Return to search

A Fault-aware Sensor Fusion System for Autonomous Vehicles

There have been several accidents involving autonomous vehicles on public
roadways under scenarios that are normally avoidable by competent human
drivers. This thesis contains a review of these accidents and their causes as
a result of inadequate hazard mitigation. As a solution to this problem, a
novel design pattern is proposed. This design pattern was developed from a
hazard analysis using Systems Theoretic Process Analysis ( STPA ) methodologies
that analyzed the circumstances common to several of these accidents. To
demonstrate the effectiveness of the novel design pattern, an example system is
constructed and tested in simulation against several accident scenarios similar to
the ones studied. The results are then explained to demonstrate the effectiveness
of the proposed design pattern. / Thesis / Master of Applied Science (MASc)

Identiferoai:union.ndltd.org:mcmaster.ca/oai:macsphere.mcmaster.ca:11375/25903
Date January 2020
CreatorsBarkovic, Joshua
ContributorsWassyng, Alan, Lawford, Mark, Computing and Software
Source SetsMcMaster University
LanguageEnglish
Detected LanguageEnglish
TypeThesis

Page generated in 0.0015 seconds