Agent driving behavior modeling for traffic simulation and emergency decision support

Traffic evacuation is one of the most important tasks in emergency management, and it is challenging for governments to plan an efficient and safe evacuation before a huge disaster strikes. This paper presents a traffic evacuation simulation system that generates agent's driving behavior based on multi-level driving decision models. The agent's driving behavior combines multiple widely used behavior models from each decision level. The agent-based traffic evacuation system is proposed and a prototype system implements each agent's multi-level modular driving decision models. The simulation experiment studies show varied clearance time, evacuation rates per shelter, and the variety and number of traffic jams to support traffic evacuation planning decisions in a crowded city liked Beijing, China. The simulation studies compare the existing evacuation plan with other simulated plans and evaluate it for designing a better and more realistic traffic evacuation plan.

Following the principles of agent-oriented analysis and design, the urban traffic micro simulation system was divided into several modules and a micro simulation framework based on multi-agent was obtained on the basis of requirement analysis. The paper discuss agent-oriented traffic micro simulation modeling process, beginning with traffic flow generation model, car-following model, it gives design scheme of agents in the system. Besides, the paper gives simulation systempsilas infrastructure and simulation flow. Thus a reusable and flexible framework of urban traffic micro simulation system was achieved.

Traffic evacuation plays a critical role in saving lives in devastating disasters such as hurricanes, wildfires, floods, etc. An ability to evaluate evacuation plans in advance for these rare events, including identifying traffic flow bottlenecks, improving traffic management policies, and understanding the robustness of the traffic management policy are critical for emergency management. Given the rareness of such events and the corresponding lack of real data, traffic simulation provides a flexible and versatile approach for such scenarios, and furthermore allows dynamic interaction with the simulated evacuation. In this paper, we build a traffic simulation pipeline to explore the above problems, covering many aspects of evacuation, including map creation, demand generation, vehicle behavior, bottleneck identification, traffic management policy improvement, and results analysis. We apply the pipeline to two cases studies in California. The first is Paradise, which was destroyed by a large wildfire in 2018 and experienced catastrophic traffic jams during the evacuation. The second is Mill Valley, which has high risk of wildfire and potential traffic issues since the city is situated in a narrow valley.

In large-scale events, the effectiveness of traffic evacuation is crucial for reducing congestion and improving traffic safety. However, individual decision-making in group decision-making behavior is easily influenced by the preference of the group leader, especially in emergency evacuation scenarios, the leader of the crowd becomes a hidden leader, and the irrationality of its individual evacuation decision-making is very likely to cause decision-making bias, which forms group evacuation decision-making bias, leading to a decrease in the actual evacuation efficiency. In this paper, based on the principle of group decision bias, we study how to guide the local interaction between individual decision makers and the group in the process of traffic evacuation for large-scale events, construct a traffic evacuation induction decision model by combining real-time traffic information updates, establish a microscopic traffic simulation system by using the theory of meta-cellular automata, reasonably allocate traffic flow and guide vehicles and pedestrians to evacuate along different paths, so as to alleviate the negative impacts of group decision bias on evacuation behaviors. The results of the study show that the introduction of group decision-making bias can reduce the negative impact of evacuation behavior. The results show that the traffic guidance strategy for large-scale events with the introduction of group decision-making bias influencing factors can effectively reduce the influence of group decision-making bias, improve the efficiency of traffic evacuation, and provide important support for the governmental departments to make decisions on the management of traffic evacuation for large-scale events.

With the continuous improvement of national economic strength, the transportation field has also been developed at an unprecedented speed, and the transportation system simulation is an important technology and method in the field of transportation engineering. Establishing rele-vant models through traffic system simulation can not only improve the efficiency of urban traf-fic utilization in urban planning, but also optimize some existing traffic problems and promote the sustainable development of the traffic field. This paper first describes the specific concept of the traffic system simulation model, and discusses the development status of the traffic system simulation model from the microscopic traffic simulation model, the mesoscopic traffic simula-tion model, and the macroscopic traffic simulation model, as well as the characteristics and dif-ferences of the three types of models. Finally, it selects examples of each type of simulation model for specific analysis. The overview of the traffic system simulation model can improve the public's awareness of the traffic system simulation and help the specific development of urban traffic.

Trajectories of community fire adaptation: Social diversity, social fragmentation and the temporal evolution of wildfire action.

When disasters strike, hospitals are challenged to continue the delivery of health care, much of which is dependent on trainees. Fortunately, disasters are infrequent; however, that infrequency leads to an absence of training in how to plan and execute a disaster response, and leaves medical professionals and trainees unprepared to handle the burden of a disaster when it strikes. In August 2017, Hurricane Harvey tested the efficacy of the graduate medical education (GME) disaster plan at Corpus Christi Medical Center (CCMC) and provided an opportunity to evaluate residents' performance in a disaster situation in the inpatient setting. In this Invited Commentary, the authors recall their experience at CCMC during Hurricane Harvey and its aftermath. They describe the challenges that resulted from a disaster plan that proved to be inadequate. Based on their own lessons learned, the authors offer several recommendations for more effective disaster planning for GME programs: adequate staffing, adequate resources, optimal team structure, effective communication, safe evacuation, and thorough planning. This evaluation of how the residents prepared for and responded to an actual natural disaster provides perspective into organizational and institutional processes that could benefit from further development and implementation.

Traffic simulation systems have been widely used for traffic system analysis and optimization. The traditional simulation system uses analytical models for each kind of driving behaviour, with little regard for the coupling relationship between the models, resulting in limited performance and complicated calibration and validation processes. In this study, a Data-Driven Simulation System (DDSS) framework was introduced to define traffic system operation processes and coordinate submodules. The proposed DDSS includes a General Kernel for running the simulation environment, and a Customized Interface for accessing to various data-driven driving behaviour models. To unify the modelling of multiple driving behaviour and increase prediction accuracy, a data-driven Sim-Hybrid Retraining Constrained LSTM (SHRC-LSTM) model was built. In addition, experiments on two NGSIM freeway testbeds demonstrated that DDSS produced more precise results in terms of efficiency, safety, and emissions than the most widely-used simulation system VISSIM.

Ensuring safe and efficient evacuation in university dormitories is crucial for minimizing risks during emergencies. This study develops a comprehensive safety evacuation scheme evaluation model by integrating the entropy weight method (EMW) and the technique for order preference by similarity to an ideal solution (TOPSIS). The model aims to provide an objective and systematic approach to evaluate and rank evacuation schemes for university dormitories. A set of evaluation indicators, encompassing building scale, building design and layout, emergency equipment and facilities, personnel factors and emergency management, evacuation effectiveness and safety, management and support, is established. The EWM is employed to calculate the weight of each indicator, reflecting its relative importance. The TOPSIS method is then applied to measure the closeness of each evacuation scheme to the ideal solution, enabling comparative ranking. A case study conducted in 8 university dormitories validates the model’s practicality and effectiveness. The results demonstrate that the proposed model offers a robust decision-making tool for university administrators, aiding in optimizing evacuation plans and enhancing safety during emergencies.

Traffic applications, in which vehicles are equipped with a radio interface and communicate directly with each other and the road traffic infrastructure are a promising field for ad-hoc network technology. Vehicular applications reach from entertainment to traffic information systems, including safety aspects where warning messages can inform drivers about dangerous situations in advance. As performance tests of the real system are very expensive and not comprehensive, today's evaluations are based on analysis and simulation via traffic simulators. In order to investigate the impact of traffic information systems there are two options: First, traffic simulators can be extended by application code and a simplified model for wireless communication. Second, existing network simulators can be coupled with existing traffic simulators. We favor the coupling of existing and well known simulators as we believe that the wireless communication characteristics influence the data transfer significantly and an oversimplified transmission model can lead to flawed results. In this paper we describe the feedback loop between traffic and network simulators named traffic control interface (TraCI) and outline its versatility. We explain its use to determine possible energy consumption reduction when traffic lights send their phase schedules to vehicles.

Simulation of real‐world traffic scenarios is widely needed in virtual environments. Different from many previous works on simulating vehicles or pedestrians separately, our approach aims to capture the realistic process of vehicle–pedestrian interaction for mixed traffic simulation. We model a decision‐making process for their interaction based on a gap acceptance judging criterion and then design a novel environmental feedback mechanism for both vehicles' and pedestrians' behavior‐control models to drive their motions. We demonstrate that our proposed method can soundly model vehicle–pedestrian interaction behaviors in a realistic and efficient manner and is convenient to be plugged into various traffic simulation systems. Copyright © 2015 John Wiley & Sons, Ltd.

In order to meet the increasing aesthetic needs of the public, improve the integration of traffic planning and urban planning, facilitate traffic simulation data analysis and effect display, and facilitate traffic planning scheme evaluation, this paper is based on cesium to develop a three-dimensional simulation platform for urban traffic, design Celestia came out, and based on common simulation software such as sumo, Paramics, Vissim, and used Python and JavaScript language to design and develop a web page simulation platform to display the 3D effect of road traffic simulation for users, and added a lot to improve the simulation effect, which is convenient for users. Functions to evaluate simulation effects. Users only need to open the website, upload the simulation file or select the map area in the map link box, select the simulation parameter requirements, and wait for the data to be read in the background to get an interactive 3D traffic simulation. This work with convenient operation, powerful function and broad development space largely fills the blank of domestic road traffic 3D simulation. Experiments show that when the number of divisions reaches 15, the resolution is 0.037m (within 5 cm), which can meet most practical needs.

With the outbreak of COVID-19, the phenomenon of crowds has attracted much attention. To study the impact of fire on evacuation density of teaching building under epidemic situation, a university teaching building was simulated by FDS. The influence of smoke exhaust window opening on fire development was studied by analyzing the law of smoke, temperature and CO concentration, and the allowable evacuation time ASET of teaching building was obtained. Evacuation simulation using Pathfinder determines the required evacuation time RSET and analyzes congestion points, making evacuation improvements from two aspects: reducing the proportion of people and planning evacuation. The results show that CO concentration is an important factor affecting the ASET of teaching buildings, and it can extend the ASET of teaching buildings when the top smoke exhaust window is open; The evacuation congestion points of teaching buildings are mostly concentrated in the classroom exit, the east corner of the passage, the corner of the stair platform and the corner of the west exit. Although reducing the proportion of people can achieve safe evacuation, it can not meet the needs of the evacuation density under the epidemic situation. Through further evacuation planning, it can not only meet the requirements of safe evacuation, but also reduce the evacuation density, which provides a reference for the safe evacuation of teaching buildings under the epidemic situation.

In emergency scenarios service vehicles must identify potential route(s) and use the best available route. However, route identification requires intelligent decision-support systems which generally use non-traditional approaches with tools characterised by flexible non-hierarchical structures. Conventional models using group decision-support systems have been applied; however, when used in smart urban environments, emergency response services have limitations in their ability to identify unobstructed paths (routes) in dynamic operating environments. In this paper we introduce a novel path planning method for autonomous vehicle control in emergency situations. The proposed model uses self-organizing maps in an integrated Spiral STC algorithm termed the: Hybrid SOM-Spiral STC model which uses hedge algebras and Kansei evaluation in group decision-support. The proposed model has been designed to quantify qualitative factors using sensor derived data processed with human sensibilities and preferences in emergency decision support. The experimental results show that the proposed model achieves significant improvements in group decision-support under dynamic uncertainty. We posit that our novel approach holds the prospect of improvements in the provision of emergency services.

Traffic simulators can capture the complex dynamics of road networks thus are widely used to understand the behavior of the traffic system and predict the effects of transportation technologies, events and new policy changes. To build a traffic simulation model that can accurately capture the real traffic conditions, the Origin-Destination (OD) matrix is needed to be fed into the simulator as an input. In general, it is difficult to acquire information about the real OD matrix of a network. In this paper, we propose a neural network model for estimating the OD matrix that excites the microscopic simulation model for complex traffic networks to reproduce real world traffic flows using only the flow rate information of a small subset of links in the traffic network, which is relatively easy to collect. An optimization method is used to generate the training dataset of the neural network. Combining the OD matrix estimation model, the training dataset generation method, and the microscopic traffic simulator, an integrated traffic simulation-prediction system is developed to predict the behavior of the transportation system. We test the proposed system on the road network of the central terminal area of the Los Angeles International Airport and demonstrate that the integrated traffic simulation-prediction system can reproduce the real world traffic flow with low relative root mean square errors especially for high volume links and can be used to simulate the behavior of real world traffic scenarios.