Eilers, Mark and Möbus, Claus (2014) Discriminative Learning of Relevant Percepts for a Bayesian Autonomous Driver Model. ThinkMind // COGNITIVE 2014. pp. 19-25. ISSN 2308-4197

[img]
Preview


Volltext (3350Kb)
Official URL: http://www.thinkmind.org/index.php?view=article&ar...

Abstract

Models of the human driving behavior are essential for the rapid prototyping of assistance systems. Based on psychological studies, various percepts and measures have been proposed for the lateral and longitudinal control in driver models without demonstrating the generalizability of results to natural settings. In this paper, we present the learning of a probabilistic driver model. It represents and mimics the lateral and longitudinal human driving behavior on virtual highways by performing situation-adequate lane-following, car-following, and lane changing behavior. Because there is considerable uncertainty about the relevant percepts in natural driving behavior, we select hypothetically relevant percepts from the variety of possibilities based on their statistical relevance. This is a new approach to generate hypothesis about the relevant percepts and situation-awareness of drivers in dynamic traffic scenes. The percepts are revealed in a structure-learning procedure using a discriminative scoring criterion based on the Bayesian Information Criterion. Discriminative learning maximizes the conditional likelihood of probabilistic models, whereas the traditional generative learning maximizes the unconditional likelihood. This way, it attempts to find the structure with the best performance for the intended use, which in our application is the best prediction of driving actions given the available percepts.

Item Type: Article
Uncontrolled Keywords: Bayesian Autonomous Driver Model, human driving behavior, lateral and longitudinal control, relevant percepts, statistical relevance, situation-awareness, dynamic traffic scenes, structure-learning, discriminative scoring criterion, Bayesian Information Criterion, Discriminative learning, conditional likelihood
Subjects: Generalities, computers, information > Computer science, internet
Philosophy and psychology > Psychology
Technology, medicine, applied sciences > Engineering and machine engineering
Divisions: School of Computing Science, Business Administration, Economics and Law > Department of Computing Science
Date Deposited: 11 Jul 2014 09:28
Last Modified: 11 Jul 2014 09:28
URI: https://oops.uni-oldenburg.de/id/eprint/1864
URN: urn:nbn:de:gbv:715-oops-19458
DOI:
Nutzungslizenz:

Actions (login required)

View Item View Item

Document Downloads

More statistics for this item...