Route Choice Models

Ben‐Akiva, Moshe; Ramming, M. Scott; Bekhor, Shlomo

doi:10.1007/978-3-662-07809-9_2

Cited by 33 publications

(29 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Basic Route Choice Model and Data We considered a basic mathematical route choice model adapted from one of the common route choice models [33] in literature that serves as the baseline model.…”

Section: A Overviewmentioning

confidence: 99%

“…where the constant α b is 0.601 [33], and T is the travel time on the alternative route to a fixed destination after exiting the highway. We uniformly sampled 10,000 driving record samples from the probability distribution predicted by the baseline model for a highway segment with four exits, along with associated travel times for the alternative routes after exiting the highway through the available exits, for a fixed destination.…”

Section: A Overviewmentioning

confidence: 99%

See 1 more Smart Citation

Improving Route Choice Models by Incorporating Contextual Factors via Knowledge Distillation

Mukhopadhyay

Zhu

et al. 2019

2019 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Route Choice Models predict the route choices of travelers traversing an urban area. Most of the route choice models link route characteristics of alternative routes to those chosen by the drivers. The models play an important role in prediction of traffic levels on different routes and thus assist in development of efficient traffic management strategies that result in minimizing traffic delay and maximizing effective utilization of transport system. High fidelity route choice models are required to predict traffic levels with higher accuracy. Existing route choice models do not take into account dynamic contextual conditions such as the occurrence of an accident, the socio-cultural and economic background of drivers, other human behaviors, the dynamic personal risk level, etc. As a result, they can only make predictions at an aggregate level and for a fixed set of contextual factors. For higher fidelity, it is highly desirable to use a model that captures significance of subjective or contextual factors in route choice. This paper presents a novel approach for developing high-fidelity route choice models with increased predictive power by augmenting existing aggregate level baseline models with information on drivers' responses to contextual factors obtained from Stated Choice Experiments carried out in an Immersive Virtual Environment through the use of knowledge distillation.

show abstract

Section: A Overviewmentioning

confidence: 99%

Section: A Overviewmentioning

confidence: 99%

Improving Route Choice Models by Incorporating Contextual Factors via Knowledge Distillation

Mukhopadhyay

Zhu

et al. 2019

2019 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

show abstract

“…Ideally, the discrete choice approach should be employed for representation of parking choice in the model. Some researchers such as (Ben-Akiva et al [5]) have used discrete choice methods to develop sophisticated route choice models. They presented a route choice model for large-scale urban networks.…”

Section: Extension Of Agents' On-street Parkingmentioning

confidence: 99%

A Discrete Choice Approach to Define Individual Parking Choice Behaviour for the Parkagent Model

Khaliq

Janssens

2017

WIT Transactions on the Built Environment

View full text Add to dashboard Cite

PARKAGENT is an agent based model for simulating parking search in the city. In PARKAGENT, the agents choose a parking spot based on the expected number of free parking spaces, distance to destination and length of parking space. For a true representation of underlying parking choice behaviour of agents in PARKAGENT model, a behavioural model is required. Behavioural models are considered as the core of agent based simulations, therefore a behavioural model capable to exhibit parking choice process in PARKAGENT has been proposed in this paper. This model explains that parking choice is based on the principles of utility maximization. Several research studies have used discrete choice models to describe parking choice phenomena. Discrete choice models determine the utility associated with choice of services and products. It is assumed that individual make decisions rationally, it is very difficult to measure the actual utility associated with a parking space. For a realistic calculation of the utility, factors affecting parking choice such as (parking cost, distance to destination, etc.) are required. In this research, the choice of on-street parking is considered keeping in view the factors associated with the street situation (e.g. occupancy, security). The decision of an agent to choose a street for parking is based on the factors associated to street. The necessary data is collected through stated choice questionnaire. The collected data is analysed using a discrete choice model (multinomial logit model). The results indicate show that the identified attributes of streets significantly affect the parking choice behaviour of agents. Keywords: discrete choice model, agent based parking simulation model PARKAGENT, factors affecting on-street parking choice. INTRODUCTIONThe aim of urban mobility plans is to attain sustainable urban transport system that ensures accessibility and quality of urban environment. These goals can only be accomplished with the help of certain forecasting tools. These tools provide the assessment of the future situation and support in making well informed decisions. Traffic induced due to parking search has significantly grabbed the attention of policy makers. It is crucial to model parking behaviour of motorists, in order to identify the effect of change in parking behaviour on the overall travel behaviour of drivers. Understanding and modelling parking choice behaviour is essential for urban planning and decision making. It is necessary to find, measure and model all the relevant factors influencing individual parking choice behaviour and decision-making processes.Parking choice process involves decision making. An efficient parking model should represent drivers parking choice more accurately, therefore behavioural models are considered as the cornerstones of agent based simulations. The major challenge in developing an agent based parking simulation model is the realistic nature of the parking choice behaviour model. The concept of discrete choice modelling can be used to in...

show abstract

“…We focus on probabilistic route choice models, as empirical evidence (see, e.g., Ben-Akiva et al, 2004) has shown that only a small percentage of travelers choose the minimum distance, minimum travel time or minimum generalized cost paths where the path attributes (travel time, cost and etc) are obtained from a network model. The Multinomial Logit (MNL) model is a popular candidate for probabilistic route choice models.…”

Section: Path-size Logitmentioning

confidence: 99%

A dynamic traffic assignment model for highly congested urban networks

Ben‐Akiva

Gao

Wei

et al. 2012

Transportation Research Part C: Emerging Technologies

Self Cite

126

View full text Add to dashboard Cite

The management of severe congestion in complex urban networks calls for dynamic traffic assignment (DTA) models that can replicate real traffic situations with long queues and spillbacks. DynaMIT-P, a mesoscopic traffic simulation system, was enhanced and calibrated to capture the traffic characteristics in the city of Beijing, China. All demand and supply parameters were calibrated simultaneously using sensor counts and floating car travel time data. Successful calibration was achieved with the Path-size Logit route choice model, which accounted for overlapping routes. Furthermore, explicit representations of lane groups were required to properly model traffic delays and queues. A modified treatment of acceptance capacity was required to model the large number of short links in the transportation network (close to the length of one vehicle). In addition, even though bicycles and pedestrians were not explicitly modeled, their impacts on auto traffic were captured by dynamic road segment capacities.

show abstract

Route Choice Models

Cited by 33 publications

References 5 publications

Improving Route Choice Models by Incorporating Contextual Factors via Knowledge Distillation

Improving Route Choice Models by Incorporating Contextual Factors via Knowledge Distillation

A Discrete Choice Approach to Define Individual Parking Choice Behaviour for the Parkagent Model

A dynamic traffic assignment model for highly congested urban networks

Contact Info

Product

Resources

About