Autonomous Underwater Vehicles (AUVs) have been used for a huge number of tasks ranging from commercial, military and research areas etc, while the fundamental function of a successful AUV is its localization and mapping ability. This report aims to review the relevant elements of localization and mapping for AUVs. First, a brief introduction of the concept and the historical development of AUV...

This paper describes a probabilistic approach to the problem of recognizing places based on their appearance. The system we present is not limited to localization, but can determine that a new observation comes from a previously unseen place, and so augment its map. Effectively this is a SLAM system in the space of appearance. Our probabilistic approach allows us to explicitly account for perce...

The last few years have seen the implementation of autonomous systems in industrial applications that operate in a reliable and consistent manner in areas such as stevedoring, mining, agriculture and a variety of indoor applications. To solve the localisation problem, these systems make use of either absolute information such as GPS, beacons at known positions or available maps of the environme...

In the event of an emergency due to a fire or other crisis, a necessary but time consuming pre-requisite, that could delay the real rescue operation, is to establish whether the ground or area can be entered safely by human emergency workers. The objective of the VIEWFINDER research project is to develop robots which have the primary task of gathering data. The robots are equipped with sensors ...

Detection and tracking of moving objects (DATMO) in crowded urban areas from a ground vehicle at high speeds is difficult because of a wide variety of targets and uncertain pose estimation from odometry and GPS/DGPS. In this paper we present a solution of the simultaneous localization and mapping (SLAM) with DATMO problem to accomplish this task using ladar sensors and odometry. With a precise ...

This paper describes problems to be solved when modelling a 3D object from images acquired by a visual sensor moved manually by an operator. The object is set on a plane ; the sensor is moved on a semisphere centered on the object. In order to build a 3D model from such a protocol, several functions must be developped : 2D and 3D data acquisition, motion estimation from interest points tracked ...

This paper presents an approach to Simultaneous Localization and Mapping (SLAM) based on stereo vision. Standard stereo techniques are used to estimate 3D scene structure (point clouds). Point clouds at subsequent times are registered to estimate robot motion, and used to build a global environment map. Preliminary experimental results are also presented and discussed. Key-Words: Robot localisa...

This paper will explore the relationship between sensory accuracy and Simultaneous Localization and Mapping (SLAM) performance. As inexpensive robots are developed with commodity components, the relationship between performance level and accuracy will need to be determined. Experiments are presented in this paper which compare various aspects of sensor performance such as maximum range, noise, ...

A common way of localization in robotics is using triangulation on a system composed of a sensor and some landmarks (which can be artificial or natural). First, when no identifying marks are set on the landmarks, their identification by a robust algorithm is a complex problem which may be solved thanks to correspondence graphs. Second, when the localization system has no a priori information ab...

In order to create a meaningful interface between robots and humans, we advance the notion that a ”collaborative cognitive workspace” should form the basis for a dynamic information exchange between robots and their operators. One way to achieve this is through mapping the environment at the semantic level. Instead of traditional SLAM methods, which do not interpret sensor information other tha...