I am Chief Investigator of the QUT Centre for Robotics where I lead the Visual Understanding and Learning Program. I am furthermore Chief Investigator of the Australian Centre for Robotic Vision, and a Senior Lecturer (roughly equivalent to a tenured Assistant Professor position in the US system) at Queensland University of Technology (QUT) in Brisbane, Australia.
I conduct research in robotic vision, at the intersection of robotics, computer vision, and machine learning. My research interests focus on scene understanding, semantic SLAM, and new ways to incorporate semantics into reinforcement learning. I furthermore lead a project on new benchmarking challenges in robotic vision.
I am very honoured that my work was recognised through a Google Faculty Research Award (2018) and an Amazon Research Award (2020).
I regularly organise workshops at robotics and computer vision conferences, such as RSS, CVPR, and ICRA. I am member of the editorial board for the International Journal of Robotics Research (IJRR), and co-chair of the Technical Committee on Computer and Roboti Vision of IEEE the Robotics and Automation Society. I was Associate Editor for the IEEE Robotics and Automation Letters journal (RA-L) from 2015 to 2019, and served as AE for the IEEE International Conference on Robotics and Automation (ICRA) 2018 and 2020.
|Mar 5, 2020||We are hiring PhD students and postdocs! I am offering a 3 year contract for a postdoctoral research fellow to work with me on our Visual Learning and Understanding research program. If you are interested, please read the position description and contact me. The QUT Centre for Robotics is also offering fully funded PhD positions in a number of areas, including visual learning and understanding, perception and localisation, decision and control, physical interaction, and human interaction.|
|Feb 15, 2020||Our workshop proposal at ECCV has been accepted! We will organise a half-day workshop on Beyond mAP: Reasessing the Evaluation of Object Detectors and will run our Probabilistic Object Detection Challenge again.|
|Jan 25, 2020||Our paper Residual Reactive Navigation: Combining Classical and Learned Navigation Strategies for Deployment in Unknown Environments has been accepted for ICRA 2020. In this work led by Krishan Rana, we focus on improving the efficiency and generalisation of learned navigation strategies when transferred from their training environment to previously unseen environment. Check out the paper on arxiv, and the project website. Code is available too.|
|Dec 15, 2019||I had a fantastic week at the IEEE Robotics and Automation Society Summer School on Deep Learning for Robot Vision in Santiago, Chile! It felt very rewarding to interact with around 100 undergraduate, Master’s and PhD students from Chile, South America, and around the world – the next generation of robotics researchers. I gave an introduction to deep learning and two more lectures about two of my favourite research topics: uncertainty and reliability of deep learning, and semantic object-based SLAM.|
|Nov 9, 2019||Had a great time at IROS 2019 in Macau, catching up with colleagues and co-organising a workshop on the Importance of Uncertainty in Deep Learning for Robotics.|
|Sep 11, 2019||A short article about our Probabilistic Object Detection Challenge is published in the September issue of Nature Machine Intelligence. Read it here.|
|Sep 8, 2019||I have been nominated and appointed as one of two co-chairs for the IEEE Robotics and Automation Society Technical Committee on Robot Vision. I am looking forward to this new role alongside Davide Scaramuzza from the University of Zürich.|
|Jun 20, 2019||We will organise a workshop at IROS in Macau on the topic of The Importance of Uncertainty in Deep Learning for Robotics. I am really excited about this topic! A paper lead by Quazi Marufur Rahman with Feras Dayoub will be presented at IROS as well. Read the preview here: Did You Miss the Sign? A False Negative Alarm System for Traffic Sign Detectors.|
|Jun 7, 2019||Congratulations to Sean McMahon for being awarded his PhD for his research in “Direct Visual Hazard Affordance Detection”! I had the pleasure to be associate supervisor for Sean since he started as a PhD student with the Australian Centre for Robotic Vision in 2015.|
|Apr 10, 2019||Sourav Garg led a paper on Semantic–geometric visual place recognition: a new perspective for reconciling opposing views that just appeared in the International Journal for Robotics Research (IJRR). Joint work with Michael Milford.|