Professor Niko Suenderhauf

Research Project Leadership I am a Chief Investigator of the Australian Centre for Robotic Vision. In this role, I lead the project on Robotic Vision Evaluation and Benchmarking, and am deputy project leader for the Centre's Scene Understanding project. Robotic Vision Evaluation and Benchmarking (2018 – Present) Big benchmark competitions like ILSVRC or COCO fuelled much of the progress in computer vision and deep learning over the past years. We aim to recreate this success for robotic vision. To this end, we develop a set of new benchmark challenges for robotic vision that evaluate probabilistic object detection, scene understanding, uncertainty estimation, continuous learning for domain adaptation, continuous learning to incorporate previuosly unseen classes, active learning, and active vision. We combine the variety and complexity of real-world data with the flexibility of synthetic graphics and physics engines. See project

Scene Understanding and Semantic SLAM (2017 – Present) Making a robot understand what it sees is one of the most fascinating goals in my current research. To this end, we develop novel methods for Semantic Mapping and Semantic SLAM by combining object detection with simultaneous localisation and mapping (SLAM) techniques. We furthermore work on Bayesian Deep Learning for object detection, to better understand the uncertainty of a deep network’s predictions and integrate deep learning into robotics in a probabilistic way. See project

Bayesian Deep Learning and Uncertainty for Object Detection (2017 – Present) In order to fully integrate deep learning into robotics, it is important that deep learning systems can reliably estimate the uncertainty in their predictions. This would allow robots to treat a deep neural network like any other sensor, and use the established Bayesian techniques to fuse the network’s predictions with prior knowledge or other sensor measurements, or to accumulate information over time. We focus on Bayesian Deep Learning approaches for the specific use case of object detection on a robot in open-set conditions. See project

Reinforcement Learning for Robot Navigation and Complex Task Execution (2017 – Present) How can robots best learn to navigate in challenging environments and execute complex tasks, such as tidying up an apartment or assist humans in their everyday domestic chores? Often, hand-written architectures are based on complicated state machines that become intractable to design and maintain with growing task complexity. I am interested in developing learning-based approaches are effective and efficient, and scale better to complicated tasks. See project

Visual Place Recognition in Changing Environments (2012 – Present) An autonomous robot that operates on our campus should be able to recognize different places when it comes back to them after some time. This is important to support reliable navigation and localisation and therefore enable the robot to perform a useful task. The problem of visual place recognition gets challenging if the visual appearance of these places changed in the meantime. This usually happens due to changes in the lighting conditions (think day vs. night or early morning vs. late afternoon), shadows, different weather conditions, or even different seasons. We develop algorithms for vision-based place recognition that can deal with these changes in visual appearance. See project

Organised Research Workshops Dedicated workshops are a great way of getting in contact with fellow researchers from around the world that are working on similar scientific questions. Over the past years I was lead organiser or co-organiser for these workshops at leading international conferences:

• The Importance of Uncertainty in Deep Learning for Robotics (IROS 2019)
• Robotic Vision Probabilistic Object Detection Challenge (CVPR 2019)
• Deep Learning for Semantic Visual Navigation (CVPR 2019)
• New Benchmarks, Metrics, and Competitions for Robotic Learning (RSS 2018)
• Real-World Challenges and New Benchmarks for Deep Learning in Robotic Vision (CVPR 2018)
• Long-term autonomy and deployment of intelligent robots in the real-world (ICRA 2018)
• Learning for Localization and Mapping (IROS 2017)
• New Frontiers for Deep Learning in Robotics (RSS 2017)
• Deep Learning for Robotic Vision (CVPR 2017)
• Are the Sceptics Right? - Limits and Potentials of Deep Learning in Robotics (RSS 2016)
• Visual Place Recognition: What is it good for? (RSS 2016)
• Visual Place Recognition in Changing Environments (ICRA 2015)
• Visual Place Recognition in Changing Environments (CVPR 2015)
• Visual Place Recognition in Changing Environments (ICRA 2014)
• Robust and Multimodal Inference in Factor Graphs (ICRA 2013)