Learning

Gustavo Carneiro is a Chief Investigator in the Centre, and Project Leader (Learning). He is a Professor at the School of Computer Science, University Adelaide. He joined the University of Adelaide as a Senior Lecturer in 2011, became an Associate Professor in 2015, and full Professor in December, 2018. His main research interests are in the fields of computer vision, medical image analysis and machine learning. In particular, in medical image analysis, Gustavo is developing multimodal methods to analyse medical images using deep learning techniques.  In computer vision his focus is in the development of new training procedures for deep learning methods and the development of feature learning approaches.

Feras Dayoub is a Senior Lecturer and a Chief Investigator with the Centre at QUT. He is the co-lead of the project on benchmarking and evaluation of robotic vision systems at ACRV. Feras is deeply interested in the reliable deployment of machine learning and computer vision on mobile robots in challenging environments. From 2016 to 2019, Feras was a Research Fellow with the Centre, based at QUT. From 2012 to 2016, he was a Post-Doctoral Research Fellow with the robotics group at QUT where he worked with various types of robots including Agrobotics as part of a Queensland DAF Agricultural Robotics Program in QUT, Autonomous Underwater Vehicles (AUV) as the computer vision lead on the COTSBot project, Unmanned Aerial Vehicles (UAV) as part of a project on assisted autonomy during the inspection of power infrastructure and Mobile service robots as a research fellow on an Australian research council discovery project on lifelong robotic navigation using visual perception. Feras obtained his PhD in 2012 from Lincoln Centre for Autonomous Systems (L-CAS), UK.

Ajanthan joined the Centre as a Research Fellow in January 2019. Prior to this, he was a Postdoctoral Research Fellow at the Torr Vision Group at the University of Oxford from June 2017. Ajanthan obtained his PhD from ANU in May 2017 and he was primarily supervised by Professor Richard Hartley. During his PhD he was also a member of the Analytics group at Data61, CSIRO, Canberra. He holds a Bachelor’s degree in Electronic and Telecommunication Engineering from the University of Moratuwa, Sri Lanka. Ajanthan has broad interests in Graphical Models, Optimization Algorithms and Machine Learning.

He is part of the Centre’s Learning research project team.

Sadegh is an Associated PhD researcher at our ANU node. He is working on generative modeling of natural human motion, which has applications in human motion prediction, motion synthesis, and better motion capture. He is also working on generative models in general, focusing on variational autoencoders, autoregressive models, and normalizing flows. During his PhD, Sadegh has done several internships, working on motion analysis, adversarial machine learning, and generative modeling.

Aimee is a PhD researcher at Monash University, working under the supervision of Professors Tom Drummond and Dana Kulic. Her previous studies were in Mechatronics and Commerce. She has spent 10 years working across diverse industries including software development, data analysis, hardware, IT education/training and research support.  Aimee’s research interests involve designing robots with strong functional and social requirements that people can both like and trust, incorporating elements of HRI, AGI, biomimicry, robotic vision and machine learning.

Gil is a PhD researcher supervised by Professor Tom Drummond at Monash University in Melbourne. His PhD research interests lay on the intersection of Representation Learning and Generative models applied to Computer Vision tasks. During his PhD, Gil interned at Microsoft and Amazon. Prior to undertaking a PhD, Gil worked in the Israel tech industry for 4 years on various Computer Vision and Robotics projects.

Jiawang is currently a PhD researcher at the University of Adelaide and an Associated PhD researcher with the Centre. He is advised by Professor Ian Reid and Professor Chunhua Shen. His research interests lie in the field of computer vision, machine learning, and robotics. Jiawang received his B.Eng degree from Nankai University, where he was advised by Professor Ming-Ming Cheng. He was a research assistant at the Singapore University of Technology and Design (SUTD), where he worked with Professor Sai-Kit Yeung. Jiawang also worked as a trainee research engineer at the Advanced Digital Sciences Center in Singapore (ADSC), Huawei Technologies Co., Ltd, and Tusimple.

Dylan joined the Centre as a Research Fellow at the ANU in August 2018. Previously, he was a PhD student at ANU and Data61/CSIRO, where he worked on geometric vision problems, and a research assistant in the Cyber-Physical Systems group of Data61/CSIRO, where he worked on Resource Constrained Vision.  Dylan received a BE in Mechatronic Engineering from the University of New South Wales. He has broad research interests within computer vision and robotics, including geometric vision and human-centred vision. In particular, he has investigated geometric sensor data alignment problems, such as camera localisation, simultaneous localisation and mapping, and structure from motion.

He is currently looking at the problems of recognising, modelling, and predicting human actions, poses and human-object interactions with a view to facilitate robot-human interaction as part of a Centre project.

Vibha completed her Bachelor degree in Mechatronics Engineering from Monash University (Malaysian campus) before completing her Masters in Robotics at the University of Pennsylvania. While at UPenn, she was part of the team who competed in RoboCup 2013 and won the Humanoid League. She joined the Centre in 2019 and is completing her PhD in Efficient Reinforcement Learning for Robotics supervised by Research Fellow Juxi Leitner and Associate Investigator Thierry Peynot.

Vibha is highly interested in understanding how the human brain works and emulating it in artificial agents, and believes curious agents are a step towards achieving it.

Luke graduated with a bachelor of electrical and computer systems engineering (honors) from Monash University.  He then worked in engineering consulting before returning to Monash to start his PhD in 2018. Luke is researching generalisation and memory in deep reinforcement learning. In his free time, he enjoys hobby electronics and is involved in the maker community.

Tom Drummond is a Professor and Head of the Department of Electrical and Computer Systems Engineering at Monash University. He is also the Monash Node Leader and sits on the Executive Committee of the ARC Centre of Excellence for Robotic Vision. He has been awarded the Könderink prize and the IEE International Symposium on Mixed and Augmented Reality (ISMAR) 10 year impact award.

He studied a BA in mathematics at the University of Cambridge.  In 1989 he emigrated to Australia and worked for CSIRO in Melbourne for four years before moving to Perth for his PhD in Computer Science at Curtin University.  In 1998 he returned to the University of Cambridge as a Postdoctoral Research Associate and in 1991 was appointed to the position of Lecturer.  In 2010 he returned to Melbourne and took up a Professorship at Monash University.  His research is principally in the field of real-time computer vision (ie processing of information from a video camera in a computer in real-time typically at frame rate), machine learning and robust methods. These have applications in augmented reality, robotics, assistive technologies for visually impaired users as well as medical imaging. During his time at both the University of Cambridge and Monash University he has been awarded research and industry grands in excess of $30M AUD.

Jordan graduated from QUT in 2017 with first class honours in a Bachelor of Mechatronic Engineering.  He worked with QUT’s team for the Amazon Picking Challenge, as well as working on a CSIRO project involving developing autonomous surveying with UAVs. He started his PhD in 2018 and is supervised by Centre Research Affiliate and QUT Research Fellow Chris Lehnert, Research Fellow Juxi Leitner and Centre Director Peter Corke. His field of study involves developing and improving generalisable robotic manipulation skills.

Luis Guerra completed a Bachelor of Electronics Engineering (2013) and a Masters of Science in Digital Signal Processing (2015) in Chihuahua, Mexico. During his undergraduate studies, he completed an internship at the Advanced Materials Research Centre where he won a national research contest. Afterwards he entered the automotive industry as an embedded software developer for a year and then held a research position as Computer Vision Engineer in ADAS for another year. Luis started his PhD with the Centre at Monash University at the end of 2017. His research interests are focused on efficient heterogeneous deep learning implementations for embedded systems and constrained devices. He is supervised by Chief Investigator Professor Tom Drummond.

Stephen Gould is a Professor in the Research School of Computer Science at ANU. He is also the ANU Node Leader and sits on the Executive Committee of the ARC Centre of Excellence for Robotic Vision.

He received his BSc Degree in Mathematics and Computer Science and BE Degree in Electrical Engineering from the University of Sydney in 1994 and 1996, respectively. He received his MS Degree in Electrical Engineering from Stanford University in 1998 and his PhD, also from Stanford in 2010. He then worked in industry for a number of years where he co-founded Sensory Networks, which sold to Intel in 2013. His research interests include computer and robotic vision, machine learning, probabilistic graphical models, deep learning and optimisation.

In 2017 Steve spent a year in Seattle leading a team of computer vision researchers and engineers at Amazon before returning to Australia in 2018.  He was awarded an ARC Future Fellowship in 2020 for the project, “Declarative Networks; Towards Robust and Explainable Deep Learning”.

Kartik joined the Centre as an associated PhD researcher at ANU in 2018. He is currently working on neural network quantization. Before joining ANU, Kartik worked as a Research Engineer in machine learning for around 1.5 years. He completed his MS (by Research) degree in computer science from Indian Institute of Technology (IIT) Mandi in 2017, working mainly in the area of computer vision.  He also worked with Professor Darius Burschka as a DAAD research scholar at Technical University of Munich (TU Munich) during his Masters. In 2018, he began his research at ANU and Data61 CSIRO under the supervision of Professor Richard Hartley.

Ben studied undergraduate courses in Computer Science and Mechatronics Engineering at Monash University before then completing a PhD with the ACRV in the area of Computer Systems Engineering. Ben’s research has principally focused on developing and understanding efficient methods for the representation and retrieval of high dimensional big data.

In 2020 Ben joined CSIRO Data61 as a Postdoctoral Fellow in the Spatiotemporal Activity within the Machine Learning and Artificial Intelligence Future Science Platform. Ben’s current research interests include self-supervised learning, multi-modal representation learning, human-in-the-loop active learning and non-linear dimension reduction.

Gus completed his Bachelors degree in electrical engineering and arts (philosophy) at Monash University in 2015. He spent a few years alternately working, travelling and studying economics before returning to Monash in 2018 to start his PhD in robotic vision with Chief Investigator Professor Tom Drummond. His research aspires to better understand how we can represent and model useful concepts like physics, objects, relations, and causality, which he anticipates might help lift the binding constraint in a number of robotics and vision domains.

In his free time Gus enjoys scuba diving, reading, cycling, and talking about social science.

Adrian completed his undergraduate degree in Computer Science at the University of Adelaide before joining a research group for twelve months, where he worked on software engineering tools for the Defense Science Technology Group. He then returned to complete his honours degree in Computer Science, graduating with first class honours. Prior to beginning his PhD, he worked as a software engineer for the Australian Institute for Machine Learning (AIML). He commenced PhD studies in 2015 under the supervision of Professor Gustavo Carneiro. Adrian’s PhD research is focused on 3D object reconstruction using Deep Learning. Adrian recently completed his PhD in September 2020. He has previously worked for LifeWhisperer developing Computer Vision and AI techniques for IVF. He is currently working towards launching his own company applying AI and Computer Vision to the natural sciences.

Rongkai joined the Centre in 2019 as a PhD researcher at Monash University under the supervision of Chief Investigator Professor Tom Drummond. In 2018, he received his bachelor degree (First Class Honours) in engineering from Monash and has a bachelor of Engineering from Central South University in Changsha, China. Rongkai is primarily interested in Deep Learning and its application in computer vision and robotics.

Ben completed his PhD in August 2019 at the Centre at Monash University, under the supervision of Tom Drummond. He continued his work at the Centre as a Research Fellow until July 2109. Ben’s research focuses primarily on deep learning, with particular interest in the problems of metric learning, novelty detection, open set recognition, active learning and generative models.

Dimity joined the Centre in 2018 after graduating from QUT in 2017 with First Class Honours in a Bachelor of Mechatronics Engineering. Dimity is currently completing her PhD on how to obtain uncertainty and robustness in deep learning for robotic vision. She is particularly interested in the reliability of deep learning in open-set conditions, where object classes that were not present in the training data are encountered.

Medhani is doing research under the supervison of Hondong Li and Chuong Nguyen. Her research interests are Deeplearning, computer vision, Robotics and control systems. She did a Bachelor of Science and Technology specializing in Mechatronics, Uva Wellassa University, Sri Lanka(2012). Medhani then followed with a Master of Science in robotics and control systems at University of Moratuwa, Sri Lanka (2014). She has several conference publications relevant to haptic and vibration suppression of bilateral control systems.  She is currently working on object classification and detection by using deeplearning.

Serena started her PhD with the Centre in 2018 after being introduced to research by her supervisor, Centre CI Dr. Niko Sünderhauf, when she completed a Vacation Research Experience Scheme (VRES) project in 2016/2017. This led to an Honours project supervised by Dr. Sünderhauf “Learning to Navigate with Reinforcement Learning”. Along with her interests in robotics, she also has a passion towards the protection and conservation of the environment. Surveying is important for understanding and protecting ecosystems but is repetitive, time consuming and expensive. By using her knowledge of deep learning and its associated frameworks, robotic task design, and semantic representation she is focusing on efficient detection of flora and fauna from aerial surveillance.

Vladimir joined the Centre as a PhD researcher in 2017 and graduated from the University of Adelaide in December 2020 under the supervision of Professor Ian Reid and Professor Chunhua Shen. He received Dean’s Commendation letter for his  thesis titled “Semantic Segmentation and Other Dense Per-Pixel Tasks: Practical Approaches”.

Cuong Nguyen is a PhD researcher at The University of Adelaide. He received his Bachelor degree from Portland State University, USA in 2012, and his MPhil degree from The University of Adelaide in 2018. He is interested in creating intelligent machines that can quickly learn from only a few examples. He joined the Centre in 2020 to research in meta-learning, a challenging field that builds algorithms for robots to quickly adapt to new tasks or new environments with a limited number of training examples. He is supervised by Centre Chief Investigator Gustavo Carneiro and is working in the Centre’s Learning Project.

Amir joined the Centre as PhD researcher at ANU supervised by Richard Hartley. His research interests are object detection, probabilistic graphical models, learning with limited labelled data, and deep neural network confidence calibration.

Maruf completed his bachelor’s and master’s degree from Department of Computer Science and Engineering, University of Dhaka, Bangladesh in 2012 and 2014 respectively. During his master’s degree, he started working in the software industry and has gained five years of industry experience before starting his PhD with the Centre in 2018. He is interested in applying deep learning in robotic vision and is supervised by Dr Feras Dayoub, Associate Professor Niko Sünderhauf and Centre Director Distinguished Prof. Peter Corke. His research topic is to identify the failure of a robotic vision system at run-time. This research is of paramount importance to improve the safety and reliability of vision-based robotic system during the deployment phase. Maruf is proficient in multiple deep learning and machine learning frameworks, and programming languages.

Krishan graduated with first class honours in a Bachelor of Mechatronics Engineering in 2018 and began his PhD with the Centre under the supervision of Dr Niko Suenderhauf and Prof Michael Milford soon after. His research is particularly focused on fusing classical control and deep reinforcement learning strategies for mobile robot navigation. He is additionally interested in methods which can allow policies trained in simulation to robustly transfer to real world scenarios.

Michele Sasdelli’s original background is in physics. He has studied and worked in five countries both in academic and industry environments. He worked as a Postdoctoral Researcher at the Astrophysics Research Institute in Liverpool, focusing on deep learning applications. He was a research scientist at Cortexica Vision Systems, an AI company in London working on deep learning based algorithms for computer vision.

His interests lie in fundamental machine learning questions for computer vision and astrophysics. He is a science enthusiast and firmly believes in cross-feeding between different research fields. He joined the Centre in 2018 as a Research Fellow at the University of Adelaide working in learning theory for deep learning.  He is now a member of AIML.

Itzik joined the Centre as a Research Fellow at the ANU node in July 2019. Previously, he was a PhD student at Technion Israel Institute of Technology where he worked on “Classification, segmentation, and geometric analysis of 3D point clouds using deep learning” under the supervision of Professor Anath Fischer and Michael Lindenbaum. Itzik completed his Bsc. Cum Laude in 2008 and his Msc. Summa Cum Laude in 2015 (Mechanical Engineering, Technion). His research interests lie at the intersection of robotic perception, 3D computer vision, and geometric analysis, usually using 3D point cloud data.

During his time at the Centre, he played a key role in the IKEA assembly dataset team, joined the RVSS organizing committee and presented DeepFit, a novel surface fitting method, at ECCV 2020 as an oral presentation./  His mission is to make beautifully practical and accessible 3D data algorithms to change the world.

Chunhua Shen is a Professor at School of Computer Science, University of Adelaide. He is also an adjunct Professor of Data Science and AI at Monash University.

Prior to that, he was with the computer vision program at NICTA (National ICT Australia), Canberra Research Laboratory for about six years. His research interests are in the intersection of computer vision and statistical machine learning. He studied at Nanjing University and at ANU and received his PhD degree from the University of Adelaide. From 2012 to 2016, he held an Australian Research Council Future Fellowship. He is Associate Editor (AE) of the Pattern Recognition journal, IEEE Transactions on Circuits and Systems for Video Technology and served as AEs for a few journals including IEEE Transactions on Neural Networks and Learning Systems.

Libo joined the Centre as a PhD researcher in 2019 at the University of Adelaide, under the supervision of Professor Chunhua Shen. Before this he worked as a project officer and research associate at Nanyang Technological University, Singapore. His current research interests are mainly in the field of robotics, computer vision, and deep learning. In his free time, Libo enjoys hiking and travelling and has visited many places of interest including the Terracotta Warriors, The Great Wall of China, and Angkor Wat in Cambodia.

Associate Professor Niko Suenderhauf is a Chief Investigator at the Centre where he leads the Robotic Vision Evaluation and Benchmarking project. As a member of the Executive Committee, Niko leads the Visual Learning and Understanding program at the QUT Centre for Robotics.  Niko conducts research in robotic vision, at the intersection of robotics, computer vision, and machine learning. His research interests focus on scene understanding and how robots can learn to perform complex tasks that require navigation and interaction with objects, the environment, and humans.

Associate Professor Suenderhauf is co-chair of the IEEE Robotics and Automation Society Technical Committee on Robotic Perception and regularly organises workshops at leading robotics and computer vision conferences.  He is member of the editorial board for the International Journal of Robotics Research (IJRR), and was Associate Editor for the IEEE Robotics and Automation Letters journal (RA-L) from 2015 to 2019. Niko served as AE for the IEEE International Conference on Robotics and Automation (ICRA) 2018 and 2020.

In his role as an educator at QUT, Niko enjoys teaching Introduction to Robotics (EGB339), Mechatronics Design 3 (EGH419), as well as Digital Signals and Image Processing (EGH444) to the undergraduate students in the Electrical Engineering degree.

Niko received his PhD from Chemnitz University of Technology, Germany in 2012. In his thesis, Niko focused on robust factor graph-based models for robotic localisation and mapping, as well as general probabilistic estimation problems, and developed the mathematical concepts of Switchable Constraints. After two years as a Research Fellow in Chemnitz, Niko joined QUT as a Research Fellow in March 2014, before being appointed to a tenured Lecturer position in 2017.

Brendan graduated from QUT in 2017 with a Bachelor of Engineering majoring in Mechatronics, achieving first class honors. In 2016 Brendan developed a tethered autonomous underwater vehicle as part of QUT’s entry to the Robotx Maritime challenge, travelling with the team to Hawaii. TeamQUT competed against 13 universities from around the world, where TeamQUT received second place.

Brendan joined the Centre in late 2017 under supervision of Dr Juxi Leitner and associate supervisor Distinguished Professor Peter Corke. In 2018 Dr Nicholas Hudson from Data61 at CSIRO joined his supervisory team, and in 2019 Dr Akansel Cosgun (Monash University) filled in for Dr Leitner. Brendan’s work uses reinforcement learning to control dynamic legged robots traversing challenging terrains. The focus of this work is on modularity, where any number of controllers can be combined to extend the mobility of a dynamic platform on unstructured environments.

This topic lead him to work with CSIRO as part of a team funded by DARPA in their latest robotics competition, a subterranean challenge. In the Subt challenge a team of robots (CSIRO’s team includes tracked, legged, and flying robots), commanded by a single operator must enter an underground scenario and localise target artifacts. The Subt challenge consists of 4 stages, including a Tunnel circuit (Aug 2019), Urban circuit (Feb 2020), Cave circuit (Oct 2020), and a final combination circuit (Aug 2021). Brendan has travelled with the team for all engagements thus far, and was one of two operators for the Urban and Cave circuits.

Max is currently a Data Scientist at AGL Energy in Melbourne, Australia. He completed his PhD at Monash University in December 2015 and was supervised by Associate Investigator Ahmet Sekercioglu and Chief Investigator Tom Drummond. His research interests include robotic vision, machine learning and distributed systems.

Yunyan completed her Bachelor of Electrical and Computer System Enginnering degree at Monash University in 2017, graduating with first class honours. She started her PhD at Monash University in 2018 and is supervised by Professor Tom Drummond. Her current research focuses on utilising deep reinforcement learning to improve video prediction.

Alan completed a double degree in 2017 with a Bachelor of Engineering and Bachelor of Science at Monash University, graduating with first class honours. He is currently supervised by Chief Investigator Tom Drummond in the field of Computer Vision and Artificial Intelligence. His current research goal is to investigate how to use the advantage of attention mechanism and distance metric to improve the performance of metric learning applications.

Jing Zhang is currently a PhD student with Research School of Electrical, Energy and Materials Engineering, ANU.  Her main research interests include saliency detection, weakly supervised learning, generative model. She won the Best Student Paper Prize at DICTA 2017, the Best Deep/Machine Learning Paper Prize at APSIPA ASC 2017 and the Best Paper Award Nominee at IEEE CVPR 2020.

Tong Zhang joined the Centre as a PhD researcher at ANU in 2018. He obtained his masters degree from New York University in 2014 and his bachelor degree from Beihang University in 2011. He is mainly working on subspace clustering, weakly-supervised learning and generative models.

Bohan joined the Centre as a Research Fellow after completing his PhD at the University of Adelaide in March 2018, supervised by Chief Investigators Chunhua Shen and Ian Reid.  He is currently a lecturer with the Faculty of Information Technology at Monash University.  His research interest is in compressing and accelerating deep neural networks for resource constraint devices. And he also focuses on a wide span of applications in Computer Vision. He completed his bachelor degree in Electrical Engineering in July, 2014 at Dalian University of Technology, China. During his undergraduate study, Bohan worked with Prof. Huchuan Lu. In his spare time, Bohan is a music amateur and has been playing piano since 4 years old.

Yan completed his PhD titled “Advances in Decision Forests and Ferns with Applications in Deep Representation Learning for Computer Vision” in 2019 under the supervision of Chief Investigator Professor Tom Drummond. During his PhD, his research focused on a family of learning algorithms categorised as ensemble learning methods. His work involved investigating methods for incorporating decision forests and decision ferns within deep learning frameworks and applying them to computer vision. These applications include a range of tasks including image classification, image segmentation, image synthesis and video prediction. He then joined the Centre as a Research Fellow in June 2019 and his current research is focused on solving problems in machine perceptron using learning approaches such as Generative Adversarial Networks and Reinforcement Learning for navigation and mapping within the Learning project of the Centre.