Despite the rise of self-driving cars and drones, an autonomous system that can operate reliably outside a carefully structured factory floor is rare. The main reason is uncertainty. A robot must decide how to strategise and behave to accomplish its tasks, despite not knowing the exact effect of its actions, errors in sensors and sensing, and the lack of information and understanding about itself and its environment. However, the technology for making good decisions in the presence of uncertainty is lacking. In this talk, I will present some of our past and ongoing work in developing such technology, specifically in computational methods to enable general and mathematically principled concepts for decision-making under uncertainty —deemed intractable for over four decades— to become practical for robotics. I will also discuss how I direct these work and my collaborations, including industry collaborations, towards forming foundational components for building general-purpose robots, which remains a holy grail of robotics.
Meeting ID: 868 2360 6818
Hanna Kurniawati joined the School of Computing at ANU in 2019 as a faculty member, receiving an ANU and CS Futures fellowships. She was also a Research Affiliate at the Dept. of Mechanical Engineering, MIT (2014-2020) and is a Computer Scientist by training, earning a BSc and PhD in Computer Science from the University of Indonesia and National University of Singapore, respectively.
Hanna’s research interests include robotics, planning under uncertainty, robot learning, computational geometry applications, and applications of planning in autonomous cyber operations. She has presented her work as invited talks at multiple venues, including a keynote talk at the Int. Conf. on Intelligent Robots and Systems (IROS) 2018. Together with her students and collaborators, she has received multiple awards, including the prestigious Robotics: Science and Systems 2021 Test of Time Award.
Hanna is actively involved in the robotics community, including in leading editorial roles. The most recent ones being Senior Editor for IEEE Robotics and Automation Letters (RA-L, from 2021) and Program Co-Chair for Int. Conf. on Robotics and Automation (ICRA) 2022. ICRA, RA-L, and IROS are the top three publication venues in terms of impact in robotics, according to Google Scholar Metric.