Evaluation of the influence of terrain and traffic road conditions on the driver’s driving performances by applying machine learning

Abstract

In this paper, research is done in the influence of different terrain and traffic conditions on road sections on the driver?s driving performances, i.e. on the car energy efficiency and CO2 emission. A methodology aimed at determining to which extent unfavorable traffic and/or terrain conditions on a road section contribute to the driver?s worse driving performances, and also to determine when the driver?s aggressive driving style is responsible for greater fuel consumption and greater CO2 emission is proposed. In order to apply the proposed methodology, a research study was carried out in a cargo transportation company and 12 drives who drove the same vehicle on five different road sections were selected. As many as 284 014 of the instances of the data about the defined parameters of the road section and the driver?s driving style were collected, based on which and with the help of machine learning a prediction of the scores for the road section and the scores for the driver?s driving style was performed. The obtained results have shown that the proposed methodology is a useful tool for managers enabling them to simply and quickly determine potential room for increasing the energy efficiency of the vehicle fleet and decreasing CO2 emission.

Assessment of the driver's driving style using supervised machine learning

“…U tabeli 5 može se videti da se prosečne stvarne i projektovane ocene svih šest vozača podudaraju na jednu decimalu, a kod četiri vozača i na dve decimale. U radu [11] objedinjeni su podaci koji opisuju vožnje 12 različitih vozača na jednoj ruti, pa je obučavanje modela mašinskog učenja izvršeno nad jednim skupom podataka od 122 559 instanci, testiranje nad jednim skupom podataka od 61 279 instanci, dok je za predikciju ocene vozačevog stila vožnje korišćen jedan skup podataka od 48 588 instanci. U pomenutom radu obučavano je i testirano šest različitih modela, a najbolji rezultat pokazao je model baziran na algoritmu Random Forest, pa je predikcija ocene vozačevog stila vožnje izvršena uz pomoć ovog modela.…”

“…Fuzzy Logic System Type-2, FLS2) za utvrđivanje uticaja različitog stila vožnje profesionalnih vozača na potrošnju goriva, pri čemu su upotrebljeni sledeći parametri vožnje: broj obrtaja motora, ubrzanje/usporenje vozila i procenat pritiska papučice gasa. Navedeni parametri vožnje su, pored ostalih, upotrebljeni i u radu [11] za vrednovanje uticaja terenskih i saobraćajnih uslova puta na vozačeve performanse vožnje i na energetsku efikasnost vozila uz primenu mašinskog učenja. Pri tome, za ocenu vozačevog stila vožnje navedeni parametri snimljeni su samo na jednoj ruti.…”