Utilizing School Bus Routes to Deliver Meals to Families in Need
This report summarizes the results of a 3-month project aimed at coupling artificial intelligence (AI)-based routing and scheduling technology with machine learning to demonstrate an initial solution to the problem of remote delivery of school meals to students in need, and jumpstarting research in this area. With the onset of the COVID-19 pandemic, K-12 school meal programs have been unexpectedly disrupted, raising the need for alternative remote delivery processes. Working together with Allies for Children, a local non-profit organization, and the Penn Hills School District, the authors developed intelligent delivery-location selection along with initial route optimization algorithms and applied them to produce a set of vehicle delivery routes aimed at providing meals to those students in greatest need, while satisfying remote food delivery and social distancing constraints. Delivery vehicles began driving these routes as Penn Hill’s summer school delivery program in July 2020. As of early August, over 5000 school meals have been delivered, and plans are in place to transition this remote meal delivery program into the fall. In this report, the authors summarize the problem, their technical approach and results obtained to date.
- Record URL:
- Dataset URL:
- Dataset URL:
- Record URL:
-
Supplemental Notes:
- This document was sponsored by the U.S. Department of Transportation, University Transportation Centers Program. Supporting datasets available at: http://www.ozone.ri.cmu.edu/icll-data-repository/remote-meal-delivery-data-repository/
-
Corporate Authors:
Mobility21 (University Transportation Center)
Heinz College, Carnegie Mellon University
5000 Forbes Ave, Hamburg Hall
Pittsburgh, PA United States 15213-3890Office of the Assistant Secretary for Research and Technology
University Transportation Centers Program
Department of Transportation
Washington, DC United States 20590 -
Authors:
- Smith, Stephen F
- 0000-0002-7053-3166
- Lightman, Karen
- Rubinstein, Zachary B
- 0000-0002-6344-8692
- Li, Ashley
- 0000-0001-7211-2018
- Publication Date: 2020-9
Language
- English
Media Info
- Media Type: Digital/other
- Edition: Final Research Report
- Features: Appendices; Figures; Maps; Photos; References; Tables;
- Pagination: 11p
Subject/Index Terms
- TRT Terms: Algorithms; COVID-19; Delivery service; Food; Low income groups; Machine learning; Optimization; Routes and routing; Schedules and scheduling; School buses; Students
- Geographic Terms: Pittsburgh (Pennsylvania)
- Subject Areas: Planning and Forecasting; Public Transportation; Society;
Filing Info
- Accession Number: 01752516
- Record Type: Publication
- Contract Numbers: 69A3551747111
- Files: UTC, NTL, TRIS, ATRI, USDOT
- Created Date: Sep 22 2020 10:45AM