5 postdoctoral positions at QUT
The ARC Centre of Excellence for Robotic Vision is leading the world in transformational research tackling the critical and complex challenge of applying computer vision to robotics. We believe that the ability to see, to visually understand the complex world around us and respond to it, is critical for the next generation of robots that will perform useful work in agriculture, environmental monitoring, healthcare, infrastructure inspection, construction and manufacturing.
We’re looking for five creative and imaginative postdoctoral researchers or engineers to join our team to solve real world problems working at the intersection of robotics, vision, learning and applications.
We’re particularly looking for people passionate about:
- integrating hardware and software to build impressive robotic systems that perceive, act, and interact with the environment
- deploying state-of-the-art machine learning on robots in the real world
- integrating different fields of research, such as scene understanding, learning, probabilistic robotics, planning, and control
- addressing the mismatch between the performance of deep learned systems evaluated on datasets and the real world
- working in a large, diverse team of researchers at the intersection of robotics, vision, learning and applications
Ideally, you have experience in creating complex robotic software with ROS, and developing/applying deep learning architectures for tasks such as object detection, segmentation, reinforcement learning with common frameworks, including dataset preparation. You enjoy programming in Python and C++ and working in Linux.
In addition, you have specialised experience and interest in one or more of the following areas:
- Robotic grasping and manipulation
- Creating mobile manipulation demos including navigating in complex environments
- Designing novel mechanisms, for hands, arms and grippers, integrating tactile and haptic sensing
- Implementing vision-guided grasping systems
- Investigating (bimanual) object manipulation algorithms
- Integrating multi-modal robot sensing to improve manipulation (vision, tactile and force measurements)
- Experimentally evaluating robotic and computer vision systems
- Designing and conducting experiments to evaluate computer vision, machine learning, and robotics systems
- A profound understanding of currently used benchmark datasets, their evaluation metrics and their limitations with respect to robotic vision
- Working with simulations to better understand how robotic vision, computer vision, or machine learning systems behave in realistic scenarios. Experience with environments such as UnrealCV, OpenAI Gym is appreciated.
- Working with cloud commute services such as AWS, Amazon Turk, or Google Cloud Platform Services
- System integration and deployment of robotic systems
- Deploying learning techniques on robotic systems: from initial deployment, to data collection, update, and all the way to continuous/lifelong learning on robot systems
- Machine learning, reinforcement learning, computer vision
- Bayesian Deep Learning, introspection and uncertainty estimation in deep learning for robotic vision
- Deep reinforcement learning and imitation learning exploiting semantics, meta learning
- Transfer learning (sim-to-real, robot-to-robot)
- Semi-supervised and unsupervised learning
- Continuous learning and active learning on robotic platform
- continuous space reinforcement learning
- Developmental and generative models for robotic learning
- Attention and Artificial Curiosity
- Open set classification
- Autonomous vehicle demonstrators and research
- Develop and run centre-wide self-driving car research challenges and technical demonstrations, including the development of a standard miniature autonomous car platform and running of regular experiments on full-size self-driving cars and vehicle platforms,
- Conduct and facilitate collaborative research in SLAM, localization, perception, detection, sensing, scene understanding and action recognition in close collaboration with leading researchers across the centre’s 4 nodes,
- A working familiarity with computer vision, deep learning, machine learning, autonomous robots / vehicles and sensing hardware, and a strong track record in leading collaborative team activity.
You would join the Australian Centre for Robotic Vision (https://roboticvision.org) which is a partnership between four leading Australian universities. You’d be based at QUT in Brisbane — working with an inclusive group of people in a well equipped and modern lab in a very liveable city with a wonderful climate, see https://research.qut.edu.au/ras for details. Travel to the centre’s other nodes in Melbourne, Adelaide and Canberra will be required.
We are offering two year contracts with a salary range between AUD93,313 and AUD110,821 and can also offer some assistance with relocation expenses. These are positions without teaching obligations, but with opportunities to supervise undergraduate and graduate students.
The Australian Centre for Robotic Vision supports a flexible working environment. Subject to visa restrictions, the present position is available as either full‐time or part‐time. Women are strongly encouraged to apply. For information on the Centre’s benefits in regards to travel funding and assistance for families please contact email@example.com for an information sheet.
To apply please send an email to firstname.lastname@example.org and include a full CV, a description of your relevant experiences, and a research statement that describes your passion for robotic vision research, outlines the problems you want to work on, and the approaches you would like to take to address them. Closing date is 19 January 2018.
Centre staff at our recent annual symposium.
You can also search for current vacancies at each of our Australian partner institutions via the links below: