Complex Traffic Situations Research Articles

S-RAF: A Simulation-Based Robustness Assessment Framework for Responsible Autonomous Driving

As artificial intelligence (AI) technology advances, ensuring the robustness and safety of AI-driven systems has become paramount. However, varying perceptions of robustness among AI developers create misaligned evaluation metrics, complicating the assessment and certification of safety-critical and complex AI systems such as autonomous driving (AD) agents. To address this challenge, we introduce Simulation-Based Robustness Assessment Framework (S-RAF) for autonomous driving. S-RAF leverages the CARLA Driving simulator to rigorously assess AD agents across diverse conditions, including faulty sensors, environmental changes, and complex traffic situations. By quantifying robustness and its relationship with other safety-critical factors, such as carbon emissions, S-RAF aids developers and stakeholders in building safe and responsible driving agents, and streamlining safety certification processes. Furthermore, S-RAF offers significant advantages, such as reduced testing costs, and the ability to explore edge cases that may be unsafe to test in the real world.

Advancing VR simulators for autonomous vehicle–pedestrian interactions: A focus on multi-entity scenarios

Recent research has increasingly focused on how autonomous vehicles (AVs) communicate with pedestrians in complex traffic situations involving multiple vehicles and pedestrians. VR is emerging as an effective tool to simulate these multi-entity scenarios, offering a safe and controlled study environment. Despite its growing use, there is a lack of thorough investigation into the effectiveness of these VR simulations, leaving a notable gap in documented insights and lessons. This research undertook a retrospective analysis of two distinct VR-based studies: one focusing on multiple AV scenarios (N = 32) and the other on multiple pedestrian scenarios (N = 25). Central to our examination are the participants’ sense of presence and their crossing behaviour. The findings highlighted key factors that either enhance or diminish the sense of presence in each simulation, providing considerations for future improvements. Furthermore, they underscore the influence of controlled scenarios on crossing behaviour and interactions with AVs, advocating for the exploration of more natural and interactive simulations that better reflect real-world AV and pedestrian dynamics. Through this study, we set a groundwork for advancing VR simulators to study complex interactions between AVs and pedestrians.

Revolutionizing Roads: The Impact of Autonomous Vehicles on Future Travel

This project focuses on developing an autonomous self-driving car by integrating advanced algorithms with cutting-edge hardware. The vehicle is designed to perceive its environment, make informed decisions, and navigate complex traffic scenarios autonomously by leveraging machine learning and computer vision technologies. Essential methods include using deep learning algorithms for object detection and classification, sensor fusion techniques to combine data from cameras, LiDAR, and radar, and reinforcement learning for decision-making in dynamic environments. The project emphasizes the critical role of AI in enabling the car to interpret and respond to dynamic road conditions while ensuring reliable performance through rigorous testing and validation in simulated and real-world scenarios. Initial results from testing indicate that the car can successfully navigate complex traffic situations, such as merging onto highways and responding to pedestrians, with a high degree of accuracy. By pushing the boundaries of autonomous vehicle technology, this research aspires to contribute to the ongoing evolution of self-driving cars and their potential to revolutionize mobility. With a focus on safety, efficiency, and innovation, this endeavor represents a significant step forward in developing autonomous vehicles, offering new possibilities for the future of transportation. The project promises to improve travel convenience and significantly reduce traffic accidents, ultimately contributing to a safer and more efficient road system.

Comparing and Parameterizing the Electrical Energy Consumption Models in SUMO

This paper examined the performances of the current four battery models in SUMO. The possibility of expanding the model parameterization was also investigated and the corresponding extension was carried out for PHEMlight. Accordingly, the models can be compared more fairly. Three scenarios were used, namely the Worldwide harmonized Light vehicles Test Cycle, a constant high-speed highway scenario and an area scenario with a relatively complex traffic situation. The results show that all models can address recuperation and propulsion, and deliver the similar result at very low acceleration. The models based on average vehicle data generally tend to deliver higher battery consumption than the models with individual vehicle type-specific parameterization, especially PHEMlight5, while HBEFA4 only has one electric vehicle class and is therefore not sensitive to various vehicle characteristics. Moreover, the model by Kurczveil and López (EVM) seems to tend to have the lowest consumption of all models.

A big data analytics method for the evaluation of maritime traffic safety using automatic identification system data

The complex traffic situations are among the factors influencing maritime safety. They can be quantitatively estimated through the analysis of traffic data. This paper explores the impact of complex traffic situations on maritime safety, focusing on inland waterway traffic. It presents a big data analytics method, utilizing data from the Automatic Identification System (AIS) and historical maritime accident records. The methodology involves AIS data preprocessing and spatial autocorrelation models, including Moran's index, to extract and evaluate the dynamic characteristics of maritime traffic. The analysis of traffic characteristic includes a thorough investigation into the spatial-temporal distribution of ship average speed and trajectory density. The paper then introduces an effective traffic characteristic analysis model that evaluates the relationship between maritime traffic patterns and accidents. The study, specifically targeting the Nanjing section of the Yangtze River, reveals variations in ship trajectory density and average speed over time. It identifies several hotspots with a significant local correlation between these factors. Moreover, a substantial correlation is found between the locations of maritime accidents and areas with increased ship trajectory density and average speed. These results may provide insights for traffic safety management and highlight strategies for preventing maritime accidents.

Analysis of coping capacities and cognitive biases of novice drivers-A questionnaire-based study.

Coping capacity is a key aspect of driver-vehicle interaction when drivers observe and make decisions, and is of great importance for drivers. However, different drivers have different self-cognition and assess their driving abilities differently, especially for novice drivers. Based on questionnaire data, this study has investigated the coping capacities of drivers in both static environments and dynamic environments. With the ANOVA analysis method and the structural equation model (SEM), this study has verified the effects of gender and driving factors (driving years, driving frequency, driving time) on drivers' coping capacities based on drivers' self-assessment scores and mutual assessment scores. Drivers' self-assessment scores show significant effects of all factors on drivers' coping capacities, and drivers' mutual assessment scores show significant effects of all factors, excluding driving time, on drivers' coping capacities. Also, it has been found that all drivers in the driving year group have cognitive biases. It seems that first-year drivers are always overconfident with their driving skills, while drivers with a driving experience of more than three years usually score driving skills of themselves and other drivers most conservatively. With increased exposure to various traffic conditions, experienced drivers are more aware of their limitations in dealing with complex traffic situations, while novice drivers do not know their lack of capability to properly respond to any unexpected situation they could encounter.

Does the priority of ambulance guarantee no delay? a MIPSSTW model of emergency vehicle routing optimization considering complex traffic conditions for highway incidents.

Globally, traffic accidents on the highway network contribute significantly to a high fatality rate, drawing considerable attention from health institutions. The efficiency of transportation plays a vital role in mitigating the severe consequences of these incidents. This study delves into the issues of emergency vehicles experiencing delays despite having priority. Therefore, we construct mixed-integer linear programming with semi-soft time windows (MIPSSTW) model for optimizing emergency vehicle routing in highway incidents. We analyze the time-varying and complex traffic situations and respectively propose corresponding estimation approaches for the travel time of road segments, intersections on the urban road network, and ramp-weave sections on the highway network. Furthermore, we developed a modified cuckoo search(MCS) algorithm to solve this combinatorial problem. Optimization strategies of Lévy flight and dynamic inertial weight strategy are introduced to strengthen the exploration capability and the diversity of solution space of the CS algorithm. Computational experiments based on the Chinese emergency medical system data are designed to validate the efficacy and effectiveness of the MIPSSTW model and MCS algorithm. The results show that our works succeed in searching for high-quality solutions for emergency vehicle routing problems and enhance the efficacy of strategic decision-making processes in the realm of incident management and emergency response systems.

Quantitative analysis and model prediction of urban traffic flow optimization by geographic information technology

Abstract With the development of intelligent transportation, urban traffic flow prediction faces more complex traffic situations and higher accuracy requirements. In this paper, we collected multi-day traffic data from local cities and used a k-means clustering algorithm to analyze the data by clustering. A BP neural network prediction algorithm combined with k-means clustering analysis is designed to construct an “hour-day-week” urban traffic flow prediction model. The model is trained and applied to real-time urban traffic flow prediction to further analyze the performance effect of this model. The training time of this model is the shortest, which is about 67 minutes, and the MAE value is 3.02. The training speed is ahead of the longest training time in model 2, which is about 163 minutes, and the error is reduced by 8.04 compared with that of the highest prediction error in model 1. With different levels of noise added, the R², ACC, and RMSE values of the model in this paper are maintained at about 0.45, 0.63, and 0.8, respectively, indicating that different levels of noise have a significant effect on the performance of this model. This indicates that different degrees of noise have little effect on the performance of the model in this paper. In addition, the prediction effect is better after clustering analysis. The MAPE value of this paper’s model is the lowest, only 2.64%, which is 3.65%-7.52% lower than the other three control models. The experimental results above fully demonstrate the superior performance of this paper’s model, which suggests that this paper’s model is more effective in predicting urban traffic flow.

Design of a Novel Convolutional Deep Network Model for Car Accident Prediction

Real-time collision risk estimation is thought to be essential to a sophisticated traffic management system. To swiftly determine accident probability is the goal of real-time crash risk prediction. However, due to the complex traffic situation on urban arterials, urban arterials were rarely included in previous studies, which mostly focused on highways. This paper suggests using Convolutional Deep Network model (CDNM) to forecast the probability of vascular accidents in real time. This model has the benefit of being able to use both LSTM and CNN. CNN retrieves the time-invariant characteristics, while LSTM captures the data's long-term dependability. To estimate the likelihood of an accident, many sorts of data are used, including weather, traffic, and signal timing data. There are also many other data preparation methods employed. The problem of data imbalance is also addressed by normalization which oversamples the crash cases. Using a variety of measures, the CDNM is enhanced on the training data and assessed on the test data. Five more benchmark models are constructed for model comparison. K-NN, ISVM, ANN, CNN, CNN-EVT and GAN are some of the models in this group. Experimental findings show that the proposed CDNM beats the competition in terms of sensitivity, specificity, accuracy, AUC and G-mean value. The findings of this paper demonstrate that CDNM can real-time prediction of crash risk at arterials.

Optimization Of The Use Of ATC Automation Approach Control Surveillance At Perum LPPNPI MATSC Branch

ATC (Air Traffic Control) automation system is a complex system, which helps maintain air traffic order, guarantee flight intervals, and prevent aircraft collisions. This is important to ensure the safety of air traffic. Failure effect evaluation is an important part of ATC automation system reliability engineering. However, changes like these also present challenges and ethical considerations that need to be considered to ensure that aviation safety remains a top priority. In optimizing the use of ATC Automation, research was carried out using qualitative analysis, which means that in this study, data, interviews and documents related to the problem were used. The data used is the result of interviews submitted to the ATC. In conducting this research, the study was conducted in May 2023 using descriptive analysis. The intended purpose of this study is to find out that the use of ATC Automation has been running optimally and has also reduced workload. Accurate in dealing with complex traffic situations. This research is also expected to be used as further research in the use of ATC Automation.

Semantics-Aware Dynamic Graph Convolutional Network for Traffic Flow Forecasting

Traffic flow forecasting is a challenging task due to its spatio-temporal nature and the stochastic features underlying complex traffic situations. Currently, Graph Convolutional Network (GCN) methods are among the most successful and promising approaches. However, most GCNs methods rely on a static graph structure, which is generally unable to extract the dynamic spatio-temporal relationships of traffic data and to interpret trip patterns or motivation behind traffic flows. In this paper, we propose a novel Semantics-aware Dynamic Graph Convolutional Network (SDGCN) for traffic flow forecasting. A sparse, state-sharing, hidden Markov model is applied to capture the patterns of traffic flows from sparse trajectory data; this way, latent states, as well as transition matrices that govern the observed trajectory, can be learned. Consequently, we can build dynamic Laplacian matrices adaptively by jointly considering the trip pattern and motivation of traffic flows. Moreover, high-order Laplacian matrices can be obtained by a newly designed forward algorithm of low time complexity. GCN is then employed to exploit spatial features, and Gated Recurrent Unit (GRU) is applied to exploit temporal features. We conduct extensive experiments on three real-world traffic datasets. Experimental results demonstrate that the prediction accuracy of SDGCN outperforms existing traffic flow forecasting methods. In addition, it provides better explanations of the generative Laplace matrices, making it suitable for traffic flow forecasting in large cities and providing insight into the causes of various phenomena such as traffic congestion. The code is publicly available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/gorgen2020/SDGCN</uri> .

Trajectory planning based on spatio-temporal reachable set considering dynamic probabilistic risk

Trajectory planning in complex traffic situations has always been a challenging task for intelligent vehicles. Comparing to the decoupling method, the spatio-temporal trajectory planning method owns more flexibility and reasonability due to the combination of lateral and longitudinal motion. However, it still has some shortcomings, such as unreasonable risk assessment, high computational complexity and heavy dependence on other models for generating target points. Therefore, a novel spatio-temporal based trajectory planning framework considering probability risk is proposed in this paper. Firstly, a GNN-LSTM based on trajectory prediction algorithm is presented in terms of risk analysis, and particularly the predicted trajectories and the vehicle dynamic model are combined for risk assessment. Secondly, a rough-fine hierarchical planning framework based on reachable set and dynamic programming is proposed. In this framework, the reachable set is taken as spatio-temporal node to reduce the computational costs and dynamic programming can help the algorithm to eliminate the dependence of other models in evaluating target points. Finally, a traffic scenario with random interactive obstacles is built and tested on a HIL platform. The experimental results show that compared with other typical algorithms, the average driving efficiency, driving risk behavior and driving comfort of the vehicle are significantly improved.

Toward resilient autonomous driving—An experience report on integrating resilience mechanisms into the Apollo autonomous driving software stack

Autonomous driver assistance systems (ADAS) have been progressively pushed to extremes. Today, increasingly sophisticated algorithms, such as deep neural networks, assume responsibility for critical driving functionality, including operating the vehicle at various levels of autonomy. Elaborate obstacle detection, classification, and prediction algorithms, mostly vision-based, trajectory planning, and smooth control algorithms, take over what humans learn until they are permitted to control vehicles and beyond. And even if humans remain in the loop (e.g., to intervene in case of error, as required by autonomy levels 3 and 4), it remains questionable whether distracted human drivers will react appropriately, given the high speed at which vehicles drive and the complex traffic situations they have to cope with. A further pitfall is trusting the whole autonomous driving stack not to fail due to accidental causes and to be robust against cyberattacks of increasing sophistication. In this experience report, we share our findings in retrofitting application-agnostic resilience mechanisms into an existing hardware-/software-stack for autonomous driving—Apollo—as well as where application knowledge helps improve existing resilience algorithms. Our goal is to ultimately decrease the vulnerability of autonomously driving vehicles to accidental faults and attacks, allowing them to absorb and tolerate both, as well as to come out of them at least as secure as before the attack has happened. We demonstrate replication and rejuvenation on the driving stack's Control module and indicate how this resilience can be extended both downwards to the hardware level, as well as upwards to the prediction and planning modules.

A collision avoidance algorithm with intention prediction for inland waterways ships

Collision avoidance is one of the most challenging problems in developing a Maritime Autonomous Surface Ship. This paper proposes a pro-active collision avoidance algorithm for inland waterway ships. The algorithm addresses the problem of avoiding collisions with dynamic obstacles by applying a situation-based intention prediction for neighboring ships. This prediction algorithm allows own ship to be aware of future collision threats caused by the course changes of nearby ships. The prediction scheme is integrated into a scenario-based model predictive control scheme that has been modified for application in inland waterway traffic. The proposed algorithm can deal with complex traffic situations that a ship can encounter, and the performance of the proposed algorithm is evaluated in several experiment simulations.

The impacts of automated urban delivery and consolidation

Automation in urban freight transport is an important milestone for city logistics, but it is challenging due to the complex traffic situations. While the parcel volume is soaring due to the popularity of e-commerce – and especially accelerated by COVID, cities are thinking about the future delivery system. Automation and consolidation are expected to bring disruptive changes to the system we know today. The aim of the present paper is to provide an insight in the impact assessment method used and the results related to parcel delivery in Vienna. By applying analytical methods, we show which impacts at what magnitude we may expect from the changes brought by automation in freight transport. We consider the direct impacts consisting of fleet size, freight mileage and fleet operation costs, as well as the wider impacts consisting of parking space, public health and road safety.

Cross-Area Travel Time Uncertainty Estimation From Trajectory Data: A Federated Learning Approach

Along with urbanization and the deployment of GPS sensors in vehicles and mobile phones, massive amounts of trajectory data have been generated for city areas. The analysis of these data has substantially contributed to research and advancements of travel time estimation. However, existing work focuses on estimating travel time inside a particular area, and cross-area travel time estimation has privacy security challenges due to data exchange issues among areas. Meanwhile, the majority of methods estimate a deterministic travel time for a given trajectory, which does not account for complex traffic situations and user requirements. To address these problems, we propose a cross-area travel time uncertainty estimation algorithm for estimating the uncertainty of travel times while preserving privacy among different areas. Specifically, we design a comprehensive cross-area privacy-preserving solution that trains a tailor-made neural network travel time estimator in each area by local data, and incorporates federated learning for training. Furthermore, we employ Bayesian deep learning principles and adopt Monte-Carlo dropout to quantify the uncertainty associated with travel time. To evaluate the proposed approach, we conduct a series of comprehensive case studies with two real-world trajectory datasets. Extensive results demonstrate the superiority of the proposed approach compared to baselines in the context of the cross-area setting.

Physics of microscopic vehicular traffic prediction for automated driving.

With the use of microscopic traffic simulations, physical features of microscopic traffic prediction for automated driving that should improve traffic harmonization and safety have been found: During a short-time prediction horizon (about 10s), online prediction of the locations and speeds of all vehicles in some limited area around the automated-driving vehicle is possible; this enables the automated vehicle control in complex traffic situations in which the automated-driving vehicle is not able to make a decision based on current traffic information without the use of the microscopic traffic prediction. Through a more detailed analysis of an unsignalized city intersection, when the automated vehicle wants to turn right from a secondary road onto the priority road, the statistical physics of the effect of a data uncertainty caused by errors in data measurements on the prediction reliability has been studied: (i) probability of the prediction reliability has been found; (ii) there is a critical uncertainty, i.e., a maximum amplitude of errors in data measurements: when the uncertainty does not exceed the critical uncertainty, the prediction reliability probability is equal to 1, otherwise, the prediction is not applicable for a reliable automated vehicle control; (iii) physical characteristics of the microscopic traffic prediction, at which the critical uncertainty can be increased considerably, have been found; and (iv) there is an optimal automated vehicle control at which the critical uncertainty reaches a maximum value.

Identifying And Improving Young Drivers’ Perceptions Towards Vulnerable Road Users

Vulnerable road users (VRUs) like bicyclists, pedestrians, and road users of other modalities, are at a higher risk of collision with young drivers when a complex traffic situation presents itself. Past research has established the importance of young drivers’ perceptions about VRUs around safe interactions. This research aimed to design and evaluate a novel persuasive intervention that can improve perceptions of young drivers towards VRUs. First, the study identified recently licensed (12 to 18 months) perceptions towards VRUs through structured interviews. Based on these findings, an interactive intervention was designed and evaluated. Results showed improvement over time in self-reported violations among groups who received the intervention or the control. Additionally, participants who received a citation showed lower violations and lapses. The findings have implications for designing future interventions for interactions with VRUs.

Multi-Agent Trajectory Prediction With Heterogeneous Edge-Enhanced Graph Attention Network

Simultaneous trajectory prediction for multiple heterogeneous traffic participants is essential for safe and efficient operation of connected automated vehicles under complex driving situations. Two main challenges for this task are to handle the varying number of heterogeneous target agents and jointly consider multiple factors that would affect their future motions. This is because different kinds of agents have different motion patterns, and their behaviors are jointly affected by their individual dynamics, their interactions with surrounding agents, as well as the traffic infrastructures. A trajectory prediction method handling these challenges will benefit the downstream decision-making and planning modules of autonomous vehicles. To meet these challenges, we propose a three-channel framework together with a novel Heterogeneous Edge-enhanced graph ATtention network (HEAT). Our framework is able to deal with the heterogeneity of the target agents and traffic participants involved. Specifically, agents’ dynamics are extracted from their historical states using type-specific encoders. The inter-agent interactions are represented with a directed edge-featured heterogeneous graph and processed by the designed HEAT network to extract interaction features. Besides, the map features are shared across all agents by introducing a selective gate-mechanism. And finally, the trajectories of multiple agents are predicted simultaneously. Validations using both urban and highway driving datasets show that the proposed model can realize simultaneous trajectory predictions for multiple agents under complex traffic situations, and achieve state-of-the-art performance with respect to prediction accuracy. The achieved final displacement error (FDE@3sec) is 0.66 meter under urban driving, demonstrating the feasibility and effectiveness of the proposed approach.

Lessons learned from setting up a demonstration site with autonomous shuttle operation – based on experience from three cities in Europe

The interest in operating autonomous vehicles is growing and several demonstration sites using automated shuttles have been established all over the world. Major work is involved in setting up an automated shuttle operation that involves more than identifying the relevant site, including adhering to current regulations and obtaining approval, as well as a considerable amount of preparation and commissioning required at the site. The shuttle must pass relevant national vehicle regulations, and the operation site has to undergo a site assessment. This paper is based on lessons learned achieved from setting up automated shuttle operations in three different areas in Europe: Brussel (Belgium), Linköping (Sweden) and Turin (Italy). The focus is on the practical aspects of operation. Through the experience we have gained of setting up demonstration sites at three locations in Europe, we have identified the need to summarise the lessons learned from preparing AV shuttle operation sites in order to facilitate the implementation of other operation sites. Hence, this paper aims to consolidate lessons learned during preparation and implementation of automated shuttle operations in near urban environments and to identify the path toward future implementation The three sites operate different brands and number of shuttles, different types of infrastructure and varying local conditions. The focus here was on generic lessons learned and not to understand differences between brands and operators. It is clear that further development of the AV shuttles is vital to ensure that they operate smoothly in complex traffic situations considering lane and road width, shared spaces, snow, dust, rain, leaves, birds, etc. Adapting the road infrastructure to enable the shuttles to run in the autonomous mode should be avoided, instead the shuttle development should prioritise fitting into the existing traffic environment and eco system. Mitigation areas have been identified covering: road infrastructure, weather dependant operation, season dependent operation, improvement of localisation, digital infrastructure, design and working conditions, and citizens’ user experience.