The University of Queensland 

Dr Kurniawati is a lecturer and mechatronics plan director at the School of Information Technology and Electrical Engineering, the University of Queensland. Her current research focuses on algorithms to enable decision theory become practical software tools in robotics.

Such tools will enable robots to design their own strategies, such as deciding what data to use, how to gather the data, and how to move, for accomplishing specific tasks, despite various modelling errors and uncertainty in the system and its operating environment.

Prior to joining UQ, Dr Kurniawati was a Research Scientist at the SMART Center, MIT. She earned a PhD in Computer Science from National University of Singapore, and a BSc also in Computer Science from the University of Indonesia.

More information about her work is available at

Dr Hanna Kurniawati will be lecturing at AMSI Winter School 2017, delivering a course on “A Decision Making View Of Machine Learning”.

Dr Hanna Kurniawati


1. Can you tell us about your work? What drives your interest in this field?

I design algorithms and develop software for autonomous decision making in the presence of uncertainty.

I grew up watching movies that feature amazing robots, from R2D2 and C3PO to Doraemon. So, I think it’s natural that I want to have such robots too – Autonomous robots that actually work. I found that the biggest problem in making this dream a reality is that robots (just as humans) can’t escape uncertainty. So, I try to develop algorithms that will enable robots make good decision in the presence of uncertainty.

2. What are the most interesting “big questions” or challenges facing researchers in your area?

Scalability in the action space and automatic modelling of the problem are still relatively open problems.

3. What are some key industry applications of your work?

Robust autonomous robots.

4. What do you consider your biggest achievement to date?I like to think that my work enables principled and robust approaches for decision making in uncertain and unpredictable scenarios – until now considered impractical – to start becoming practical, at least for robotics. This then could bring safer, and more effective and efficient autonomous and semi-autonomous systems. For instance, our work have been shown to increase the safety risk of mid-air collision avoidance module of existing TCAS by 20X. TCAS is an assistive device that helps pilots avoid collisions and is mandatory in all commercial aircraft.

5. Do you have any advice for future researchers?

Enjoy the journey!!