Robust Decision-making & Learning Lab

School of Computing

Australian National University


Date News
Jan 24 Marcus' paper has been accepted for oral presentation at AAAI24. Congrats, Marcus!
Sep 23 We have 2 papers accepted to NeurIPS 2023! Congrats to Yongbo, Edward and Yohan!
Jul 23 Yuanchu Liang's paper (from his 3rd year project) has been accepted to IROS 2023! Congrats, Yuanchu! [Paper]
Jun 23 An extended version of Marcus Hoerger's WAFR22 paper has been accepted to IJRR! Congrats, Marcus! [Paper]
Mar 23 Congrats to Hanna Kurniawati for her appointment as the SmartSat CRC Professorial Chair for System Autonomy, Intelligence, and Decision Making! [Link]
Jan 23 Jonathon Schwartz paper has been accepted to AAMAS 2023! Congrats, Jonathon! [Paper]
Jun 22 We are excited to be part of the soon to be launched ARC Research Hub in Intelligent Robotic Systems and Asset Management
Feb 22 We are excited to collaborate with Safran under the ARC Linkage Program to investigate AI-based co-pilot for HEMS
Jul 21 Congrats to Hanna Kurniawati for the RSS'21 Test of Time Award! [Link]
Dec 21 Congrats to Nick Collins for winning the Alberto Elfes Best Paper Award at ACRA'20! [Paper]
Jul 20 Congrats to Erli Wang for his new job as a Researcher at NEC Lab!
Mar 20 Congrats to Marcus Hoerger for his PhD conferral!
Feb 20 Congrats to Joshua Song for his MPhil conferral & new job at Clarivate!


We focus on the design and development of algorithms to enable robust decision theory becomes practical computational tools for robotics and related domain. Such computational tools will enable robots to design their own strategies, such as deciding what data to use, how to gather the data, and how to adaptively improve its strategies, so as to accomplish various tasks well, despite various modelling errors and types of uncertainty, and despite limited to no information about the system and its operating environment.

Here are a couple of application examples in robotics:

Active Projects

POMDP Planning for Problems with Complex Dynamics

POMDP Planning for Problems with Large Discrete Action Space

On-line POMDP Planning Toolkit (OPPT)

Partially Observed Inventory Control

Incorporating Defender's Behaviour in Autonomous Pen-Testing


Here are some of the framework/ toolkits that we have developed over the years.


A general framework for online POMDP solver


An early version of OPPT.


An offline POMDP solver implementation of the SARSOP algorithm


Robust Decision-making and Learning (RDL) Lab
Australian National University
108 North Road (CSIT Building) Room N325
Acton, 2601
Canberra, ACT, Australia

Phone: +61 (02) 612 51577

E-mail: rdllab@anu.edu.au