Real‐time predictive eco‐driving assistance considering road geometry and long‐range radar measurements
DOI: 10.1049/itr2.12047
archive: archived pipeline: cataloged verified
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This paper presents the development and evaluation of a real-time predictive eco-driving assistance system designed to reduce fuel consumption and CO₂ emissions in road transport. Motivated by the need to decarbonize the transport sector, which has seen rising emissions despite reductions in other industries, the authors propose a system that coaches drivers toward energy-efficient behaviors. Unlike previous systems that rely solely on driver feedback or pre-computed profiles, this system utilizes real-time data from GPS and long-range automotive radar to account for upcoming road geometry and the motion of preceding vehicles. The system aims to provide general-purpose assistance applicable to various driving scenarios, including urban, rural, and highway conditions, while respecting individual driver preferences for acceleration, speed, and following distances. The system architecture comprises three layers: Perception, Decision, and Action. The Perception layer gathers data from a GPS unit, a front-mounted Doppler radar, and the vehicle’s Electronic Control Unit (ECU) to determine vehicle position, road curvature, and the range and relative velocity of lead vehicles. The Decision layer employs a Model Predictive Control (MPC) scheme to solve a non-linear optimization problem in real-time. This optimization minimizes a weighted sum of fuel consumption and deviations from driver preferences, using a fourth-order polynomial fuel consumption model derived from empirical data. The Action layer displays the recommended speed profile to the driver via a visual human-machine interface (HMI) featuring an "eco-band" overlay on the speedometer. The system was implemented in both a fixed-base driving simulator and an on-road prototype, with the optimization solved at a rate of 2 Hz using the ACADO toolkit. The study evaluated the system’s effectiveness through a repeated-measures experiment with 36 participants in the driving simulator. Results indicated an overall fuel consumption reduction of 6.09%. Statistical analysis using repeated-measures ANOVA, adjusted for average speed, revealed that these improvements were significantly greater than those expected from speed reductions alone, suggesting that the system successfully promoted fuel-saving behaviors such as avoiding unnecessary braking. The fuel-efficiency gains were comparable to those observed in unassisted eco-driving but were achieved with improved travel times in motorway situations. Additionally, on-road testing demonstrated the technical feasibility of the system, validating the fuel consumption model against CANbus data and confirming the reliability of sensor data acquisition and real-time optimization performance. The significance of this work lies in its demonstration that predictive eco-driving assistance can effectively reduce fuel usage without compromising travel time, addressing a key barrier to user acceptance. By incorporating real-time environmental data and driver preferences, the system offers a more adaptable and practical solution than static feedback devices. The findings suggest that such systems can induce learning effects in drivers, promoting long-term adoption of eco-driving behaviors. The successful implementation of the system in both simulator and real-world settings highlights its potential for integration into existing vehicle drivetrains, contributing to broader efforts to meet future decarbonization targets in the transport sector.
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 | 2026-06-17 |
| archive | success | openalex | — | — | 5 | 2026-06-25 |
| extract | success | cached | — | — | 2 | 2026-06-25 |
| clean | success | clean | — | — | 1 | 2026-06-18 |
| chunk | success | chunk | — | — | 1 | 2026-06-18 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-18 |
| promote | success | — | — | — | 1 | 2026-06-17 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 1 | 2026-06-25 |
| tag | success | vector_similarity | — | — | 6 | 2026-06-18 |
| verify | success | — | — | — | 1 | 2026-06-26 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-25; 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: tool software