In outdoor environments shadows are common. These typically strong visual features cause considerable change in the appearance of a place, and therefore confound vision- based localisation approaches. In this work we describe how to convert a colour image of the scene to a greyscale invariant image where pixel values are a function of underlying [...]
This paper explores the suitability of commonly employed classification methods to action-selection tasks in robotics, and argues that a classifier’s introspective capacity is a vital but as yet largely under-appreciated attribute. As illustration we propose an active learning framework for semantic mapping in mobile robotics and demonstrate it in the context of autonomous driving. In [...]
Autonomous vehicles operating in places like parking lots can leverage of a higher-level understanding of the objects around it. For instance, the knowledge hat there is an upcoming zebra crossing should be taken into account in the vehicle’s current motion plan and speed. Also labelling of parking spots, could be crucial in other tasks as efficient assignment of [...]
The Digital Rail team is led by Akshay Morye and consists of postdoctoral researchers, D.Phil students, support engineers and industrial partners.
The Robotcar flagship team is led by Will Maddern and consists of postdoctoral researchers, D.Phil students, support engineers and industrial partners.
In the context of decision making in robotics, the use of a classification framework which produces scores with inappropriate confidences will ultimately lead to the robot making dangerous decisions. In order to select a framework which will make the best decisions, we should pay careful attention to the ways in which it generates scores. Precision [...]
This work addresses the difficult problem of navigation in changing, dynamic environments. Assuming the world is static in appearance results in brittle mapping and localisation systems. Change comes from many sources (dynamic objects, time of day, weather, seasons) and over different time scales (minutes, hours, days, months). In this work we look to account for these variations [...]
This work addresses the challenging problem of vision-based pose estimation in busy and distracting urban environments. By leveraging laser-generated 3D scene priors, we demonstrate how distracting objects of arbitrary types can be identified and masked in order to improve egomotion estimation. Results from data collected in central London during the Olympics show how our system [...]
This work is about extending the reach and endurance of outdoor localisation using stereo vision. At the heart of the localisation is the fundamental task of discovering feature correspondences between recorded and live images. One aspect of this problem involves deciding where to look for correspondences in an image and the second is deciding what [...]
Learning Place-Dependent Feature Detectors for Localisation Across Extreme Lighting and Weather Conditions
This work is about metric localisation across extreme lighting and weather conditions. The typical approach in robot vision is to use a point-feature-based system for localisation tasks. However, these system typically fail when appearance changes are too drastic. This research takes a contrary view and asks what is possible if instead we learn a bespoke detector for every place. [...]