AI-Driven Indoor Sensing and Localisation Using Ambient Wireless Signals on Embedded Systems
Engineering, IT, Mathematics and Statistics
ABOUT THE INDUSTRY PARTNER
Telstra is Australia’s leading telecommunications and technology company, offering a full range of communications services and competing in all telecommunications markets. In Australia Telstra provides around 22.5 million retail mobile services and 3.4 million retail bundle and data services.
WHAT’S IN IT FOR YOU?
- Deep expertise in signal processing and machine learning: Gain hands-on experience designing and implementing state-of-the-art algorithms for wireless signal feature extraction, deep learning–based classification, and sensor fusion — skills highly sought after in both academia and industry.
- Full-stack embedded systems development: Develop end-to-end proficiency from low-level firmware and real-time data acquisition on resource-constrained embedded systems through to cloud-connected analytics pipelines, building a compelling engineering portfolio.
- Industry-relevant innovation: Collaborate on a project with clear commercial pathways in smart building management, healthcare monitoring, and IoT infrastructure, equipping you with practical, transferable skills that bridge academic research and real-world product development.
RESEARCH TO BE CONDUCTED
The proposed research will investigate the use of ambient wireless signal characteristics to perform indoor sensing and localisation. The project comprises three interlocking parts:
Part 1 — Literature Review and Algorithm Evaluation: A thorough review of existing indoor sensing algorithms spanning classical signal processing, statistical methods, and machine learning. The student will go beyond reported accuracy figures to critically assess the real-world conditions and assumptions under which results were obtained — many methods achieve high precision only under idealised or controlled scenarios that do not generalise well to practical deployments. Each approach will be evaluated against deployment complexity, computational cost, robustness to environmental variation, and feasibility for implementation on resource-constrained hardware.
Part 2 — Embedded System Pipeline Implementation: Design and implementation of a sensing and localisation pipeline on low-cost embedded hardware. The focus is to characterise the platform’s performance and limitations — including throughput, latency, memory constraints, power consumption, and reliability under sustained operation — to establish what is practically achievable and where the system boundaries lie. This phase will produce a clear technical baseline that informs the algorithm design choices in the subsequent phase.
Part 3 — Algorithm Development, System Integration, and Evaluation: Building on Part 1 insights and Part 2 platform characterisation, this phase develops sensing algorithms tailored to real-world constraints, making informed trade-offs between computational performance and sensing precision to deliver a solution that is both accurate and deployable. The algorithms will be integrated into a cohesive end-to-end system and evaluated in real-world indoor environments across diverse scenarios to validate accuracy, latency, robustness, and scalability.
SKILLS WISH LIST
If you’re a postgraduate research student and meet some or all the below we want to hear from you. We strongly encourage women, indigenous and disadvantaged candidates to apply:
Essential:
- Strong programming skills in C/C++ and Python
- Solid foundation in digital signal processing (DSP) and linear algebra
- Familiarity with machine learning frameworks (e.g., PyTorch, TensorFlow/TensorFlow Lite)
- Experience with embedded systems or microcontroller development
Desirable:
- Knowledge of wireless communication fundamentals (OFDM, channel estimation, MIMO)
- Experience with model optimisation for edge deployment (quantisation, pruning)
- Familiarity with real-time operating systems (RTOS) and firmware development
- Prior exposure to PCB design or hardware prototyping
- Technical writing and data visualisation skills
RESEARCH OUTCOMES
- A comprehensive benchmark and survey of indoor sensing and localisation algorithms, evaluated against accuracy, computational cost, and suitability for embedded deployment, contributing a valuable reference to the research community.
- An integrated sensing pipeline and development framework for resource-constrained embedded platforms, providing a reusable foundation for further research and product development in indoor sensing and localisation.
- An end-to-end open-source prototype system comprising embedded sensing nodes, a multi-node fusion engine, and a visualisation interface — demonstrating practical feasibility for smart building and healthcare applications.
ADDITIONAL DETAILS
The intern will receive $3,300 per month of the internship, usually in the form of scholarship payments.
It is expected that the intern will primarily undertake this research project during regular business hours and maintain contact with their academic mentor throughout the internship either through face-to-face or phone meetings as appropriate.
The intern and their academic mentor will have the opportunity to negotiate the project’s scope, milestones and timeline during the project planning stage.
Please note, applications are reviewed regularly and this internship may be filled prior to the advertised closing date if a suitable applicant is identified. Early submissions are encouraged.
INTERNSHIP CONTACT
CONNECT WITH APR.INTERN
