Deep Inverse Reinforcement Learning for Route Choice Modeling

06/18/2022
by   Zhan Zhao, et al.
0

Route choice modeling, i.e., the process of estimating the likely path that individuals follow during their journeys, is a fundamental task in transportation planning and demand forecasting. Classical methods generally adopt the discrete choice model (DCM) framework with linear utility functions and high-level route characteristics. While several recent studies have started to explore the applicability of deep learning for travel choice modeling, they are all path-based with relatively simple model architectures and cannot take advantage of detailed link-level features. Existing link-based models, while theoretically promising, are generally not as scalable or flexible enough to account for the destination characteristics. To address these issues, this study proposes a general deep inverse reinforcement learning (IRL) framework for link-based route choice modeling, which is capable of incorporating high-dimensional features and capturing complex relationships. Specifically, we adapt an adversarial IRL model to the route choice problem for efficient estimation of destination-dependent reward and policy functions. Experiment results based on taxi GPS data from Shanghai, China validate the improved performance of the proposed model over conventional DCMs and other imitation learning baselines, even for destinations unseen in the training data. We also demonstrate the model interpretability using explainable AI techniques. The proposed methodology provides a new direction for future development of route choice models. It is general and should be adaptable to other route choice problems across different modes and networks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/02/2019

A tutorial on recursive models for analyzing and predicting path choice behavior

The problem at the heart of this tutorial consists in modeling the path ...
research
05/08/2020

Modeling Route Choice with Real-Time Information: Comparing the Recursive and Non-Recursive Models

We study the routing policy choice problems in a stochastic time-depende...
research
08/13/2018

Generalized Multivariate Extreme Value Models for Explicit Route Choice Sets

This paper analyses a class of route choice models with closed-form prob...
research
05/18/2023

Massively Scalable Inverse Reinforcement Learning in Google Maps

Optimizing for humans' latent preferences is a grand challenge in route ...
research
05/22/2020

Experiments on route choice set generation using a large GPS trajectory set

Several route choice models developed in the literature were based on a ...
research
12/19/2019

Online route choice modeling for Mobility-as-a-Service networks with non-separable, congestible link capacity effects

With the prevalence of MaaS systems, route choice models need to conside...
research
07/07/2020

A Dynamic Choice Model with Heterogeneous Decision Rules: Application in Estimating the User Cost of Rail Crowding

Crowding valuation of subway riders is an important input to various sup...

Please sign up or login with your details

Forgot password? Click here to reset