The picture below illustrates the idea of place recognition: An autonomous robot that operates in an environment (for example our university campus) should be able to recognize different places when it comes back to them after some time. This is important to support reliable navigation, mapping, and localisation. Robust place recognition is therefore a crucial capability for an autonomous robot.
Challenges for Visual Place Recognition
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.
Convolutional Networks for Place Recognition under Challenging Conditions (ongoing since 2014)
In two papers published at RSS and IROS 2015 we explored how Convolutional Networks can be utilized for robust visual place recognition. We found that the features from middle layers of these networks are robust against appearance changes and can be used as change-robust landmark descriptors.
- Sünderhauf, N., Shirazi, S., Dayoub, F., Upcroft, B., Milford, M. (2015). On the Performance of ConvNet Features for Place Recognition. Proc. of IEEE International Conference on Intelligent Robots and Systems (IROS). Hamburg, Germany.
- Sünderhauf, N., Shirazi, S., Jacobson, A., Pepperell, E., Dayoub, F., Upcroft, B., Milford, M. (2015). Place Recognition With ConvNet Landmarks: Viewpoint-Robust, Condition-Robust, Training-Free. Proceedings of Robotics: Science and Systems (RSS), Rome, Italy.
Predicting Appearance Changes (2013 – 2015)
In earlier work, conducted at TU Chemnitz with colleagues Peer Neubert and Peter Protzel, we explored the possibilities of predicting the visual changes in appearance between different seasons. This is a more active approach to robust place recognition, since it aims at reaching robustness not by becoming invariant to changes, but rather learn them from experience, and use the learned model to predict how a place would appear under different conditions (e.g. in winter or in summer).
- Neubert, P., Sünderhauf, N., Protzel, P. (2015). Superpixel-based Appearance Change Prediction for Long-Term Navigation Across Seasons. Robotics and Autonomous Systems Journal.
- Neubert, P., Sünderhauf, N., Protzel, P. (2013). Appearance Change Prediction for Long-Term Navigation Across Seasons. Proc. of 6th European Conference on Mobile Robots (ECMR), Barcelona, Spain.
- Sünderhauf, N., Neubert, P., Protzel, P. (2013). Predicting the Change – A Step Towards Life-Long Operation in Everyday Environments. Proc. of Robotics: Science and Systems (RSS) Robotics Challenges and Vision Workshop, Berlin, Germany.
- Sünderhauf, N., Neubert, P., Protzel, P. (2013). Are We There Yet? Challenging SeqSLAM on a 3000 km Journey Across All Four Seasons. Proc. of Workshop on Long-Term Autonomy, IEEE International Conference on Robotics and Automation (ICRA), Karlsruhe, Germany.
- Sünderhauf, N., Protzel, P. (2011). BRIEF-Gist — Closing the Loop by Simple Means. Proc. of IEEE International Conference on Intelligent Robots and Systems (IROS), San Francisco, USA.