Modelling the performance of delivery vehicles across urban micro-regions to accelerate the transition to cargo-bike logistics

TL;DR

This paper models urban delivery vehicle performance to promote cargo-bike adoption, using machine learning on datasets and urban context features to evaluate environmental and business impacts.

Contribution

It introduces datasets and models that analyze how urban micro-region characteristics influence delivery times, aiding cargo-bike logistics transition.

Findings

Urban context significantly predicts delivery performance.

Machine learning models can evaluate cargo-bike viability.

Urban micro-region features improve delivery time predictions.

Abstract

Light goods vehicles (LGV) used extensively in the last mile of delivery are one of the leading polluters in cities. Cargo-bike logistics has been put forward as a high impact candidate for replacing LGVs, with experts estimating over half of urban van deliveries being replaceable by cargo bikes, due to their faster speeds, shorter parking times and more efficient routes across cities. By modelling the relative delivery performance of different vehicle types across urban micro-regions, machine learning can help operators evaluate the business and environmental impact of adding cargo-bikes to their fleets. In this paper, we introduce two datasets, and present initial progress in modelling urban delivery service time (e.g. cruising for parking, unloading, walking). Using Uber's H3 index to divide the cities into hexagonal cells, and aggregating OpenStreetMap tags for each cell, we show that urban context is a critical predictor of delivery performance.