WaveSense: Advanced Signal Processing and AI for Next-Gen Human Presence Detection
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?
- Hands-On Experience with Cutting-Edge Technologies: Work directly with state-of-the-art mmWave sensing technology combined with AI-driven signal processing. Candidates will acquire a deep understanding of mmWave signal processing techniques and their integration with AI models.
- Interdisciplinary Research Opportunities: This project bridges several key fields, including physics, signal processing, machine learning, and wireless communication. Candidates will have the opportunity to build expertise in both theoretical and applied research that spans multiple domains, enhancing their skillset and broadening their research portfolio. This project offers a unique environment which allows candidates to solve complex challenges that require both innovative thinking and technical expertise.
- Real-World Impact and Applications: By working on this project, candidates will contribute to the development of mmWave technology with applications in smart environments, security systems, asset monitoring, and more. WaveSense has the potential to revolutionise how we interact with our environments, enabling intuitive, seamless interactions that enhance conveniences, security, and accessibility.
- Industrial and Processional Development: Candidates will receive leading mentorship from the industry, which will help them refine their research skills, improve their technical understanding, explore career opportunities, develop a strong foundation for future career opportunities in academia, industry, or entrepreneurship. Candidates will also gain experience in project management, collaboration in team setting, and presenting their research findings to diverse audiences.
RESEARCH TO BE CONDUCTED
- The proposed WaveSense research aims to advance human presence detection using next-gen mmWave sensing technology combined with AI-driven signal processing. The project will focus on developing innovative methods to accurately detect human presence in real–time, with potential application in smart environments, security, asset monitoring, and more.
- The primary objective is to leverage non-invasive capabilities of mmWave signals to create robust sensing systems that can operate in diverse environment, including indoor and outdoor settings. The research will explore how AI models can be applied to mmWave data to improve detection accuracy, adapt to different environmental conditions, and reduce false positives.
- The research will involve the design and implementation of advanced signal processing algorithms that can extract meaningful features from the raw mmWave data. These algorithms will be critical in detecting motion and identifying objects. Machine learning techniques will be employed to continuously improve detection capabilities through training on diverse datasets.
- Additionally, the project will explore the integration of these sensing systems into practical edge devices. A key focus will be on designing lightweight, energy-efficient algorithms that balance performance with resource constraints, ensuring that the system can run on edge devices without sacrificing accuracy. Techniques such as model pruning, quantisation, and edge-friendly architectures will be explored to make AI models scalable and deployable on small, low-power IoT devices.
- The project will also focus on designing a real-world, market-ready product. This project will prioritise professional product design principles, including reliability, scalability, and user experience, ensuring that the solution is ready for industrial use, offering tangible benefits in real-world applications.
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:
- Signal Processing: Strong understanding of advanced signal processing techniques, such as filtering, feature extraction, signal analysis for range and velocity estimation, and clutter removal techniques.
- AI and Machine Learning: Strong knowledge of machine learning algorithms, especially in model optimisation, and edge computing frameworks, such as TensorFlow Lite or custom edge solutions.
- Electromagnetic Wave Propagation: Understanding of electromagnetic wave propagation, particularly for mmWave frequencies.
- Embedded Systems: Experience in the design, development, and integration of embedded systems, such as hardware interfacing, embedded C programming, RTOS. MQTT.
- Tools and Techniques: Proficient in Python and embedded C, knowledge of FreeRTOS. Git, debugging tools, and Agile methodology
RESEARCH OUTCOMES
- Demonstrate the feasibility of using mmWave sensing and AI for human presence and object detection. Key deliverables:
(a) Successful integration of mmWave sensors and basic signal processing algorithms.
(b) Deliver a proof-of-concept prototype capable of detecting human presence and objects with reasonable accuracy in controlled settings. - Design and optimise signal processing algorithms and AI models for resource-constrained edge IoT devices. Key deliverables:
(a) Design and integrate customised signal processing algorithms and an edge AI framework on an IoT device
(b) Design and implement different physical lenses for a variety of user requirements and validate the performance. - Transform the research into a fully market-ready industrial product, with a focus on scalability, reliability, and ease of integration into real-world applications. Key deliverables:
(a) A scalable and reliable product that works autonomously in real-time across multiple environments.
(b) Fully optimised signal processing algorithms and AI models with automated data pipeline for training and inferencing.
ADDITIONAL DETAILS
The intern will receive $3,000 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
