hh.sePublications
Change search
Link to record
Permanent link

Direct link
BETA
Publications (5 of 5) Show all publications
Carpatorea, I., Nowaczyk, S., Rögnvaldsson, T. & Lodin, J. (2017). Features extracted from APPES to enable the categorization of heavy-duty vehicle drivers. In: 2017 Intelligent Systems Conference (IntelliSys): . Paper presented at Intelligent Systems Conference (IntelliSys 2017), London, United Kingdom, 7-8 September, 2017 (pp. 476-481).
Open this publication in new window or tab >>Features extracted from APPES to enable the categorization of heavy-duty vehicle drivers
2017 (English)In: 2017 Intelligent Systems Conference (IntelliSys), 2017, p. 476-481Conference paper, Published paper (Refereed)
Abstract [en]

Improving the performance of systems is a goal pursued in all areas and vehicles are no exception. In places like Europe, where the majority of goods are transported over land, it is imperative for fleet operators to have the best efficiency, which results in efforts to improve all aspects of truck operations. We focus on drivers and their performance with respect to fuel consumption. Some of relevant factors are not accounted for inavailable naturalistic data, since it is not feasible to measure them. An alternative is to set up experiments to investigate driver performance but these are expensive and the results are not always conclusive. For example, drivers are usually aware of the experiment’s parameters and adapt their behavior.

This paper proposes a method that addresses some of the challenges related to categorizing driver performance with respect to fuel consumption in a naturalistic environment. We use expert knowledge to transform the data and explore the resulting structure in a new space. We also show that the regions found in APPES provide useful information related to fuel consumption. The connection between APPES patterns and fuel consumption can be used to, for example, cluster drivers in groups that correspond to high or low performance. © 2017 IEEE

Keywords
truck driver, driver performance, driver behavior, fuel economy, heavy-duty vehicle performance
National Category
Computer Sciences
Identifiers
urn:nbn:se:hh:diva-33232 (URN)10.1109/IntelliSys.2017.8324336 (DOI)978-1-5090-6435-9 (ISBN)978-1-5090-6436-6 (ISBN)
Conference
Intelligent Systems Conference (IntelliSys 2017), London, United Kingdom, 7-8 September, 2017
Available from: 2017-02-08 Created: 2017-02-08 Last updated: 2018-04-03Bibliographically approved
Carpatorea, I. (2017). Methods to quantify and qualify truck driver performance. (Licentiate dissertation). Halmstad: Halmstad University Press
Open this publication in new window or tab >>Methods to quantify and qualify truck driver performance
2017 (English)Licentiate thesis, comprehensive summary (Other academic)
Abstract [en]

Fuel consumption is a major economical component of vehicles, particularly for heavy-duty vehicles. It is dependent on many factors, such as driver and environment, and control over some factors is present, e.g. route, and we can try to optimize others, e.g. driver. The driver is responsible for around 30% of the operational cost for the fleet operator and is therefore important to have efficient drivers as they also inuence fuel consumption which is another major cost, amounting to around 40% of vehicle operation. The difference between good and bad drivers can be substantial, depending on the environment, experience and other factors.

In this thesis, two methods are proposed that aim at quantifying and qualifying driver performance of heavy duty vehicles with respect to fuel consumption. The first method, Fuel under Predefined Conditions (FPC), makes use of domain knowledge in order to incorporate effect of factors which are not measured. Due to the complexity of the vehicles, many factors cannot be quantified precisely or even measured, e.g. wind speed and direction, tire pressure. For FPC to be feasible, several assumptions need to be made regarding unmeasured variables. The effect of said unmeasured variables has to be quantified, which is done by defining specific conditions that enable their estimation. Having calculated the effect of unmeasured variables, the contribution of measured variables can be estimated. All the steps are required to be able to calculate the influence of the driver. The second method, Accelerator Pedal Position - Engine Speed (APPES) seeks to qualify driver performance irrespective of the external factors by analyzing driver intention. APPES is a 2D histogram build from the two mentioned signals. Driver performance is expressed, in this case, using features calculated from APPES.

The focus of first method is to quantify fuel consumption, giving us the possibility to estimate driver performance. The second method is more skewed towards qualitative analysis allowing a better understanding of driver decisions and how they affect fuel consumption. Both methods have the ability to give transferable knowledge that can be used to improve driver's performance or automatic driving systems.

Throughout the thesis and attached articles we show that both methods are able to operate within the specified conditions and achieve the set goal.

Place, publisher, year, edition, pages
Halmstad: Halmstad University Press, 2017. p. 23
Series
Halmstad University Dissertations ; 28
Keywords
Driver performance, heavy-duty vehicle, fuel economy, fuel consumption, fuel prediction, truck driver
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:hh:diva-33229 (URN)978-91-87045-59-2 (ISBN)978-91-87045-58-5 (ISBN)
Presentation
2017-02-10, Wigforssalen, Visionen, Kristian IV:s väg 3, Halmstad, 13:40 (English)
Opponent
Supervisors
Available from: 2017-02-08 Created: 2017-02-07 Last updated: 2018-01-13Bibliographically approved
Carpatorea, I., Slawomir, N., Rögnvaldsson, T., Elmer, M. & Lodin, J. (2016). Learning of Aggregate Features for Comparing Drivers Based on Naturalistic Data. In: Lisa O’Conner (Ed.), Proceedings: 2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA). Paper presented at IEEE 15th International Conference on Machine Learning and Applications, ICMLA 2016, Anaheim, United States, 18-20 December, 2016 (pp. 1067-1072). Los Alamitos, CA: IEEE Computer Society
Open this publication in new window or tab >>Learning of Aggregate Features for Comparing Drivers Based on Naturalistic Data
Show others...
2016 (English)In: Proceedings: 2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA) / [ed] Lisa O’Conner, Los Alamitos, CA: IEEE Computer Society, 2016, p. 1067-1072Conference paper, Published paper (Refereed)
Abstract [en]

Fuel used by heavy duty trucks is a major cost for logistics companies, and therefore improvements in this area are highly desired. Many of the factors that influence fuel consumption, such as the road type, vehicle configuration or external environment, are difficult to influence. One of the most under-explored ways to lower the costs is training and incentivizing drivers. However, today it is difficult to measure driver performance in a comprehensive way outside of controlled, experimental setting.

This paper proposes a machine learning methodology for quantifying and qualifying driver performance, with respect to fuel consumption, that is suitable for naturalistic driving situations. The approach is a knowledge-based feature extraction technique, constructing a normalizing fuel consumption value denoted Fuel under Predefined Conditions (FPC), which captures the effect of factors that are relevant but are not measured directly.

The FPC, together with information available from truck sensors, is then compared against the actual fuel used on a given road segment, quantifying the effects associated with driver behavior or other variables of interest. We show that raw fuel consumption is a biased measure of driver performance, being heavily influenced by other factors such as high load or adversary weather conditions, and that using FPC leads to more accurate results. In this paper we also show evaluation the proposed method using large-scale, real-world, naturalistic database of heavy-duty vehicle operation.

Place, publisher, year, edition, pages
Los Alamitos, CA: IEEE Computer Society, 2016
Keywords
data mining, expert features, heavy-duty vehicle, vehicle driver, truck driver, driver classification, feature extraction
National Category
Computer Sciences Vehicle Engineering Transport Systems and Logistics Infrastructure Engineering Applied Psychology
Identifiers
urn:nbn:se:hh:diva-33078 (URN)10.1109/ICMLA.2016.0194 (DOI)000399100100185 ()2-s2.0-85015439319 (Scopus ID)978-1-5090-6166-2 (ISBN)
Conference
IEEE 15th International Conference on Machine Learning and Applications, ICMLA 2016, Anaheim, United States, 18-20 December, 2016
Available from: 2017-01-26 Created: 2017-01-16 Last updated: 2018-01-13Bibliographically approved
Carpatorea, I., Nowaczyk, S., Rögnvaldsson, T. & Elmer, M. (2014). APPES Maps as Tools for Quantifying Performance of Truck Drivers. In: Robert Stahlbock & Gary M. Weiss (Ed.), Proceedings of the 2014 International Conference on Data Mining, DMIN'14: . Paper presented at The 10th International Conference on Data Mining, DMIN´14, July 21-24, Las Vegas, Nevada, USA (pp. 10-16). USA: CSREA Press
Open this publication in new window or tab >>APPES Maps as Tools for Quantifying Performance of Truck Drivers
2014 (English)In: Proceedings of the 2014 International Conference on Data Mining, DMIN'14 / [ed] Robert Stahlbock & Gary M. Weiss, USA: CSREA Press, 2014, p. 10-16Conference paper, Published paper (Refereed)
Abstract [en]

Understanding and quantifying drivers’ influence on fuel consumption is an important and challenging problem. A number of commonly used approaches are based on collection of Accelerator Pedal Position - Engine Speed (APPES) maps. Up until now, however, most publicly available results are based on limited amounts of data collected in experiments performed under well-controlled conditions. Before APPES maps can be considered a reliable solution, there is a need to evaluate the usefulness of those models on a larger and more representative data.

In this paper we present analysis of APPES maps that were collected, under actual operating conditions, on more than 1200 trips performed by a fleet of 5 Volvo trucks owned by a commercial transporter in Europe. We use Gaussian Mixture Models to identify areas of those maps that correspond to different types of driver behaviour, and investigate how the parameters of those models relate to variables of interest such as vehicle weight or fuel consumption.

Place, publisher, year, edition, pages
USA: CSREA Press, 2014
Keywords
data mining, truck drivers, fuel, fuel consumptions, histograms
National Category
Information Systems
Identifiers
urn:nbn:se:hh:diva-27411 (URN)9781601323132 (ISBN)
Conference
The 10th International Conference on Data Mining, DMIN´14, July 21-24, Las Vegas, Nevada, USA
Projects
Learning Fleet
Available from: 2015-01-06 Created: 2015-01-06 Last updated: 2018-01-11Bibliographically approved
Carpatorea, I., Nowaczyk, S., Rögnvaldsson, T. & Elmer, M. (2014). Towards Data Driven Method for Quantifying Performance of Truck Drivers. In: The SAIS Workshop 2014 Proceedings: . Paper presented at 28th Annual workshop of the Swedish Artificial Intelligence Society (SAIS), Stockholm, Sweden, May 22-23, 2014 (pp. 133-142). Swedish Artificial Intelligence Society (SAIS)
Open this publication in new window or tab >>Towards Data Driven Method for Quantifying Performance of Truck Drivers
2014 (English)In: The SAIS Workshop 2014 Proceedings, Swedish Artificial Intelligence Society (SAIS) , 2014, p. 133-142Conference paper, Published paper (Refereed)
Abstract [en]

Understanding factors that influence fuel consumption is a very important task both for the OEMs in the automotive industry and for their customers. There is a lot of knowledge already available concerning this topic, but it is poorly organized and often more anecdotal than rigorously verified. Nowadays, however, rich datasets from actual vehicle usage are available and a data-mining approach can be used to not only validate earlier hypotheses, but also to discover unexpected influencing factors.

In this paper we particularly focus on analyzing how behavior of drivers affects fuel consumption. To this end we introduce a concept of “Base Value”, a number that incorporates many constant, unmeasured factors. We show our initial results on how it allows us to categorize driver’s performance more accurately than previously used methods. We present a detailed analysis of 32 trips by Volvo trucks that we have selected from a larger database. Those trips have a large overlap in the route traveled, of over 100 km, and at the same time exhibit different driver and fuel consumption characteristics.

Place, publisher, year, edition, pages
Swedish Artificial Intelligence Society (SAIS), 2014
Keywords
truck driver, fuel consumption
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:hh:diva-27596 (URN)
Conference
28th Annual workshop of the Swedish Artificial Intelligence Society (SAIS), Stockholm, Sweden, May 22-23, 2014
Available from: 2015-01-26 Created: 2015-01-26 Last updated: 2018-01-11Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0002-8797-5112

Search in DiVA

Show all publications