within diverse environments ranging from fully segregated tracks to mixed-traffic systems. This study investigated tram collisions in Melbournea city renowned for its extensive and historic tram networkand explored both systemic and behavioral factors contributing to these incidents. The analysis identified key factors such as the arrangement of tram platforms, intersection design, right-of-way (ROW) regulations, tram driver behavior, and the actions of other road users. The study revealed that inadequate tram platform arrangements and suboptimal intersection designs are major contributors to tram collisions. Recommendations for improvement include implementing elevated, standalone tram platforms with protective barriers and accessible ramps, expanding the use of Hook Turn intersections, and integrating intelligent transportation systems to enhance traffic management. Additionally, addressing behavioral factors is crucial. Enhanced training for tram drivers and educational campaigns for pedestrians and other road users are proposed to improve situational awareness and adherence to safety norms. By addressing both objective systemic issues and subjective behavioral factors, this study aimed to enhance the safety of tram operations in mixed-traffic environments, ultimately reducing collision risks and improving public confidence in tram systems.

Safedrive dreamer: Navigating safety–critical scenarios in autonomous driving with world models

Achieving stable and reliable autonomous driving in complex traffic environments while ensuring safety under unpredictable conditions is a critical challenge in autonomous driving technology. To address this issue, this study proposes the Safedrive Dreamer navigation framework, which aims to reduce the reliance on trial-and-error learning in real-world scenarios, thereby mitigating the risks associated with dynamic driving conditions and enhancing vehicle foresight. This framework integrates the predictive capabilities of world models with the constrained Markov decision process (CMDP) and safety reinforcement learning to accurately anticipate future environmental changes. This ensures the reliability of autonomous driving routes, thereby improving both safety and efficiency. Furthermore, to reduce trial-and-error costs in real-world applications, this study employs PAC-Bayesian methods to derive generalization error bounds between simulations and reality, enabling a more effective transfer of knowledge and experience from simulations to real-world scenarios. Validation experiments in simulated and real environments showed that Safedrive Dreamer significantly outperformed existing autonomous driving solutions by 3.8% in key safety metrics, excelling in collision avoidance and risk reduction. This study provides new insights into the integration of world models into decision-making processes to enhance decision-making capabilities in safety–critical applications, thereby contributing significantly to the improvement of autonomous driving safety and reliability.

A Collision Risk Assessment Method for Aircraft on the Apron Based on Petri Nets

The airport apron is a high-risk area for aircraft collisions due to its heavy operational load and high aircraft density. Currently, existing quantitative models for apron collision risk provide limited consideration and classification of risk areas. In response, this paper proposes a Petri net-based method for assessing aircraft collision risk. The method predicts the probability of aircraft reaching different areas at different times based on operational data, enabling the calculation of collision risks within the Petri net framework. This approach highlights areas with potential collision risks and provides a classification evaluation. Subsequently, aircraft path re-planning is carried out to reduce collision risks. The model simplifies the complex operations of the apron system, making the calculation process clearer. The results show that, during the mid-phase of aircraft taxiing, there is a significant deviation between the actual and ideal positions of aircraft. Areas with high taxiway occupancy are more prone to collision risks. On peak days, due to relatively high flight volumes, the frequency of collision risks is 14% higher than on regular days, with an average risk increase of 23.3%, and the risks are more concentrated. Therefore, reducing collision risks through path planning becomes more challenging. It is recommended to focus attention on areas with high taxiway occupancy during peak periods and carefully plan routes to ensure apron safety.

A Novel Resource-Aware Distributed Cooperative Decision-Making Mechanism for Connected Automated Vehicles

<div>This article proposes a new model for a cooperative and distributed decision-making mechanism for an ad hoc network of automated vehicles (AVs). The goal of the model is to ensure safety and reduce energy consumption. The use of centralized computation resource is not suitable for scalable cooperative applications, so the proposed solution takes advantage of the onboard computing resources of the vehicle in an intelligent transportation system (ITS). This leads to the introduction of a distributed decision-making mechanism for connected AVs. The proposed mechanism utilizes a novel implementation of the resource-aware and distributed–vector evaluated genetic algorithm (RAD-VEGA) in the vehicular ad hoc network of connected AVs as a solver to collaborative decision-making problems. In the first step, a collaborative decision-making problem is formulated for connected AVs as a multi-objective optimization problem (MOOP), with a focus on energy consumption and collision risk reduction as example objectives. RAD-VEGA then cooperatively solves this MOOP, taking into account the availability of AV’s onboard resources and the application layer characteristics of today’s ITS communication tools. The performance of the proposed mechanism is evaluated by solving the ZDT1 test problem and studying pareto-frontier solutions to the true front over time. The scalability of the proposed solution is estimated to be 305 CAVs, considering a communication bandwidth of 6 MB/s. Additionally, cooperative AV planning scenario examples are simulated, and the effectiveness of the proposed mechanism is demonstrated by comparing final and initial solutions after solving the MOOP using RAD-VEGA.</div>

Risk Assessment of Bird Collisions with a Wind Turbine Based on Flight Parameters

The study addresses the challenge of bird collisions with wind turbines by developing an autonomous risk assessment method. The research uses data from the stereoscopic Bird Protection System (BPS) to anticipate potential collision threats by analysing flight parameters and distance from turbines. The danger factor depends on the flight characteristics of the identified bird species and the parameters of the wind turbine control system. The paper proposes an online quantitative risk assessment model that operates in real time, with the aim of minimising unnecessary turbine shutdowns while improving bird conservation. The model is validated through field data from bird flights. The findings suggest that adaptive management of turbine operations based on real-time bird flight data can significantly reduce collision risks without compromising energy production efficiency. The research underscores the balance between ecological considerations and the economic viability of wind energy, proposing an adaptive strategy that reduces unnecessary turbine stoppages while ensuring the safety of avian species.

Leveraging Copernicus for Ice Block Detection: A Step Towards Safer Arctic Navigation

Background The Arctic is becoming more accessible due to ice melting, posing challenges for navigation due to floating ice blocks. Detecting these ice blocks is crucial for ensuring the safety of vessels navigating these waters. Methods This study introduces a novel method for detecting ice blocks in the Arctic using Artificial Intelligence (AI) and Synthetic Aperture Radar (SAR) satellite images from the Sentinel-1 mission of the Copernicus program. Our approach combines state-of-the-art image segmentation and deep learning techniques. We utilize a Convolutional Neural Network (CNN) classifier to accurately locate ice blocks within the images and retrieve their geographic coordinates. The method's performance is validated using precision, recall, and F1-score metrics. Results Our CNN classifier demonstrates robust performance in detecting ice blocks, validated through precision, recall, and F1-score metrics. The practical application of our technology was showcased in the AI-ARC project’s Arctic demo, receiving positive feedback from coast guards across various European countries. The system provides near-real-time alerts about detected ice blocks, allowing for timely route adjustments and reducing collision risks. Conclusions The developed system significantly contributes to Arctic navigation safety by providing accurate and timely detection of ice blocks. This work underscores the transformative potential of AI in environmental monitoring and maritime safety. Future refinements will be based on user feedback and advancements in AI technology, enhancing the system's effectiveness and reliability.

A human-like collision avoidance method for USVs based on deep reinforcement learning and velocity obstacle

Collision avoidance is critical in unmanned surface vehicles (USVs) and is especially challenging in scenarios involving ships of different intelligence levels. To address this problem, inspired by risk analysis and collision avoidance habits of seafarers, this paper proposes a human-like collision avoidance method based on deep reinforcement learning (DRL) and velocity obstacle (VO). It first introduces a navigation impact factor (NIF) calculation module based on fuzzy theory to simulate human beings’ attention mechanisms when facing multiple ships. To be compatible with human beings’ regulations, the convention on the International Regulations for Preventing Collisions at Sea (COLREGs) is first to be integrated into the calculation of the NIF calculation module, and the VO algorithm is incorporated into the reward function, which can reduce collision risks in paths and improve safety requirements. In addition, a series of reward functions are carefully designed to balance safety, smoothness, and driving operation. To validate the performance, experiments are conducted on our virtual simulation platform. The results show that our algorithm can accurately assess the impact of target ships (TS) on own ship (OS) in complex environments and can obey the COLREGs. Collision avoidance can be achieved effectively and the path is smoother.

Empirical and simulation data reveal a lack of avoidance of wind turbines by Gyps fulvus (Griffon Vulture)

Abstract The increase of wind turbine installations to limit climate change may affect bird populations because of collisions with rotor blades. Birds may respond to wind turbine presence along a gradient of behavioral changes: avoiding the wind farm (macro-scale) or the wind turbines either by anticipating wind turbine locations (meso-scale) or engaging in last-minute flee attempts (micro-scale). We investigated flight responses of 25 adult Gyps fulvus (Griffon Vulture) equipped with GPS tags over 3 years in an area that included 10 wind farms in Causses, France. At the macro-scale, foraging range and habitat use revealed that G. fulvus did not avoid wind farms. To investigate avoidance at meso- and micro-scales, we focused on the 4 most visited wind farms. We compared vulture flights to null movement models, which allowed us to keep the correlation between flights and topography while creating movement independent of wind turbine locations. At most sites, G. fulvus did not show avoidance behavior. Overall, our results suggest wind farm-specific responses by soaring birds as a function of landscape topography. Thus, to reduce collision risks, stakeholders should first avoid constructing wind farms close to vulture nesting colonies. When siting, developers should investigate G. fulvus use of local topography to avoid areas in which birds are likely to travel. Finally, managers must prioritize the detection of species not able to avoid turbines when designing preventive measures, such as switching off on-demand technologies.

Multimodal audio-visual robot fusing 3D CNN and CRNN for player behavior recognition and prediction in basketball matches.

Intelligent robots play a crucial role in enhancing efficiency, reducing costs, and improving safety in the logistics industry. However, traditional path planning methods often struggle to adapt to dynamic environments, leading to issues such as collisions and conflicts. This study aims to address the challenges of path planning and control for logistics robots in complex environments. The proposed method integrates information from different perception modalities to achieve more accurate path planning and obstacle avoidance control, thereby enhancing the autonomy and reliability of logistics robots. Firstly, a 3D convolutional neural network (CNN) is employed to learn the feature representation of objects in the environment for object recognition. Next, long short-term memory (LSTM) is used to model spatio-temporal features and predict the behavior and trajectory of dynamic obstacles. This enables the robot to accurately predict the future position of obstacles in complex environments, reducing collision risks. Finally, the Dijkstra algorithm is applied for path planning and control decisions to ensure the robot selects the optimal path in various scenarios. Experimental results demonstrate the effectiveness of the proposed method in terms of path planning accuracy and obstacle avoidance performance. The method outperforms traditional approaches, showing significant improvements in both aspects. The intelligent path planning and control scheme presented in this paper enhances the practicality of logistics robots in complex environments, thereby promoting efficiency and safety in the logistics industry.

Enhancing Pedestrian Tracking in Autonomous Vehicles by Using Advanced Deep Learning Techniques

Effective collision risk reduction in autonomous vehicles relies on robust and straightforward pedestrian tracking. Challenges posed by occlusion and switching scenarios significantly impede the reliability of pedestrian tracking. In the current study, we strive to enhance the reliability and also the efficacy of pedestrian tracking in complex scenarios. Particularly, we introduce a new pedestrian tracking algorithm that leverages both the YOLOv8 (You Only Look Once) object detector technique and the StrongSORT algorithm, which is an advanced deep learning multi-object tracking (MOT) method. Our findings demonstrate that StrongSORT, an enhanced version of the DeepSORT MOT algorithm, substantially improves tracking accuracy through meticulous hyperparameter tuning. Overall, the experimental results reveal that the proposed algorithm is an effective and efficient method for pedestrian tracking, particularly in complex scenarios encountered in the MOT16 and MOT17 datasets. The combined use of Yolov8 and StrongSORT contributes to enhanced tracking results, emphasizing the synergistic relationship between detection and tracking modules.

Shared eHMI: Bridging Human–Machine Understanding in Autonomous Wheelchair Navigation

As automated driving system (ADS) technology is adopted in wheelchairs, clarity on the vehicle’s imminent path becomes essential for both users and pedestrians. For users, understanding the imminent path helps mitigate anxiety and facilitates real-time adjustments. For pedestrians, this insight aids in predicting their next move when near the wheelchair. This study introduces an on-ground projection-based shared eHMI approach for autonomous wheelchairs. By visualizing imminent motion intentions on the ground by integrating real and virtual elements, the approach quickly clarifies wheelchair behaviors for all parties, promoting proactive measures to reduce collision risks and ensure smooth wheelchair driving. To explore the practical application of the shared eHMI, a user interface was designed and incorporated into an autonomous wheelchair simulation platform. An observation-based pilot study was conducted with both experienced wheelchair users and pedestrians using structured questionnaires to assess the usability, user experience, and social acceptance of this interaction. The results indicate that the proposed shared eHMI offers clearer motion intentions display and appeal, emphasizing its potential contribution to the field. Future work should focus on improving visibility, practicality, safety, and trust in autonomous wheelchair interactions.

Tying up loose ends together: Cetaceans, maritime traffic and spatial management tools in the Strait of Gibraltar

Abstract The transboundary area of the Strait of Gibraltar is home to seven protected cetacean species that are threatened by high intensity of maritime traffic. More comprehensive knowledge of cetaceans and maritime traffic is required, together with analyses of legislations, strategies and policies. This study quantitatively investigates cetacean distribution and maritime traffic intensity and, for the species of community interest bottlenose dolphin, habitat suitability. Results are qualitatively discussed considering the overlap of cetacean hot spots with different maritime activities and the consistency of spatial conservation management measures in force. The Fixed Line Transect Mediterranean Monitoring Network protocols were followed for 59 visual surveys using ferries as observation platforms for monitoring cetaceans and maritime traffic. Surveys were carried out along the transects between Algeciras and Ceuta and between Algeciras and Tanger‐Med, in 2018 and 2019. 264 cetacean sightings, including seven different species and four near‐miss collision events (involving pilot, sperm and fin whales), were reported. Monitoring cetaceans from ferries in the Strait provided insights into cetacean distribution and maritime traffic, enabling the identification of cetacean hot spots, suitable habitats and maritime traffic high‐risk zones. A transboundary management effort is required, together with an adaptive approach for protecting highly mobile species such as cetaceans. Proposals include a long‐term cetacean monitoring program carried out by dedicated observers on board ferries as a cost‐effective methodology and mandatory training for crew members, to increase cetacean knowledge and reduce collision risk. The designation of an international temporal or, in some zones, permanent speed reduction area (i.e., Cetacean Critical Navigation Zone, with a maximum speed of 13 knots) and of a micro‐sanctuary with a seasonal no‐take zone in the Bay between Algeciras and Gibraltar, together with international surveillance, are recommended measures for the enhancement of conservation efforts in the Strait.

Assessment of the risk of a dangerous event of a human collision with a remote-controlled robot

This study assesses the risk of a collision between a human and the “Robot Arm” during remote control, using a 6DoIt Mobile Robot Arm with six degrees of freedom. The bow-tie approach, combined with EN ISO 12100 standards, was employed to evaluate the risk of such a dangerous event, considering physical, organizational, psychosocial, and informational factors. The proposed risk assessment method is based on the bow-tie model, emphasizing the importance of determining the possibility of avoiding hazards as per EN ISO 12100. A three-level protective system – physical, psychological, and informational – is suggested to mitigate the risk, interconnected to enhance safety by reducing the severity of potential consequences. The approach has been refined to better determine the severity of outcomes, focusing on the ability to avoid danger. Additionally, recommendations for enhancing robotics safety management were developed, aiming to improve the effectiveness of measures to reduce collision risks during the operation of the “Robot Arm”.

A hierarchical control strategy for reliable lane changes considering optimal path and lane‐changing time point

AbstractImplementing reliable lane changes is crucial for reducing collisions and enhancing traffic safety. However, existing research lacks comprehensive investigation into the optimal path for maintaining driving quality, and little attention has been given to determining the appropriate lane changing time point. This paper addresses these gaps by presenting a novel hierarchical strategy. First, a synthesized safety distance for lane changing, which considers variable execution duration, is designed to reduce collision risk. Next, a hierarchy of optimization control strategies is proposed to obtain the optimal path. An upper neural network‐fuzzy control algorithm is established to identify an appropriate lane‐changing time point. Additionally, a lower neural network‐improved firefly algorithm is formulated to optimize the preliminary safety path based on multiple driving criteria. Furthermore, the dynamics characteristics of the vehicle are incorporated into the model predictive control algorithm to ensure the vehicle follows the optimal path. Finally, the feasibility of the proposed hierarchical control strategy is validated through typical lane‐changing scenarios conducted on the Carsim–Simulink platform.

Developing a Dynamic Speed Control System for Mixed Traffic Flow to Reduce Collision Risks Near Freeway Bottlenecks

Developing a Dynamic Speed Control System for Mixed Traffic Flow to Reduce Collision Risks Near Freeway Bottlenecks

Fine-scale collision risk mapping and validation with long-term mortality data reveal current and future wind energy development impact on sensitive species

The ongoing demand for renewable energy has boosted the development of wind farms worldwide. Given the impact these facilities have on flying species, a spatially explicit assessment of collision risk in vulnerable species is needed to guide management actions and prioritise areas for installing these infrastructures. We used GPS-tracking data of 127 adult and 50 juvenile griffon vultures in peninsular Spain gathered between 2014 and 2022 to evaluate factors influencing vulnerability and exposure and predict collision risk. We validate the observed collision risk with recorded long-term mortality data (1999–2022) at regional and wind farm scales and evaluate the estimated impact of current and future turbine facilities. Our results showed that overall food availability increases vulnerability and exposure, whilst distance to nesting areas and the presence of conspecifics decreased both vulnerability and exposure in adults and juveniles, respectively. Our maps revealed that 19% and 10% of the Spanish peninsular area had a high collision risk for adults and juveniles, respectively. Importantly, the number of turbine casualties was positively related to collision risk at the regional and wind farm scale and ∼ 18 of the breeding population lies within high collision risk areas.Moreover, the areas with the highest risk of collision also have the highest number of turbines and largely overlap with areas suitable for developing new wind farms. Our study highlights the need to reduce collision risk mapping uncertainties by validating model outputs with actual mortality data. Moreover, it emphasises the urgent need for spatial planning of wind energy development, searching for safer alternatives for biodiversity. This approach undoubtedly serves as a tool to define “not go to” areas for installing new turbines for one of the most sensitive species.

Enhancing Maritime Safety and Efficiency: A Comprehensive Sea Fog Monitoring System for Ningbo Zhoushan Port

Sea fog poses a considerable challenge to port operations, impacting maritime safety and efficiency. During the past five years, the average annual downtime of the navigation dispatch department in Ningbo Zhoushan Port due to weather was 800–1000 h, of which approximately 300 h can be attributed to sea fog. This study addresses the issue by developing a comprehensive sea fog monitoring system for Ningbo Zhoushan Port. The system utilizes automatic weather stations (AWS) and visibility laser imaging, detection, and ranging (LIDAR) to assess sea fog severity and improve monitoring accuracy. By increasing monitoring frequency and adopting corresponding warning measures, the system aims to enhance maritime safety and efficiency in Ningbo Zhoushan Port. The results showed that the implemented system successfully determines sea fog severity, enables real-time monitoring, and provides precise visibility assessments. Joint assessments revealed a substantial increase in the annual operating time and revenue of the port. These findings underscore the importance of advanced monitoring techniques in optimizing port operations, reducing collision risks, and mitigating economic losses caused by sea fog.

Driving safety zone model oriented motion planning framework for autonomous truck platooning

A driving-safety-zone-model-oriented motion planning framework (DSZMF) is proposed for autonomous platoons in heterogeneous driving environments with complex driving behaviors and interactions between human-driven and autonomous vehicles. As an extension of the responsibility-sensitive-safety (RSS) model, the driving safety zone model ensures that autonomous truck platoons adhere to explicit and implicit traffic rules as rational traffic participants.It consists of three zones created by safe distances and artificial potential field (APF), namely the restricted zone, the coordinated zone, and pre-cautionary zone. The Rational Traffic Participant (RTP) module is created by using a Finite State Machine (FSM) to provide an optimized platooning behavioral strategy based on the dynamic states of surrounding vehicles. Furthermore, the distributed model predictive controllers are utilized for motion planning, while the H infinity controller is developed to maintain the string stability of the autonomous platoon. The proposed DSZMF generates behavioral decisions by thoroughly considering the driving safety zone model, string stability, and multiple vehicle dynamics constraints. Finally, three critical scenarios are co-simulated for case studies, and the simulation results demonstrate that the DSZMF improves the safe time integration rate over the existing MCF by 18.9%, 11.1%, and 11.6% in three scenarios, respectively. In addition, DSZMF increases the minimum longitudinal and lateral Time to Collision (TTC) values to reduce collision risks. The case studies validate the efficacy of the proposed method for safety assurance and collaborative control of the autonomous platoon.

Interactive on-ramp merging decision-making with motion prediction considering merging motivation

On-ramp is one of the scenarios most likely to cause traffic accidents and congestion. In order to mitigate the conflict between mainline vehicles and ramp vehicles, and improve vehicle safety and travel efficiency, we propose an interactive on-ramp merging decision-making (IORMDM) method based on motion prediction. We first propose a motion prediction method for different actions of vehicles based on model predictive control. Meanwhile, the game theory is employed to construct the interaction behavior between the ramp vehicle and the mainline vehicle, and the merging motivation of the ramp vehicle is modeled to describe the collision risk between it with the end of the acceleration lane. Afterward, according to the predicted trajectories of vehicles, the comprehensive payoff of vehicle collision risk, efficiency, passenger comfort, and merging motivation of each action is solved. The Nash equilibrium solution is solved to determine the optimal action of each vehicle according to the payoff table. Simulation experiments demonstrate that our proposed method could reduce collision risk and improve traffic efficiency.

Space debris remediation using space-based lasers

Centimetre and sub-centimetre debris fragments present a significant threat to many operational satellites in Earth orbit. When debris can be tracked, the preferred approach is collision avoidance to slightly alter the orbit of the at-risk satellite, resulting in an along-track displacement which compounds over several orbits. Although numerous strategies for active debris removal and remediation have been proposed, most such methods involve rendezvous maneuvers with targeted pieces of debris prior to some mechanical interaction. While such approaches are appropriate for removing larger objects which are potential sources of further debris, they are unsuitable for application to fragments which are too small to be accurately tracked from Earth and with which a rendezvous would be challenging.This paper investigates the use of photon pressure and ablation from space-based lasers to directly affect the orbits of small debris fragments, both to lower their orbits and lifetimes, and to reduce collision risk with operational satellites. A mission concept is studied which enables the cataloguing of debris shells of small fragments produced after breakup events, while also allowing the encountered fragments to be illuminated by a laser on board the observation satellite(s). The concept takes advantage of a laser’s ability to impart momentum at a distance by employing opportunistic interaction with passing fragments, assuming no prior knowledge of their orbits and no ability to rendezvous. The impact of the mission over a 10-year operational lifetime is simulated statistically by analysing the dynamics of typical encounters and the achievable impact on fragment orbits. The effects of off-beam-axis components of the applied ΔV and its implications for beam tracking are also investigated, along with the effects of extreme laser fluence on fragment attitude.