ROS Theses Repository

View Item 
  •   ROS Home
  • Engineering & Physical Sciences
  • Doctoral Theses (Engineering & Physical Sciences)
  • View Item
  •   ROS Home
  • Engineering & Physical Sciences
  • Doctoral Theses (Engineering & Physical Sciences)
  • View Item
  •   ROS Home
  • Engineering & Physical Sciences
  • Doctoral Theses (Engineering & Physical Sciences)
  • View Item
  • Admin
JavaScript is disabled for your browser. Some features of this site may not work without it.

Shallow neural networks for autonomous robots

View/Open
DeLucasAlvarezM_0621_epsSS.pdf (18.47Mb)
Date
2021-06
Author
De Lucas Alvarez, Mariela
Metadata
Show full item record
Abstract
The use of Neural Networks (NNs) in modern applications is already well established thanks to the technological advancements in processing units and Deep Learning (DL), as well as the availability of deployment frameworks and services. However, the embedding of these methods in robotic systems is problematic when it comes to field operations. The use of Graphics Processing Units (GPUs) for such networks requires high amounts of power which would lead to shortened operational times. This is not desired since autonomous robots already need to manage their power supply to accommodate the lengths of their missions which can extend from hours to days. While external processing is possible, real-time monitoring can become unfeasible where delays are present. This also applies to autonomous robots that are deployed for underwater or space missions. For these reasons, there is a requirement for shallow but robust NN-based solutions that enhance the autonomy of a robot. This dissertation focuses on the design and meticulous parametrization complemented by methods that explain hyper-parameter importance. This is performed in the context of different settings and problems for autonomous robots in field operations. The contribution of this thesis comes in the form of autonomy augmentation for robots through shallow NNs that can potentially be embedded in future systems carrying NN processing units. This is done by implementing neural architectures that use sensor data to extract representations for event identification and learn patterns for event anticipation. This work harnesses Long Short-Term Memory networks (LSTMs) as the underpinning framework for time series representation and interpretation. This has been tested in three significant problems found in field operations: hardware malfunction classification, survey trajectory classification and hazardous event forecast and detection.
URI
http://hdl.handle.net/10399/4491
Collections
  • Doctoral Theses (Engineering & Physical Sciences)

Browse

All of ROSCommunities & CollectionsBy Issue DateAuthorsTitlesThis CollectionBy Issue DateAuthorsTitles

ROS Administrator

LoginRegister
©Heriot-Watt University, Edinburgh, Scotland, UK EH14 4AS.

Maintained by the Library
Tel: +44 (0)131 451 3577
Library Email: libhelp@hw.ac.uk
ROS Email: open.access@hw.ac.uk

Scottish registered charity number: SC000278

  • About
  • Copyright
  • Accessibility
  • Policies
  • Privacy & Cookies
  • Feedback
AboutCopyright
AccessibilityPolicies
Privacy & Cookies
Feedback
 
©Heriot-Watt University, Edinburgh, Scotland, UK EH14 4AS.

Maintained by the Library
Tel: +44 (0)131 451 3577
Library Email: libhelp@hw.ac.uk
ROS Email: open.access@hw.ac.uk

Scottish registered charity number: SC000278

  • About
  • Copyright
  • Accessibility
  • Policies
  • Privacy & Cookies
  • Feedback
AboutCopyright
AccessibilityPolicies
Privacy & Cookies
Feedback