Modeling Drivers’ Route Choices and Route Compliance when Interacting with an Eco-Routing Navigation System
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 drivers’ route choices and compliance behaviors when interacting with eco-routing navigation systems, addressing a gap in understanding whether and why drivers adopt energy-efficient routes over traditional time- or distance-minimizing options. Motivated by the potential of eco-routing to reduce transportation-related greenhouse gas emissions, the research aims to identify factors influencing route selection and adherence, thereby informing the design of more effective navigation systems. The researchers developed a smartphone-based eco-routing application that recommended three route options: eco (least energy consumption), fast (shortest travel time), and balanced. Forty-three participants used the app for two weeks, recording data for 737 valid trips. The study employed mixed model analyses to examine factors affecting route choice and compliance, treating driver demographics, subjective trip data, and route information as fixed effects and individual drivers as random effects. To predict route choice behavior, which was treated as a multi-label problem, the authors applied a Multi-label Random Forests (MLRF) model using 14 input variables derived from driver characteristics, subjective data, and route information. Results indicated that drivers selected the eco-route in approximately 78.6% of instances. Mixed model analyses revealed that drivers were more likely to choose the eco-route for shorter trips with higher per-mile gas consumption. Additionally, the recommendation sequence significantly influenced choice, with drivers preferring the eco-route when it was presented first. The MLRF model achieved an overall accuracy of 88.3% and an AUC of 0.86, outperforming other multi-label classifiers. Route information variables, such as distance saving and recommendation sequence, were the most significant predictors. Regarding compliance, participants followed the recommended route in 56.7% of trips on average. Drivers who selected eco or fast routes were more likely to comply than those choosing balanced routes. Furthermore, compliance rates were higher when drivers had three or more household passengers compared to driving alone or with one passenger. The findings suggest that eco-routing systems can effectively guide drivers toward energy-efficient choices, particularly when prioritized in recommendations and used for short, high-consumption trips. The high predictive accuracy of the MLRF model demonstrates its utility in modeling complex route choice behaviors. These insights provide actionable design recommendations for navigation systems to enhance driver adoption and compliance with eco-routes, contributing to more sustainable transportation practices.
Key finding
Drivers selected the eco route in approximately 78.6% of instances and complied with recommended routes 56.7% of the time, with selection influenced by trip distance, fuel consumption, and recommendation sequence, while compliance was higher with 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).
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | rosap | — | — | 2 | 2026-05-23 |
| archive | success | — | — | — | 1 | 2026-05-23 |
| extract | success | cached | — | — | 2 | 2026-06-10 |
| clean | success | — | — | — | 1 | 2026-06-01 |
| chunk | success | — | — | — | 1 | 2026-06-01 |
| embed | success | — | — | — | 1 | 2026-06-02 |
| enrich | success | — | — | — | 1 | 2026-05-23 |
| promote | success | — | — | — | 1 | 2026-05-23 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 3 | 2026-06-10 |
| tag | success | vector_similarity | — | — | 24 | 2026-06-11 |
| verify | success | — | — | — | 2 | 2026-06-10 |
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.
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