Coevolution of the Features of the Dynamics of the Accelerator Pedal and Hyperparameters of the Classifier for Emergency Braking Detection

Created by W.Langdon from gp-bibliography.bib Revision:1.4420

@Article{Podusenko:2018:Actuators,
  author =       "Albert Podusenko and Vsevolod Nikulin and 
                 Ivan Tanev and Katsunori Shimohara",
  title =        "Coevolution of the Features of the Dynamics of the
                 Accelerator Pedal and Hyperparameters of the Classifier
                 for Emergency Braking Detection",
  journal =      "Actuators",
  year =         "2018",
  volume =       "7",
  number =       "3",
  pages =        "39",
  month =        sep,
  note =         "Special Issue Novel Braking Control Systems",
  keywords =     "genetic algorithms, genetic programming, emergency
                 braking system, cooperative coevolution, evolutionary
                 computation, driving assisting agent, extreme gradient
                 boosting",
  ISSN =         "2076-0825",
  URL =          "http://www.mdpi.com/journal/actuators",
  URL =          "http://www.mdpi.com/2076-0825/7/3",
  URL =          "http://www.mdpi.com/2076-0825/7/3/39/pdf",
  DOI =          "doi:10.3390/act7030039",
  size =         "18 pages",
  abstract =     "We investigate the feasibility of inferring the
                 intention of the human driver of road motor vehicles to
                 apply emergency braking solely by analysing the
                 dynamics of lifting the accelerator pedal. Focusing on
                 building the system that reliably classifies the
                 emergency braking situations, we employed evolutionary
                 algorithms (EA) to coevolve both (i) the set of
                 features that optimally characterize the movement of
                 accelerator pedal and (ii) the values of the
                 hyperparameters of the classifier. The experimental
                 results demonstrate the superiority of the
                 coevolutionary approach over the analogical approaches
                 that rely on an a priori defined set of features and
                 values of hyperparameters. By using simultaneous
                 evolution of both features and hyperparameters, the
                 learned classifier inferred the emergency braking
                 situations in previously unforeseen dynamics of the
                 accelerator pedal with an accuracy of about 95percent.
                 We consider the obtained results as a step towards the
                 development of a brake-assisting system, which would
                 perceive the dynamics of the accelerator pedal in a
                 real-time and in case of a foreseen emergency braking
                 situation, would apply the brakes automatically well
                 before the human driver would have been able to apply
                 them.",
  notes =        "MDPI",
}

Genetic Programming entries for Albert Podusenko Vsevolod Nikulin Ivan T Tanev Katsunori Shimohara

Citations