Faculty/School

Faculty of Engineering

School of Electrical Engineering and Robotics

Topic status

We're looking for students to study this topic.

Research centre

Centre for Biomedical Technologies

Primary Supervisor

Dr Ethan Goan
Position
Research Fellow
Division / Faculty
Faculty of Engineering

Other QUT supervisors

Dr Akila Hewa Thondilege
Position
Research Fellow
Division / Faculty
Faculty of Engineering
Professor Glen Lichtwark
Position
Head of School
Division / Faculty
Faculty of Health

Overview

Develop an end-to-end biomechanics pipeline by integrating custom anatomical models with open-source physics engines and machine learning techniques. Accurate analysis of human movement is essential in fields such as clinical rehabilitation, sports science, and injury prevention, yet existing workflows are often fragmented, requiring multiple tools and significant manual intervention. This limits scalability, reproducibility, and the ability to translate research advances into practical applications.

This project addresses these challenges by creating a unified, open-source framework that links data-driven machine learning methods with physics-based biomechanical modelling. By combining pose estimation, inverse kinematics, and inverse dynamics within a single workflow, the pipeline will enable more efficient and consistent estimation of movement patterns and internal forces.

Research engagement

Students will participate in a structured research process that includes a focused literature review, hands-on software development, and the application of machine learning within a simulation environment. The project emphasises practical implementation and iterative refinement of methods. This will be supported by the guidance and collaboration of the supervisors, as well as external stakeholders with expertise in biomechanics.

Research activities

The project will develop an end-to-end biomechanics workflow integrating machine learning with physics-based simulation. This includes transferring custom anatomical models into an open-source physics engine and building a pipeline that links pose estimation to inverse kinematics and inverse dynamics. The student will also explore how machine learning can improve accuracy and efficiency, with validation against established methods in collaboration with interdisciplinary researchers.

Research skills

You will gain experience in engineering research and development, and how to translate this research to address real-world problems, particularly for clinical applications. You will develop skills needed for research, such has how to thoroughly evaluate existing research, identify important gaps, and how to develop solutions to these problems. All of this will include experience with software development and testing, computer vision, 3D rendering, anatomical modelling, machine learning, and inverse kinematics.

Outcomes

A complete open-source biomechanics pipeline for human movement analysis and measurement of internal forces throughout the body.

Skills and experience

A strong foundation in Python programming is required, as well as a deep interest in research and development. It is desirable for a suitable candidate to have prior exposure to the following areas (though not required and these skills will be developed over the research project) :

  • Machine Learning concepts
  • Software Version Control and Software Engineering best practices
  • Computer vision/image processing concepts

Start date

2 November, 2026

End date

19 February, 2027

Location

QUT Gardens Point Campus

Keywords

Contact

Ethan

ej.goan@qut.edu.au