Digital Commons Network^™

Enhancing Deep Reinforcement Learning With Expert Demonstrations For Mobile Robot Navigation In Unstructured Off-Road Environments, Dulitha Dabare

Theses: Doctorates and Masters

Advancements in the field of Deep Learning has ushered in a boom in autonomous navigation research. Most of the work being conducted in this space, however, has focused on on-road urban navigation scenarios, with unstructured outdoor terrain navigation receiving much more limited attention. Given the wide range of applications that exist for legged and wheeled ground robots in off-road environments in areas such as agriculture, mining and disaster recovery, there is a growing need for research work to improve the navigational capabilities of mobile robots deployed in these challenging environments.

A promising candidate for application to these navigation challenges in …

Exploring Hybrid Chinese-Western Compositional Practices Based On Chinese And Western Film Soundtracks, Jie Hong Yang

Theses: Doctorates and Masters

This thesis explores the development of a hybrid Chinese-Western compositional practice for film scoring, combining a written dissertation (Volume I) with a folio of 80 minutes of original orchestral music (Volume II). Drawing on analyses of Tan Dun’s Crouching Tiger Cello Concerto (2000) and John Powell’s film score for How to Train Your Dragon (2010), the research investigates how Chinese (minzu yinyue) musical elements and Western scoring techniques can be integrated to create a culturally hybrid approach. The project unfolds in two phases: the first focuses on incorporating Chinese musical characteristics into Western frameworks, resulting in 40 minutes …

Emerging From The Cocoon: Strategies To Assist The Classical Violinist Develop Improvisational Fluency In A Range Of Musical Styles, Judith A. Iddison

Theses: Doctorates and Masters

This autoethnographic practice-led research project documents the journey of expanding my classical violin practice with the aim of developing improvisational fluency in a range of musical styles. Building upon findings and strategies outlined in my honours thesis, which centred on the artistry of Australian cross-genre violinist Shenzo Gregorio (Shenton Gregory), this doctoral study is underpinned by an iterative cyclic process of critical observation, reflection and analysis and an examination of literature.

Knowledge gained through one-on-one, aural-based, practical violin-improvisation instruction with Gregorio was applied within collaboration with the evolving string ensemble, Sign of Four. Further, combining this tuition and collaboration with …

Patient Experiences Of Receiving Home-Based Immunotherapy Infusions - A Constructivist Grounded Theory Study, Patricia Ann Cook

Theses: Doctorates and Masters

Context: The treatment of cancer and chronic health conditions has been greatly revolutionised via intravenous immunotherapy infusions. Demand, both globally and in Australia, is increasing due to several factors including aging and increased populations, subsequent increases of cancer cases, new immunotherapy indications and increased survival rates.

In Perth, Western Australia, a private service provider commenced delivering a home based immunotherapy infusions model of care as a hospital substitution service provider in 2013 and the service has now been extended across Australia. The safety and efficacy of home-based infusions have been well documented in research, and an increasing number of patients …

Multimodal Scene Understanding For Mobile Robot Navigation In Unstructured Outdoor Environments, Liyana Mudiyanselage Nipuna Dinendra Wijayathunga

Theses: Doctorates and Masters

The application of autonomous field robots in agriculture, mining, transport and logistics, disaster management, and exploration has increased with advances in sensing, perception, and autonomous navigation technologies. Western Australian off-road environments present challenges for autonomous ground robots because they contain unstructured ter rain, variations in appearance and geometry, changing illumination, and visually similar regions with different traversal characteristics. Reliable operation therefore requires scene understanding methods capable of representing the environment according to its navigability for robot traversal.

This PhD research investigates multimodal scene understanding for autonomous ground robot navigation in unstructured off-road environments. The research focuses on the development of …