Dr Chirath Hettiarachchi

B.Sc. Eng (Hons) (Electronics & Telecommunication Engineering), University of Moratuwa, 2018; M.Sc (Research), University of Moratuwa, 2020; PhD (Computer Science), ANU, 2023.
Research Fellow
ANU College of Engineering, Computing and Cybernetics

Research interests

  • Reinforcement Learning
  • Machine Learning
  • Control Systems
  • Signal Processing
  • Biomedical Engineering



Chirath Hettiarachchi is a Research Fellow at the ANU School of Computing working on closed-loop healthcare applications. He completed his PhD at ANU, in the Big Data program of the “Our Health In Our Hands (OHIOH)” project, a strategic initiative of the university. His research focused on using ML to develop a control system for the artificial pancreas. He received his BSc (Hons) in Electronics & Telecommunication Engineering & MSc (Research) degrees from the University of Moratuwa, Sri Lanka in 2018 and 2020. He completed his professional qualification in Management Accounting at the Chartered Institute of Management Accountants in 2014 (CIMA-UK).

He worked as a Machine Learning Engineer in the FinTech industry from 2018 - 2019, developing algorithms for identifying outliers in corporate financial transactions, forecasting, name screening and risk prediction applications. During the final year of his undergraduate studies, he pursued his entrepreneurial aspirations by co-founding a healthcare startup which achieved multiple awards and publications.

His research interests include ML, reinforcement learning, control systems, biomedical signal processing, health informatics and financial data analytics.

Researcher's projects

  • CAPSML (https://capsml.com/) - Developing glucose control algorithms requires collaboration between clinicians, patients, researchers, and engineers. CAPSML is an online tool designed for testing and understanding RL-based glucose control  algorithms through simulations.
  • GluCoEnv (https://github.com/chirathyh/GluCoEnv) - Developing a simulation platform to facilitate research on RL-based glucose control algorithms. The simulator provides the capability to run parallel experiments (through a vectorized implementation), end-to-end on the GPU.
  • G2P2C (https://github.com/chirathyh/G2P2C) - Designing Reinforcement Learning (RL) algorithms, to fully automate glucose regulation in type 1 diabetes, addressing the real-world technical challenges associated with the problem. 

Available student projects

  • Reinforcement Learning (RL) Agents for Glucose Regulation (Link: https://comp.anu.edu.au/study/projects/reinforcement-learning-rl-agents-for-glucose-regulation/). 
  • High Performance Digital Twins for Type 1 Diabetes Research (Link: https://comp.anu.edu.au/study/projects/high-performance-digital-twins-for-type-1-diabetes-research/ ).
  • Machine Learning for Bio-marker Discovery & Modelling in Type 1 Diabetes (Link: https://comp.anu.edu.au/study/projects/machine-learning-for-bio-marker-discovery-modelling-in-type-1-diabetes/).

Past student projects

  • Noise Removal from ECG Signals Using Machine Learning Techniques - Brenda Wang.

Return to top

Updated:  19 April 2024 / Responsible Officer:  Director (Research Services Division) / Page Contact:  Researchers