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

Bao, Shan · 2020 · ROSA P / University of Michigan. Center for Connected and Automated Transportation

archive: archived pipeline: cataloged verified

Get this paper ↗ (full text — opens at the source; we link to it, we don't host it)

Summary

This study investigates driver behavior regarding route selection and compliance when interacting with an eco-routing navigation system. Motivated by the transportation sector’s significant contribution to U.S. greenhouse gas emissions, the research aims to understand how drivers choose between energy-efficient routes and those optimized for speed or balance, and whether they adhere to these recommendations. The primary objectives were to predict preferred routes from system recommendations and explore the decision-making factors influencing route selection and compliance. The methodology involved developing a cellphone-based eco-routing application that provided drivers with up to three route options (eco, fast, balanced) along with estimated fuel consumption and travel times. Data were collected through naturalistic driving experiments with 43 participants over a two-week period, resulting in 738 valid trips. GPS data were corrected using Google API to calculate the overlap between actual driving paths and recommended routes. The analysis employed mixed models to interpret route choices and compliance, while Multi-label Random Forests (MLRF) were used to predict driver behavior. Results indicated that drivers most frequently selected the "fast" route (83.4% probability), followed by the "eco" route (78.57%), and the "balanced" route (70.7%). Mixed model analyses revealed that drivers were more likely to choose the eco route if it had a shorter distance and higher gas consumption per mile. Additionally, prioritizing the eco route in the recommendation sequence significantly increased its selection likelihood. Regarding compliance, the average probability of following the selected route was 56.7%. Drivers who chose eco or fast routes were more likely to fully adhere to the recommended path than those who chose balanced routes. Furthermore, compliance increased when drivers had three or more household passengers compared to driving alone or with one passenger. The MLRF model achieved a testing accuracy of 79.3%, with route information variables showing the highest impact on predictions, while demographic factors showed no obvious relationship. The study concludes that eco-routing systems can influence driver behavior, particularly when eco routes are prioritized or offer distance advantages. Compliance is higher for eco and fast routes and is positively correlated with the number of household passengers. These findings suggest that interface design, such as recommendation ordering, and contextual factors like passenger count, are critical for maximizing the adoption of eco-friendly driving behaviors.

Key finding

Drivers were more likely to select the eco route when its distance was shorter and gas consumption per mile was higher, and they complied with recommended routes significantly more often when traveling with three or more household passengers.

Methodology

naturalistic

Sample size: 39

Provenance

The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed. Discovered via bulk_ingest_rosap on 2026-05-23 (6 acquisition events logged).

Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• eco driving

Information type

What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).

• Theoretical Contribution: computational model