Mapping

/Mapping

The Mapping theme is all about building useful representations of workspaces. Sometimes these maps are used by our robots to localise. Sometimes the maps are themselves intrinsically valuable as surveys which contain both spatial and semantic information.

Building maps over large spatial scales and updating them over large temporal scales is both fascinating and challenging.  Large scale workspaces change appearance and geometry over time – in some places this is a creeping or a cyclical process, like day and night lighting; in others it is sudden, like trucks and crowds moving.

We use both cameras and lasers in our mapping work. Sometimes we build purely visual maps whilst in other cases we build dense 3D point clouds from laser sensors. Our most recent work concerns dense mapping from low cost cameras. Expect to see much more on this soon.

 

Our latest research

Semantic Mapping

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 ...
Read More

FAB-MAP 3D: Topological Mapping with Spatial and Visual Appearance

Abstract— This paper describes a probabilistic framework for appearance based navigation and mapping using spatial and visual appearance data. Like much recent work on appearance based navigation we adopt a bag-of-words approach in which positive or negative observations of visual ...
Read More

Generating Implicit Surfaces from Lidar Data

Abstract—This paper is concerned with generating a continuous implicit representation of a robot’s workspace using sparse point cloud data. We adopt a Gaussian Process (GP) framework to model the underlying workspace surfaces and suggest a non- parametric formulation which allows ...
Read More

FAB-MAP 3D: Topological Mapping with Spatial and Visual Appearance

Abstract— This paper describes a probabilistic framework for appearance based navigation and mapping using spatial and visual appearance data. Like much recent work on appearance based navigation we adopt a bag-of-words approach in which positive or negative observations of visual ...
Read More

Efficient Non-Parametric Surface Representations Using Active Sampling for Push Broom Laser Data

Abstract—This paper concerns the creation of efficient surface representations from laser point clouds. We produce a continuous, implicit, non-parametric representation with an update time that is constant. The algorithm places no restriction on the complexity of the underlying workspace surfaces ...
Read More

Discovering and Mapping Complete Surfaces With Stereo

This paper is about the automated discovery and mapping of surfaces using a stereo pair. We begin with the observation that for any workspace which is topologically connected (i.e. does not contain free flying islands) there exists a single surface ...
Read More

Adaptive compression for 3D laser data

Abstract - This paper concerns the creation of efficient surface representations from laser point clouds created by a push broom laser system. We produce a continuous, implicit, non-parametric and non-stationary representation with an update time that is constant. This allows us ...
Read More

Accelerating FAB-MAP with Concentration Inequalities

Abstract—We outline an approach for using concentration inequalities to perform rapid approximate multi-hypothesis testing. In a scenario where multiple hypotheses are ranked according to a large set of features, our scheme improves the efficiency of selecting the best hypothesis by ...
Read More

Leveraging Experience for Long-Term LIDAR Localisation In Changing Cities

 Successful approaches to autonomous vehicle localisation and navigation typically involve 3D LIDAR scanners and a static, curated 3D map, both of which are expensive to acquire and maintain. We propose an experience-based approach to matching a local 3D swathe built ...
Read More

Building, Curating, and Querying Large-scale Data Repositories for Field Robotics Applications

Abstract—Field robotics applications have some unique and unusual data requirements -- the curating, organisation and management of which are often overlooked. An emerging theme is the use of large corpora of spatiotemporally indexed sensor data which must be searched and ...
Read More

2016-10-23T13:30:57+00:00