Analysis Of The Impact Of Driver Behavior Models On Performance Of Forward Collision Warning Systems

Keywords

Collision Avoidance; Driver Assistant; Driver Behavior; Driver Reaction; FCW; Intelligent Transportation Systems; Vehicular Networks

Abstract

A critical aspect of vehicle safety analysis is understanding the impact of human behavior on the overall performance of the system. Since active safety systems (such as collision warning systems) are designed for escaping a life threatening situation, evaluation and validation of theircomponents and the underlying algorithms are often costly, and cannot be achieved without direct exposure of test subjects to hazards. As an alternative, researchers try to use simulation toolsto design and evaluate their safety algorithms prior to building test-beds for validation. This study proposes a comprehensive simulation framework for vehicular active safety system analysis. It comprises different domains of communication, transportation, and vehicular safety. The simulation framework supplies a driver model and allows for analysis of human reaction and behavior toan imminent warning. Modeling human behavior is specially challenging and requires an in-depth breakdown and investigation of the class of actions a human driver may select from. In thisstudy, we look at the primary form of a driver reaction, i.e. braking when a warning is issued. We investigate different levels of braking and complete our analysis by studying the effect of eachbraking level on a subject forward collision warning algorithm.

Publication Date

3-29-2018

Publication Title

Proceedings - 2017 IEEE 15th International Conference on Dependable, Autonomic and Secure Computing, 2017 IEEE 15th International Conference on Pervasive Intelligence and Computing, 2017 IEEE 3rd International Conference on Big Data Intelligence and Computing and 2017 IEEE Cyber Science and Technology Congress, DASC-PICom-DataCom-CyberSciTec 2017

Volume

2018-January

Number of Pages

113-118

Document Type

Article; Proceedings Paper

Personal Identifier

scopus

DOI Link

https://doi.org/10.1109/DASC-PICom-DataCom-CyberSciTec.2017.33

Socpus ID

85038012959 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/85038012959

This document is currently not available here.

Share

COinS