Modeling Drivers’ Route Choices and Route Compliance when Interacting with an Eco-Routing Navigation System

Eco-routing navigation systems have become a promising application to reduce fuel consumption by optimizing driving routes through energy efficiency prioritization instead of solely travel time or distance minimization. Current studies have put limited efforts to investigating whether and why drivers will choose and comply with the eco route recommended by eco-routing navigation systems. Thus, to fill this research gap, this study developed a smartphone-based eco-routing navigation application (app) and collected naturalistic driving data to examine and model drivers’ route choices and compliance behavior when interacting with the recommended route. It was observed that drivers chose the eco-routing option with the most energy-saving feature in approximately 78.6% of all the selected routes in this study. To further explore the impacting factors on the eco-routing choice, mixed model analyses were conducted. The results showed that drivers were more likely to select the eco route when this trip had shorter distance and higher per mile gas consumption. It was also found that giving priority to recommend the eco route could guide drivers to choose the eco route. Since drivers’ route choices belonged to the multi-label problem, this study applied a Multi-label random forests (MLRF) model to predict route choice behavior. In this model, independent variables were derived from three aspects, including driver characteristics, subjective data, and route information. The overall accuracy and AUC (the area under the receiver operating characteristic curve) of this MLRF model were 88.3% and 0.86 respectively. Overall, the average proportion that participants complied with the recommended route while driving was 56.7%. Mixed model analyses found that when drivers chose the eco or fast routes, they were more likely to fully follow the recommended route. Compared with driving alone or with only one household passenger, drivers preferred to comply with the recommended route when there were three or more household passengers. The findings of this study can help to understand drivers’ decision making in route planning and therefore to improve eco-routing navigation system designs, which will be beneficial to the eco-friendly transportation system.

• Record URL:
  • https://dx.doi.org/10.2139/ssrn.4046357
• Record URL:
  • https://rosap.ntl.bts.gov/view/dot/73482
• Supplemental Notes:
  • This document was sponsored by the U.S. Department of Transportation, University Transportation Centers Program.
• Corporate Authors:

  Center for Connected and Automated Transportation

  University of Michigan Transportation Research Institute
  Ann Arbor, MI  United States  48109

  Department of Energy

  1000 Independence Avenue, SW
  Washington, DC  United States  20585

  Office of the Assistant Secretary for Research and Technology

  University Transportation Centers Program
  Department of Transportation
  Washington, DC  United States  20590

  Argonne National Laboratories

  Lemont, IL  United States 
• Authors:
  • Yu, Bo
  • Bao, Shan
  • Li, Zeyang
  • Rask, Eric M
  • Liu, Henry
  • Sayer, Jim
• Publication Date: 2022-3

Language

• English

Media Info

• Media Type: Digital/other
• Features: Figures; References; Tables;
• Pagination: 21p

Subject/Index Terms

• TRT Terms: Automatic data collection systems; Behavior; Decision making; Drivers; Ecodriving; Mobile applications; Navigation systems; Route choice
• Subject Areas: Data and Information Technology; Environment; Highways; Safety and Human Factors; Vehicles and Equipment;

Filing Info

• Accession Number: 01910689
• Record Type: Publication
• Files: UTC, NTL, TRIS, USDOT
• Created Date: Mar 4 2024 9:41AM