We study the problem of source localization as a multiple hypothesis testing, where each hypothesis corresponds to the event that the source belongs to a particular region. We use sequential hypothesis tests based on posterior computations to solve for the correct hypothesis. Measurements corrupted with noise are used to calculate conditional posteriors. We prove that the regional localization ...

This paper describes the role of the autonomous underwater vehicle (AUV) Sirius on a research cruise to survey drowned reefs along the shelf edge of the Great Barrier Reef in Queensland, Australia. The primary function of the AUV was to provide georeferenced, high-resolution optical validation of seabed interpretations based on acoustic data. We describe the AUV capabilities and its operation i...

This tutorial provides an introduction to Simultaneous Localisation and Mapping (SLAM) and the extensive research on SLAM that has been undertaken over the past decade. SLAM is the process by which a mobile robot can build a map of an environment and at the same time use this map to compute it’s own location. The past decade has seen rapid and exciting progress in solving the SLAM problem toget...

This paper concerns the building of enhanced scene maps during real-time monocular SLAM. Specifically, we present a novel algorithm for detecting and estimating planar structure in a scene based on both geometric and appearance and information. We adopt a hypothesis testing framework, in which the validity of planar patches within a triangulation of the point based scene map are assessed agains...

This paper presents new algorithms to implement simultaneous localisation and map building (SLAM) in environments with very large number of features. The algorithms present an efficient solution to the full update required by the Compressed Extended Kalman Filter algorithm (CEKF). It makes uses of the Relative Landmark Representation (RLR) to develop very close to optimal de-correlation solutio...

This paper introduces a fully Bayesian reformulation of Interaction Primitives for human-robot interaction and collaboration. A key insight is that a subset of human-robot interaction is conceptually related to simultaneous localization and mapping techniques. Leveraging this insight we can significantly increase the accuracy of temporal estimation and inferred trajectories while simultaneously...

This paper presents identifies and addresses the difficulties that arise from implementing visual information into the Simultaneous Localization and Mapping (SLAM) problem, with an emphasis for outdoor applications. Through identifying these problems, techniques for integrating the visual & navigation are proposed with results from their preliminary applications. Video data is gathered through ...

In this paper we propose a method for vision only topological simultaneous localisation and mapping (SLAM). Our approach does not use motion or odometric information but a sequence of noisy visual measurements observed by traversing an environment. In particular, we address the perceptual aliasing problem which occurs using external observations only in topological navigation. We propose a Baye...

In this paper we present an implementation of the Rao-Blackwellised particle filtering (RBPF) with one step look-ahead and apply the algorithm within the domain of agent navigation. Specifically we tackle the simultaneous localization and mapping problem (SLAM), which describes how a agent must concurrently attempt to determine its location and generate a map of the surrounding landmarks. Our i...

Most existing appearance models for visual tracking usually construct a pixel-based representation of object appearance so that they are incapable of fully capturing both global and local spatial layout information of object appearance. In order to address this problem, we propose a novel spatial LogEuclidean appearance model (referred as SLAM) under the recently introduced Log-Euclidean Rieman...