LESY-ECO: Learning System for Eco-driving Based on the Imitation
In this paper, the authors propose a learning method for eco-driving based on imitation. The system uses Data Envelopment Analysis (DEA) in order to calculate the driving efficiency from the point of view of the fuel consumption. The input and output parameters have been selected taking into account the Longitudinal Vehicle Dynamics Model. This technique allows the authors to notify the user about who is the most efficient driver close to him or her and to suggest the imitation of the behavior of such driver. The proposed method promotes learning by observation and imitation of efficient drivers in a practical rather than theoretical way such as attending eco-driving lessons. The DEA algorithm does not depend on the definition of a preconceived form of the data in order to calculate the efficiency. The DEA algorithm estimates the inefficiency of a particular DMU by comparing it to similar DMUs considered as efficient. This is very important due to the dynamic nature of the traffic. A validation experiment has been conducted with 10 participants who made 500 driving tests in Spain. The results show that combining eco-driving lessons with the proposed learning system, drivers achieve a very significant improvement on fuel saving (15.82%).
- Record URL:
-
Availability:
- Find a library where document is available. Order URL: http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=7284675&punumber%3D7284675%26filter%3DAND%28p_IS_Number%3A7297490%29%26pageNumber%3D2%26rowsPerPage%3D100&pageNumber=3&rowsPerPage=100
-
Supplemental Notes:
- Copyright © 2014, IEEE.
-
Corporate Authors:
Institute of Electrical and Electronics Engineers (IEEE)
3 Park Avenue, 17th Floor
New York, NY United States 10016-5997 -
Authors:
- Magaña, V Corcoba
- Organero, M Munoz
-
Conference:
- 2014 International Conference on Connected Vehicles and Expo (ICCVE)
- Location: Vienna , Austria
- Date: 2014-11-3 to 2014-11-7
- Publication Date: 2015
Language
- English
Media Info
- Media Type: Web
- Features: References;
- Pagination: pp 351-356
- Monograph Title: 2014 International Conference on Connected Vehicles and Expo (ICCVE)
Subject/Index Terms
- TRT Terms: Behavior; Drivers; Ecodriving; Fuel consumption; Learning; Vehicle dynamics
- Uncontrolled Terms: Data envelopment analysis
- Geographic Terms: Spain
- Subject Areas: Energy; Highways; Vehicles and Equipment;
Filing Info
- Accession Number: 01615675
- Record Type: Publication
- ISBN: 9781479967308
- Files: TRIS
- Created Date: Oct 31 2016 4:57PM