Skip to content

Commit

Permalink
Students Busuyi and Nicholas
Browse files Browse the repository at this point in the history
  • Loading branch information
@timothy-wiley
timothy-wiley committed Nov 6, 2024
1 parent 9b8bef2 commit 2fd2a75
Show file tree
Hide file tree
Showing 3 changed files with 164 additions and 37 deletions.
12 changes: 6 additions & 6 deletions publications.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -43,12 +43,12 @@ <h5 id="quals">PhD, BSc (Computer Science)</h5>
<h1>Publications</h1>
All of Timothy's publications, sorted by category.
<ul id="toc">
<li><a href="#journal">Journal Articles</a>
<li><a href="#books">Book Chapters</a>
<li><a href="#conference">Conference and Workshop Papers</a>
<li><a href="#techreport">Tech Reports</a>
<li><a href="#phd">PhD Thesis</a>
<li><a href="#honours">Honours Thesis</a>
<li><a href="#journal">Journal Articles</a></li>
<li><a href="#books">Book Chapters</a></li>
<li><a href="#conference">Conference and Workshop Papers</a></li>
<li><a href="#techreport">Tech Reports</a></li>
<li><a href="#phd">PhD Thesis</a></li>
<li><a href="#honours">Honours Thesis</a></li>
</ul>
<hr />

Expand Down
167 changes: 136 additions & 31 deletions students.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -43,48 +43,153 @@ <h5 id="quals">PhD, BSc (Computer Science)</h5>

<p>
An overview of the students, current and former, whom I have supervised highlighting their projects and completions.
<ul id="toc">
<li>
<a href="#completionsmasters">Completions (Masters)</a>
<ul>
<li><a href="#morris">Samuel Arthur Morris</a></li>
<li><a href="#omodaratan">Busuyi Ojo Omodaratan</a></li>
</ul>
</li>
<li>
<a href="#completionshonours">Completions (Honours)</a>
<ul>
<li><a href="#rayner">Nicolas Rayner</a></li>
</ul>
</li>
</ul>
<hr />
</p>

<h2>Completions (Masters)</h2>
<a id="completionsmasters" aria-label="Completions (Masters)"></a>
<h2 >Completions (Masters)</h2>

<h3>Samuel Arthur Morris (2024)</h3>
<div class="citation">
<div class="thesis">
<a id="morris" aria-label="Samuel Arthur Morris"></a>
<h3>Samuel Arthur Morris</h3>
<p>
<span class="title">Policy Transfer for Deep Reinforcement Agents Using Game Entity Substitution - Applied to Infinite Mario</span> <br />
School of Computing Technologies, STEM College, RMIT University, Melbourne, Australia. <br />
<span class="supervisor">Supervisors: Dr. Timothy Wiley, Dr. Michael Dann.</span>
<span class="supervisor">Supervisors: Dr. Timothy Wiley, Dr. Michael Dann.</span> <br />
November 2024.
</p>
<div class="abstract">
<p class="abstract-title">Abstract</p>
<p>
Deep Reinforcement Learning (DRL) agents have shown impressive ability in
mastering computer games, but notoriously take a long time to learn. As an
agent progresses through a game, it will often encounter new states containing
previously unencountered game entities, e.g., new enemies. In such situations,
DRL agents typically struggle to generalise their prior knowledge to the new
entities, owing to differences in state and object representations. In particular,
even when new entities behave similarly to previously encountered ones, if they
appear to be different then DRL agents can take a long time to adapt.
</p>
<p>
Policy transfer learning offers a promising approach for allowing DRL
agents to adapt their knowledge; however, establishing the connection between
the newly presented states (the target task) and previously encountered ones
(the source task) requires guidance from a domain expert. Guidance in the
form of externally constructed mapping of state-action pairings, must be continually
maintained in response to new game entity encounters.
</p>
<p>
This thesis proposes an alternative approach, where policy transfer is accomplished
by leveraging an intermediate state transformation, removing the
need for manual mapping. Each entity is mapped to a unique entity ID, and
when a new game entity is encountered, a "substitution agent" strives to learn
a mapping between the new entity ID and a previously encountered one. For
example, if the new entity is a type of enemy, the substitution agent will ideally
learn to map the new ID to a previously encountered enemy’s ID, rather
than, say, the ID of a powerup item. Experimental results show that this
approach is effective, allowing for rapid improvement of end-of-episode scores
when encountering new entity representations in the game, Infinite Mario.
</p>
</div>
</div>
<div class="thesis">
<a id="omodaratan" aria-label="Busuyi Ojo Omodaratan"></a>
<h3>Busuyi Ojo Omodaratan</h3>
<p>
Abstract <br />
Deep Reinforcement Learning (DRL) agents have shown impressive ability in
mastering computer games, but notoriously take a long time to learn. As an
agent progresses through a game, it will often encounter new states containing
previously unencountered game entities, e.g., new enemies. In such situations,
DRL agents typically struggle to generalise their prior knowledge to the new
entities, owing to differences in state and object representations. In particular,
even when new entities <em>behave</em> similarly to previously encountered ones, if they
<em>appear</em> to be different then DRL agents can take a long time to adapt. <br />
Policy transfer learning offers a promising approach for allowing DRL
agents to adapt their knowledge; however, establishing the connection between
the newly presented states (the target task) and previously encountered ones
(the source task) requires guidance from a domain expert. Guidance in the
form of externally constructed mapping of state-action pairings, must be continually
maintained in response to new game entity encounters. <br />
This thesis proposes an alternative approach, where policy transfer is accomplished
by leveraging an intermediate state transformation, removing the
need for manual mapping. Each entity is mapped to a unique entity ID, and
when a new game entity is encountered, a "substitution agent" strives to learn
a mapping between the new entity ID and a previously encountered one. For
example, if the new entity is a type of enemy, the substitution agent will ideally
learn to map the new ID to a previously encountered enemy’s ID, rather
than, say, the ID of a powerup item. Experimental results show that this
approach is effective, allowing for rapid improvement of end-of-episode scores
when encountering new entity representations in the game, <em>Infinite Mario</em>.
<span class="title">Simultaneous Road Objects and Lane Detection Models in Autonomous Vehicles</span> <br />
School of Engineering, STEM College, RMIT University, Melbourne, Australia. <br />
<span class="supervisor">Supervisors: Dr. Hamid Hkayyam, Dr. Timothy Wiley.</span> <br />
June 2024.
</p>
<div class="abstract">
<p class="abstract-title">Abstract</p>
<p>
Poor road boundary lanes and detections of road objects have been identified as some of the
serious causes of road accidents, in both conventional and autonomous driving. Therefore, it is
critical to develop models that could help autonomous vehicles' perception systems while
accurately identifying and locating road objects from images and video frames. However, the
existing models face a series of challenges due to the highly complex nature of the road traffic
scene and the influence of various road objects on the manoeuvring. Most of the existing
models cannot simultaneously detect all the major road objects, with some, either detecting
lanes or detecting some of the road objects. To address these gaps, the combined road objects
and lane detection model was developed using the You Only Look Once (YOLO) algorithm.
As a first step, a model was developed to detect road objects only and the results were compared
with existing studies. Next, another model was developed to detect road lanes based onYOLOv8 capability.
Finally, an improved YOLOv8 model was developed to simultaneously
detect road objects and lanes. To achieve this, the YOLOv8 model was tuned and optimised
using various optimization approaches considering several hyperparameters such as activation
functions and regularisation methods. Further, the effect of augmentation was investigated
using three techniques; cut-out, rotation and rotation with noise. Also, the effect of the data
stream on the performance of the model was investigated based on the obtained
hyperparameter. The relevant performance metrics such as precision, F1, and recall were
deployed. In addition, mean average precision calculated at an intersection over union (IoU)
threshold of 0.5 and 0.95 was reported to assess the model's detection capabilities. The results
from this study were further compared with some existing studies such as Feature PyramidNetworks,
Task-aligned One-stage Object Detection, Dynamic R-CNN Probabilistic AnchorAssignment with IoU Prediction,
Sparse R-CNN and CenterNet to demonstrate the
contribution of the model. Further, the performance of the models based on different dataset
(Curated data, COCO, and KITTI) showed that curated data outperformed others across all the
performance metrics. Notably, curated data has the most promising results with precision,
recall and F1 score of 0.68, 0.61, and 0.64, respectively. The success of the curated dataset
highlights the significance of tailoring datasets to the specific nuances of the targeted
application domain. Finally, the conclusion and recommendations were made based on the
findings from the study.
</p>
</div>
</div>

<!-- <h2>Completions (Honours)</h2> -->

<a id="completionshonours" aria-label="Completions (Honours)"></a>
<h2>Completions (Honours)</h2>
<div class="thesis">
<a id="rayner" aria-label="Nicolas Rayner"></a>
<h3>Nicolas Rayner</h3>
<p>
<span class="title">Development of a DigitalTwin for Building Flows</span> <br />
School of Computing Technologies, STEM College, RMIT University, Melbourne, Australia. <br />
<span class="supervisor">Supervisors: Dr. Abdulghani Mohamed, Dr. Timothy Wiley.</span> <br />
November 2023.
</p>
<div class="abstract">
<p class="abstract-title">Abstract</p>
<p>
The main objective and outcome of the research is the development of a functioning digital twin for the prediction of the flow fields
around a building exposed to a variety of wind conditions in urban environments.
Unmanned aerial vehicles, also referred to as UAVs, air taxis,
helicopters and a range of other aerial vehicles provides a promising platform for this technology due to an ever-expanding
interest in operating within these obstacle dense and unpredictable environments.
Allowing them to manoeuvre accordingly in reaction to onboard sensors comparing simulated data of the buildings flow field,
aiding in the prediction of conditions along its flight path.
Ability to predict wind conditions would be beneficial for flight path mapping with current studies highlighting the correlation
between turbulent flow experienced by aircraft in urban environments and catastrophic crashes.
Further potential is seen with the prediction of the shear layers behaviour on top of the building as these changes
in velocity and induced turbulent regions have potential for sudden disastrous effects on aircrafts behaviour during taking off,
landing and operation within this region.
In order to develop a digital twin for the stated application,
research on the behaviour of wind flow fields on isolated buildings will be conducted.
Known calculations and quantitative values of estimating the position of the points of interest such as stagnation of the flow on the front of the building,
separation on top of the build and wake sizes will need to be investigated to accurately place sensor points in simulations to train,
test, and apply the predictive abilities of the digital twin.
The proposed area of research can be carried out through the use of Computer Aided Design (CAD),
Computational Fluid Dynamics (CFD), Machine Learning (ML), High Power Computational (HPC) devices,
powerful computational servers, and practical validation testing from recorded data on scale or full-size models.
</p>
</div>
</div>

</div>
</section>
Expand Down
22 changes: 22 additions & 0 deletions styles/publications.css
View file
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,28 @@
font-style: italic;
}

.thesis h3 {
/* color: #004192; */
color: #910D00;
}

.thesis .supervisor {
font-style: italic;
}

.thesis .abstract .abstract-title {
/* font-weight: bold; */
font-style: italic;
}

.thesis .abstract p:not(:last-child) {
margin-bottom: 0.3em;
}

.thesis .abstract p:not(:first-child) {
text-indent: 1.0em;
}

/*
section li a:link, section li a:visited {
color: #000;
Expand Down

0 comments on commit 2fd2a75

Please sign in to comment.