A Scoping Review of Energy-Efficient Driving Behaviors and Applied State-of-the-Art AI Methods
DOI: 10.3390/en17020500
archive: archived pipeline: cataloged verified
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This scoping review addresses the lack of comprehensive investigations into energy-efficient driving behaviors and the application of state-of-the-art artificial intelligence (AI) methods to optimize them. Motivated by the transportation sector’s significant contribution to greenhouse gas emissions, the study aims to identify key driving factors influencing energy consumption and evaluate the AI methodologies used to model these relationships. The authors seek to fill existing gaps by providing clear, user-friendly recommendations for ecological driving styles, which are often overlooked in favor of vehicle selection or route planning strategies. The researchers conducted a systematic literature search across four databases—ACM Digital Library, IEEE Xplore, Web of Science, and Scopus—excluding Google Scholar to ensure reproducibility and peer-reviewed quality. Using specific keywords related to AI, driving, and energy efficiency, they initially retrieved 682 articles. After removing duplicates and filtering for relevance through title, abstract, and full-text assessments, 37 articles were selected for detailed analysis. The review categorized the literature based on data sources, influencing factors, and applied AI models, distinguishing between prediction models and reinforcement learning frameworks. The analysis identified eleven key factors impacting driving energy efficiency, divided into behaviors controlled by drivers (speed, acceleration, deceleration, pedal usage, steering, gear, and engine parameters) and external conditions (distance, weather, traffic signals, and road parameters). Speed and acceleration were the most frequently analyzed variables. Data collection methods varied between simulation environments and real-world experiments using meters, Controller Area Networks (CANbus), On-Board Diagnostics (OBDs), smartphones, and additional sensors. Regarding AI methodologies, supervised and unsupervised learning algorithms, particularly linear regression, neural networks, and random forests, were predominantly used for fuel consumption prediction. Reinforcement learning frameworks were also employed to generate energy-saving driving behaviors in simulated environments. The review found that prediction models accounted for 64% of the studies, with linear regression being the most popular due to its interpretability. The study concludes that energy-efficient driving strategies can reduce fuel consumption by approximately 15% under various conditions. Based on the reviewed literature, the authors propose nine energy-efficient driving styles, including guidelines for vehicle parameter adjustment, scenario-specific recommendations, and subjective suggestions for drivers and employers. The findings highlight the effectiveness of AI in modeling complex driving behaviors and provide a structured overview of current methodologies, guiding future research toward more accurate, real-world applications of AI in reducing transportation emissions.
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.
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | OpenAlex-citations | — | — | 1 | 2026-06-20 |
| archive | success | openalex | — | — | 5 | 2026-06-26 |
| extract | success | cached | — | — | 2 | 2026-06-26 |
| clean | success | clean | — | — | 1 | 2026-06-20 |
| chunk | success | chunk | — | — | 1 | 2026-06-20 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-20 |
| promote | success | — | — | — | 1 | 2026-06-20 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 1 | 2026-06-26 |
| tag | success | vector_similarity | — | — | 6 | 2026-06-20 |
| verify | success | — | — | — | 1 | 2026-06-26 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-26; 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).
- Methodological Resource: dataset resource, tool software
- Theoretical Contribution: computational model