A neural network model for enhanced operation of midblock signalled pedestrian crossings

Glenn Lyons,John Hunt,Fraser Mcleod

doi:10.1016/s0377-2217(00)00232-0

Glenn Lyons, John Hunt + Show 1 more

Open Access

https://doi.org/10.1016/s0377-2217(00)00232-0

Copy DOI

Abstract

UK transport policy has shifted dramatically in recent years. The new policy direction to promote walking as an alternative to car for short trips. Midblock signalled pedestrian crossings are a common method of resolving the conflict between pedestrians and vehicles. This paper considers alternative operating strategies for midblock signalled pedestrian crossings that are more responsive to the needs of pedestrians without increasing the delay to motorists and freight traffic. A succession of artificial neural network (ANN) models is developed and factors influencing the performance of pedestrian gap acceptance models both in terms of accuracy and processing requirements are considered in detail. The paper concludes that a feedforward ANN using backpropagation can deliver a gap acceptance model with a high degree of accuracy with acceptable constraints.

Highlights

1.1 UK transport policy Until recently transport policy emphasised the role of the private car as a symbol of personal freedom
1.3 Alternative operating strategies for pedestrian crossing facilities The proposed alternative strategies are based on the concept that it is possible to identify, in advance, a sequence of vehicle arrivals at a midblock signalled pedestrian crossing which the average pedestrian would perceive as a crossing opportunity
This paper considers the use of a feedforward Artificial neural networks (ANNs) trained using backpropagation to develop an ANN gap acceptance model for pedestrian crossing opportunities

Summary

Introduction

1.1 UK transport policy Until recently transport policy emphasised the role of the private car as a symbol of personal freedom. The aims include reducing waiting times for pedestrians at traffic signals and giving them priority in the allocation of time at junctions where this supports more walking This improvement for pedestrians needs to be achieved without increasing delays (and costs) to essential road users. 1.3 Alternative operating strategies for pedestrian crossing facilities The proposed alternative strategies are based on the concept that it is possible to identify, in advance, a sequence of vehicle arrivals at a midblock signalled pedestrian crossing which the average pedestrian would perceive as a crossing opportunity This information can be applied to provide an operating strategy that is more responsive to pedestrian demand by providing an earlier change to pedestrian precedence than is possible currently. A pragmatic approach has been adopted whereby a succession of increasingly improved models are developed based on reasoned decisions concerning options, settings, parameters and forms of data representation for preceding models and their associated performance with the available data

Development of Gap Acceptance Models Using Site Data

Conclusion and Discussion

16 Actual Reject