<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet type="text/xsl" href="static/style.xsl"?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-11-21T03:59:30Z</responseDate><request verb="GetRecord" identifier="oai:macsphere.mcmaster.ca:11375/25113" metadataPrefix="dim">https://prod-ms-be.lib.mcmaster.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:macsphere.mcmaster.ca:11375/25113</identifier><datestamp>2026-09-24T04:43:47Z</datestamp><setSpec>com_11375_271</setSpec><setSpec>col_11375_272</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:doc="http://www.lyncode.com/xoai" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="advisor">Wassyng, Alan</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="advisor">Lawford, Mark</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="author">Deevy, Spencer</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="department" lang="en_US">Computing and Software</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2019-12-12T21:16:38Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2019-12-12T21:16:38Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2019</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">http://hdl.handle.net/11375/25113</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://doi.org/10.71548/16732</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en_US">Trends in the automotive industry indicate rapid adoption of artificial intelligence&#xd;
techniques such as machine learning algorithms, enabling increasingly&#xd;
capable autonomous vehicles. However, the major focus has been to improve&#xd;
the performance and accuracy of these techniques, with a clear lack of development&#xd;
towards corresponding safety systems. Artificial intelligence techniques&#xd;
are characterized by high complexity, high variability, and low diagnosability.&#xd;
These issues all pose risks to the safety of autonomous vehicles and need to be&#xd;
taken into consideration as we move towards fully autonomous vehicles.&#xd;
Sentinel, a fault-tolerant software architecture is presented as the main&#xd;
contribution of this thesis. Sentinel has been designed to mitigate safety concerns&#xd;
surrounding artificial intelligence techniques employed by upcoming SAE&#xd;
J3016 level 5 autonomous vehicles. The architecture design process involved&#xd;
careful consideration of issues inherent to artificial intelligence techniques being&#xd;
utilized in autonomous vehicles and their corresponding mitigation strategies.&#xd;
Following this, a survey of software architectures was conducted, drawing&#xd;
inspiration from existing autonomous vehicle architectures as well as architectures&#xd;
in the related domains of artificial intelligence, organic computing, and&#xd;
robotics. These existing architectures were then iteratively combined, guided&#xd;
by an autonomous vehicle hazard analysis, resulting in the final architecture.&#xd;
&#xd;
Additionally, an assurance case was constructed to delineate the assumptions&#xd;
and evidence required to justify the continued safety of autonomous vehicles&#xd;
employing the Sentinel architecture. This work is presented to provide a&#xd;
safety-oriented framework towards fully autonomous vehicles.</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="degreetype" lang="en_US">Thesis</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="degree" lang="en_US">Master of Applied Science (MASc)</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="layabstract" lang="en_US">Artificial intelligence techniques are enabling increased autonomy in autonomous&#xd;
vehicles, however, a major concern that has yet to be addressed is how to&#xd;
ensure vehicle safety while utilizing potentially volatile artificial intelligence.&#xd;
This issue in addition to the lack of existing high-level roadmaps towards fully&#xd;
autonomous vehicles are the driving factors behind this work. We provide&#xd;
Sentinel, a safety-oriented software architecture for autonomous vehicles utilizing&#xd;
artificial intelligence techniques. The literature intersecting the fields of&#xd;
artificial intelligence and autonomous vehicles was reviewed to identify unique&#xd;
safety considerations and mitigation strategies that could be applied. The&#xd;
Sentinel architecture was then synthesized from information in the literature&#xd;
review, while also taking into consideration design choices that would increase&#xd;
industry adoption of Sentinel. An assurance case was then constructed to&#xd;
determine the assumptions and evidence required to justify the non-negative&#xd;
impacts of the architecture on the safety or reliability of a vehicle employing&#xd;
the Sentinel design.</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso" lang="en_US">en</dim:field>
   <dim:field mdschema="dc" element="title" lang="en_US">Sentinel: A Software Architecture for Safe Artificial Intelligence in Autonomous Vehicles</dim:field>
   <dim:field mdschema="dc" element="type" lang="en_US">Thesis</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
</dim:dim></metadata></record></GetRecord></OAI-PMH>