Estimating a Toronto pedestrian route choice model using smartphone GPS data

This study examines the feasibility of using revealed preference GPS data collected through a smartphone-based travel survey and discrete choice modeling techniques to determine pedestrians' preferences towards street infrastructure, built environment, and land use. Smartphone GPS points were collected after 50 m of travel and had a horizontal spatial accuracy of 30 m or less. A path size logit model with stochastic route choice generation choice set was used for this model. The results of the model showed that distance, the number of turns, the number of signalized intersections, and distance along links with sidewalks on both sides of the street were significant variables in the route choice model. Turns are found to be equivalent to an additional 32 m, signalized intersections are equivalent to a reduction of 34 m, and travel along streets with sidewalks on both sides of the road is evaluated as 33% shorter than streets with other sidewalk conditions. While the dataset used for this study was relatively small (776 trip observations), these results are consistent with other pedestrian route choice studies which support the viability of using smartphone GPS data for future pedestrian route choice studies.