A Real-Time Planning Algorithm for Route Choice Behavior and Processes

Dynamic route guidance (DRG) is an ITS application targeted to reduce the prolonged daily periods of severe congestion. The success of such system relies on its ability to disseminate reliable pieces of information to travelers in real time. The predictive accuracy of disseminated information requires a realistic understanding and representation of drivers' behavior and more specifically their route choice decisions and processes. Accordingly, this research attempts to step out of the engineering borders to the psychological arena through adopting one of the most successful decision theories; decision field theory (DFT). The choice mechanism of DFT is based on the simulation of the evolution of decision-makers preferences through out the deliberation process reflecting a process-oriented modeling approach. This study presents a modeling framework for drivers' decision making process based on the theoretical foundation of DFT. Three scenarios are discussed that vary in the level of traveler information presented to the driver, namely; no information, descriptive information (congestion states) and prescriptive information (specific guidance). Due to the highly intertwined elements of the theory and resulting model framework, an overly simplified application is used for illustration purposes

Advance Traveller Information Systems (ATIS) are considered a promising tool to alleviate traffic congestion and improve road network performance. They provide real time traffic information and route recommendation to road users, in order to increase their ability to choose the best alternative path. Though such systems have reached a high technical standard, their actual impact in traffic pattern and network performance is controversial. The methodology used is based on a Multi Agent Simulation to model how the presence of information influences the driver's reactive behavior and the network efficiency. The case study is the well known network of the Braess' paradox and the specific aim is to find the proper route recommendation strategy to avoid that adding a new road to traffic network may result in increasing the total travel time. Through a software platform able to simulate a virtual road network, where single drivers interact with each other and with the spatial environment according to a defined behavior, that is their reaction to external outputs, two behavioral patterns will be simultaneously considered. The first refers to the driver's path choice among those available for a fixed origin-destination pair; the second refers, once the path is chosen, to the microscopic motion of each vehicle as a function of the leader vehicle along each link of the network. To simulate the presence of drivers equipped with ATIS system and drivers who are not, or equivalently to simulate different reactive behavior to the information provided, it has been used a variable “probability of feedback”. Pattern arrival vehicle flow can be varied together with speed and acceleration of the vehicles. The general purpose of the paper is to contribute to the analysis of the impact of ITS (Intelligent Transport Systems) technology in traffic pattern and network performance. The specific objective is modelling driver's behavior in road networks when real time traffic information is provided. The results show that a proper rate of provided information is able to reduce the effect of the Braess' paradox and that network performance increases when drivers' behavior is affected by their ability to see local traffic conditions.

Handling uncertainty in route choice models: From probabilistic to possibilistic approaches

An application of cumulative prospect theory to freeway drivers’ route choice behaviours

Feedback contents of previous information feedback strategies in advanced traveler information systems are almost real-time traffic information. Compared with real-time information, prediction traffic information obtained by a reliable and effective prediction algorithm has many undisputable advantages. In prediction information environment, a traveler is prone to making a more rational route-choice. For these considerations, a mean velocity prediction information feedback strategy (MVPFS) is presented. The approach adopts the autoregressive-integrated moving average model (ARIMA) to forecast short-term traffic flow. Furthermore, prediction results of mean velocity are taken as feedback contents and displayed on a variable message sign to guide travelers' route-choice. Meanwhile, discrete choice model (Logit model) is selected to imitate more appropriately travelers' route-choice behavior. In order to investigate the performance of MVPFS, a cellular automaton model with ARIMA is adopted to simulate a two-route scenario. The simulation shows that such innovative prediction feedback strategy is feasible and efficient. Even more importantly, this study demonstrates the excellence of prediction feedback ideology.

Route Choice Behavior Model with Guidance Information

Day-To-Day Route Choice Decision Simulation Based on Dynamic Feedback Information

An integrated Belief-Desire-Intention (BDI) modeling framework is proposed for human decision making and planning for evacuation scenarios, whose submodules are based on a Bayesian Belief Network (BBN), Decision-Field-Theory (DFT), and a Probabilistic Depth-First Search (PDFS) technique. A key novelty of the proposed model is its ability to represent both the human decision-making and decision-planning functions in a unified framework. To mimic realistic human behaviors, attributes of the BDI framework are reverse-engineered from human-in-the-loop experiments conducted in the Cave Automatic Virtual Environment (CAVE). The proposed modeling framework is demonstrated for a human's evacuation behaviors in response to a terrorist bomb attack. The simulated environment and agents (models of humans) conforming to the proposed BDI framework are implemented in AnyLogic® agent-based simulation software, where each agent calls external Netica BBN software to perform its perceptual processing function and Soar software to perform its real-time planning and decision-execution functions. The constructed simulation has been used to test the impact of several factors (e.g., demographics, number of police officers, information sharing via speakers) on evacuation performance (e.g., average evacuation time, percentage of casualties).

In developing countries like India, limited Intelligent Transportation Systems (ITS) infrastructure is available and it is difficult to generate real time traffic information for city wide or larger regions. On the other hand, cellular network is widely deployed in India covering major part of the road network. However, cellular network based positioning data have large location error (250-500 meters) and is not directly useful for edge level travel time or speed estimation. Also, penetration of GPS enabled vehicles/phones is very low in India to generate useful real time traffic information. In this simulation based study we use the map matching algorithm, proposed in [1], that operates on a series of position points having large location error to get accurate vehicle count for every edge, with time lag of about 10 minutes. Temporal extrapolation using exponential moving average is used to overcome the time lag. The vehicle count is then used to estimate edgewise vehicle flow and occupancy. Simulation results show the mean estimation error of less than 10%. Then, the edge level congestion estimation is done using volume-capacity ratio (V/C ratio) and mean error of less than 10% is observed. These results are encouraging as they show feasibility of using widely deployed cellular network for real time congestion level estimation. For edge level speed estimation, a subset of edges are chosen for infrastructure deployment using historical data of congestion levels observed on various edges in a road network. The edges with ITS infrastructure are used to learn the occupancy-speed relationship which is then spatially extrapolated to infrastructure-less edges using GPS probe data to enable travel speed estimation on all the edges in the road network. The simulation results show that speed estimation with ninety percentile error of less than 15% is achievable.

. Aiming at the characteristics of Electric Vehicles (EVs) combined with transportation and mobile load, and their charging and driving behaviors will interact with the traffic system and power grid system. On the basis of this, a route planning and charging navigation strategy for EVs based on real-time traffic information and grid information was presented in this paper. First, a dynamic traffic network model was established according to the time-varying feature of traffic information. And also, the road resistance model with road segment impedance and intersection node impedance was proposed depending on the attribute of urban roads. Furthermore, based on the establishment of traffic network model, distribution network model and single EV model, a multi-objective optimization function integrated with the road travel time, the charging station load and the quantity of vehicles entering into the station was determined, which was solved to recommend the optimal driving and charging paths by dynamic Dijkstra dynamic search algorithm. At last, the actual road network of a certain zone in Nanjing was selected as an example to analyze the spatial-temporal distribution of EV charging load, and evaluated the impact of its charging and driving on traffic network and distribution network. Simulation results demonstrate its effectiveness and feasibility.

Road network management under critical conditions is achievable by adopting technologies that trace vehicles and capture unsafety events to provide users with real time traffic information. Most common approaches used to acquire vehicle tracking data are based on video image processing algorithms and satellite navigation systems. However, many studies are increasingly focused on the emerging smartphone technologies for tracking vehicles. The aim of this study is to present a procedure for acquiring vehicle tracking data from smartphone sensors, supporting managers of transportation systems to take effective decisions on their networks, especially in conjunction with special events and/or critical road safety issues.

Vehicle Routing Problems (VRPs) are usually treated as static routing problem, since all the information is known before the routes been constructed. However, the real world VRPs are dynamic, where information relevant to the routing can change after the initial scheme has been done. This paper treats the dynamic VRPs with real time traffic information. We formulate the mathematic model of the VRPs, and propose a dynamic programming algorithm based on chaos optimization, whereas the route calculating module and dynamic programming module are introduced. Finally, the efficiency of the proposed algorithm is demonstrated by computer simulations.

Intelligent Transport System uses real time traffic information and thus in an urban environment the time delay in shifting patients to hospital is reduced increasing the possibility of saving life. Road traffic congestion plays a major obstruction for the ambulance from its location to the hospital.In the proposed system, traffic status is monitored by the Road Side Units (RSUs). For sharing the traffic information status, RSUs decides the route and guides the ambulance to move on the less congested path. During transition of the patient health parameters will be monitored in the ambulance and broadcasted to the medical consultant. On arrival of the patient to hospital necessary arrangements are made to receive the patient for further investigation and treatment.During transition, ambulance broadcasts for short path/shortest time to the destination. After realizing congestion in different routes to the destination, the ultimate path to encounter the congestion is to take shortest path using metro rail. Medical consultant arranges an ambulance to receive the patient from nearest metro station. On arrival of the patient to hospital, source ambulance receives a confirmation message.

The research of driver?s route choice behavior helps to increase utility of existed route network (especially city traffic network), and improve traffic conditions. From the point of macroscopic view, through discussing the time evolution pattern of driver's route choice behavior with the influence of dynamic traffic information upon the pattern, it is proved that the behavior of route choice is uncertain. So in designing traffic guiding system or traffic information system, the influence of disturbing factor should be taken into consideration to guarantee a balanced dynamic traffic distribution of the system.

Drivers' route choice model is essential in transportation software such as navigation, fleet management, and simulation, where the random utility models (RUM) have dominated for years. The authors investigate here whether machine learning (ML) models could be applied into this field, and whether these approaches outperform the traditional models in goodness‐of‐fit and prediction. The application framework and data structure are proposed, where the challenging problems lie in: (i) to pool data from multiple origin–destination pairs; and (ii) to interpret results for behaviour analysis. All RUM and ML models are applied in a real network. Results suggest that the random forest, one of the ML models, has satisfying performances with acceptable computation time, making it suitable for large network and real‐time analysis. This study shows that the ML models can be adopted for behaviour analysis, such as to prioritise the importance of variables, compute the elasticity, and forecast for scenarios. Future directions on combining the RUM and ML models are discussed.