The original group in what is now the ORI, the Mobile Robotics Group is about building robots and systems which answer “where am I and what surrounds me?” On real vehicles in real-hard places.
It has a proud systems heritage, taking on ambitious field deployments which shine a light on what doesn’t work and has to be fixed by smart application of machine learning, AI and robotics expertise.
LiDAR Lateral Localisation Despite Challenging Occlusion from Traffic This paper presents a system for improving the robustness of LiDAR lateral localisation systems. This is made possible by including detections of road boundaries which are invisible to the sensor (due [...]
Look Around You: Sequence-based Radar Place Recognition with Learned Rotational Invariance Abstract - This paper details an application which yields significant improvements to the adeptness of place recognition with Frequency-Modulated Continuous-Wave radar - a commercially promising sensor poised for [...]
Real-time Kinematic Ground Truth for the Oxford RobotCar Dataset Abstract - We describe the release of reference data towards a challenging long-term localisation and mapping benchmark based on the large-scale Oxford RobotCar Dataset. The release includes 72 traversals of [...]
Kidnapped Radar: Topological Radar Localisation using Rotationally-Invariant Metric Learning Abstract - This paper presents a system for robust, large-scale topological localisation using Frequency-Modulated ContinuousWave (FMCW) scanning radar. We learn a metric space for embedding polar radar scans using CNN [...]
This blog post provides an overview of our paper: [bibtex key="ICRA19_porav"] Abstract We present a method for improving segmentation tasks on images affected by adherent rain drops and streaks. We introduce a novel stereo dataset recorded using a system that [...]