Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Urban context and delivery performance: Modelling service time for cargo bikes and vans across diverse urban environments

Maxwell Schrader, Navish Kumar, Esben Sørig, Soonmyeong Yoon, Akash Srivastava, Kai Xu, Maria Astefanoaei, Nicolas Collignon

Abstract

Light goods vehicles (LGV) used extensively in the last mile of delivery are one of the leading polluters in cities. Cargo-bike logistics and Light Electric Vehicles (LEVs) have been put forward as a high impact candidate for replacing LGVs. Studies have estimated 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. However, the logistics sector suffers from a lack of publicly available data, particularly pertaining to cargo-bike deliveries, thus limiting the understanding of their potential benefits. Specifically, service time (which includes cruising for parking, and walking to destination) is a major, but often overlooked component of delivery time modelling. The aim of this study is to establish a framework for measuring the performance of delivery vehicles, with an initial focus on modelling service times of vans and cargo-bikes across diverse urban environments. We introduce two datasets that allow for in-depth analysis and modelling of service times of cargo bikes and use existing datasets to reason about differences in delivery performance across vehicle types. We introduce a modelling framework to predict the service times of deliveries based on urban context. We employ Uber's H3 index to divide cities into hexagonal cells and aggregate OpenStreetMap tags for each cell, providing a detailed assessment of urban context. Leveraging this spatial grid, we use GeoVex to represent micro-regions as points in a continuous vector space, which then serve as input for predicting vehicle service times. We show that geospatial embeddings can effectively capture urban contexts and facilitate generalizations to new contexts and cities. Our methodology addresses the challenge of limited comparative data available for different vehicle types within the same urban settings.

Urban context and delivery performance: Modelling service time for cargo bikes and vans across diverse urban environments

Abstract

Light goods vehicles (LGV) used extensively in the last mile of delivery are one of the leading polluters in cities. Cargo-bike logistics and Light Electric Vehicles (LEVs) have been put forward as a high impact candidate for replacing LGVs. Studies have estimated 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. However, the logistics sector suffers from a lack of publicly available data, particularly pertaining to cargo-bike deliveries, thus limiting the understanding of their potential benefits. Specifically, service time (which includes cruising for parking, and walking to destination) is a major, but often overlooked component of delivery time modelling. The aim of this study is to establish a framework for measuring the performance of delivery vehicles, with an initial focus on modelling service times of vans and cargo-bikes across diverse urban environments. We introduce two datasets that allow for in-depth analysis and modelling of service times of cargo bikes and use existing datasets to reason about differences in delivery performance across vehicle types. We introduce a modelling framework to predict the service times of deliveries based on urban context. We employ Uber's H3 index to divide cities into hexagonal cells and aggregate OpenStreetMap tags for each cell, providing a detailed assessment of urban context. Leveraging this spatial grid, we use GeoVex to represent micro-regions as points in a continuous vector space, which then serve as input for predicting vehicle service times. We show that geospatial embeddings can effectively capture urban contexts and facilitate generalizations to new contexts and cities. Our methodology addresses the challenge of limited comparative data available for different vehicle types within the same urban settings.
Paper Structure (36 sections, 2 equations, 5 figures, 16 tables)

This paper contains 36 sections, 2 equations, 5 figures, 16 tables.

Table of Contents

  1. Introduction
  2. Related works
  3. Urban delivery datasets
  4. Van deliveries in US cities: Amazon Last Mile Routing Research Challenge
  5. Amazon dataset overview
  6. Descriptive statistics of the Amazon dataset
  7. Cargo Bike Deliveries in London and Brussels: Pedal Me and Urbike datasets
  8. Pedal Me dataset overview
  9. Urbike dataset overview
  10. Analysing distance to the door and cruising for parking in cargo-bike datasets
  11. Comparison of Urbike and Pedal Me service-time datasets
  12. Discussion of cargo-bike and van data sets
  13. Overview of variation in service times across data sets
  14. Distinct Operational Profiles: Parcel Deliveries vs. Diverse Urban Logistics
  15. Limitations in data granularity
  16. ...and 21 more sections

Figures (5)

  • Figure 1: The probability of delivery service time within a hexagon lasting longer than 2.5, 5, and 10 minutes respectively in the Amazon van dataset. We show three hexagons (A-C) sampled from three different areas in Boston to illustrate the effect of urban context on service time. A has a median service time near the 5th quantile and is located in a residential neighborhood. B has a service time close to median and is located in a mixed use area. C, a hexagon with an expected service time near the 95th quantile, is in the Boston downtown.
  • Figure 2: Box plots of Amazon van service times by within-city cluster. The clusters are organized such that 1 has the highest mean service time and 4 the lowest. The top row is a summary of deliveries in Boston, Massachusetts and the bottom of Seattle, Washington.
  • Figure 3: Box plots representing the empirical cargo-bike service times across city clusters. The clusters are organized such that 1 has the highest median service time and 4 the lowest. The top row is a summary of delivery service times in London, United Kingdom and the bottom of Brussels, Belgium.
  • Figure 4: Display of neighbor H3 cells in Boston (892a3075d77ffff, 892a3075d3bffff) and Austin (89489e24d7bffff, 89489e248b7ffff) with visual similarity but disparate OSM tags.
  • Figure 5: Distribution of the count of building_house vs building_yes tags in the 6 cities of interest. Los Angeles, USA has a high frequency of 0 building_yes tags per hexagon.