Abstract — An important competence for a mobile robot system is the ability to localize and perform context interpretation. This is required to perform basic navigation and to facilitate local specific services. Usually localization is performed based on a purely geometric model. Through use of vision and place recognition a number of opportunities open up in terms of flexibility and association of semantics to the model. To achieve this the present paper presents an appearance based method for place recognition. The method is based on a large margin classifier in combination with a rich global image descriptor. The method is robust to variations in illumination and minor scene changes. The method is evaluated across several different cameras, changes in time-of-day and weather conditions. The results clearly demonstrate the value of the approach. I.

The ability to represent knowledge about space and its position therein is crucial for a mobile robot. To this end, topological and semantic descriptions are gaining popularity for augmenting purely metric space representations. In this paper we present a multi-modal place classification system that allows a mobile robot to identify places and recognize semantic categories in an indoor environment. The system effectively utilizes information from different robotic sensors by fusing multiple visual cues and laser range data. This is achieved using a high-level cue integration scheme based on a Support Vector Machine (SVM) that learns how to optimally combine and weight each cue. Our multi-modal place classification approach can be used to obtain a real-time semantic space labeling system which integrates information over time and space. We perform an extensive experimental evaluation of the method for two different platforms and environments, on a realistic off-line database and in a live experiment on an autonomous robot. The results clearly demonstrate the effec-

We present a robot localization system using biologically-inspired vision. Our system models two extensively studied human visual capabilities: (1) extracting the “gist” of a scene to produce a coarse localization hypothesis, and (2) refining it by locating salient landmark points in the scene. Gist is computed here as a holistic statistical signature of the image, yielding abstract scene classification and layout. Saliency is computed as a measure of interest at every image location, efficiently directing the time-consuming landmark identification process towards the most likely candidate locations in the image. The gist features and salient regions are then further processed using a Monte-Carlo localization algorithm to allow the robot to generate its position. We test the system in three different outdoor environments — building complex (38.4x54.86m area, 13966 testing images), vegetation-filled park (82.3x109.73m area, 26397 testing images), and open-field park (137.16x178.31m area, 34711 testing images) — each with its own challenges. The system is able to localize, on average, within 0.98, 2.63, and 3.46m, respectively, even with multiple kidnapped-robot instances.

In this paper we consider the problem of controlling the six degrees of freedom of a manipulator using the projection of 3D lines in the image plane of central catadioptric systems. Most of the e#ort in visual servoing are devoted to points, only few works have investigated the use of lines in visual servoing with traditional cameras and none has explored the case of omnidirectional cameras. First a generic interaction matrix for the projection of 3D straight lines is derived from the projection model of the entire class of central catadioptric cameras. Then an image-based control law is designed and validated through simulation results.

In this paper we consider the problem of controlling a robotic system using the projection of 3D lines in the image plane of central catadioptric systems. Most of the effort in visual servoing are devoted to points, only few works have investigated the use of lines in visual servoing with traditional cameras and none has explored the case of omnidirectional cameras. First a generic central catadioptric interaction matrix for the projection of 3D straight lines is derived from the projection model of an entire class of camera. Then an image-based control law is designed and validated through simulation results.

Abstract — We have demonstrated that a properlyequipped mobile robot can easily construct a detailed map of the wireless coverage of an urban environment. The Autonomous Vehicle for Exploration and Navigation of Urban Environments (AVENUE) mobile robot was successfully used to generate such maps in both manual and autonomous modes of operation. The resulting database contained a wealth of information for many different positions in the region, with a list of all access points viewable from each location together with a quality measure (the signal-to-noise ratio) of every detected signal. At a later time, the AVENUE system effectively used the data in this map to determine the approximate position of the robot as it traveled through the urban area. £ I.

Abstract — Localization and context interpretation are two key competences for mobile robot systems. Visual place recognition, as opposed to purely geometrical models, holds promise of higher flexibility and association of semantics to the model. Ideally, a place recognition algorithm should be robust to dynamic changes and it should perform consistently when recognizing a room (for instance a corridor) in different geographical locations. Also, it should be able to categorize places, a crucial capability for transfer of knowledge and continuous learning. In order to test the suitability of visual recognition algorithms for these tasks, this paper presents a new database, acquired in three different labs across Europe. It contains image sequences of several rooms under dynamic changes, acquired at the same time with a perspective and omnidirectional camera, mounted on a socket. We assess this new database with an appearancebased algorithm that combines local features with support vector machines through an ad-hoc kernel. Results show the effectiveness of the approach and the value of the database. I.

This paper describes a topological navigation system, based on the description of key-places by a reduced number of parameters that represent images associated to specific locations in configuration space, and the application of the developed system to robotic soccer, through the implementation of the developed algorithms to RoboCup MiddleSize League (MSL) robots, under the scope of the SocRob project (Soccer Robots or Society of Robots). A topological map is associated with a graph, where each node corresponds to a key-place. Using this approach, navigation is reduced to a graph path search. Principal Components Analysis was used to represent key-places from pre-acquired images and to recognize them at navigation time. The method revealed a promising performance navigating between key-places and proved to adapt to different graphs. Furthermore, it leads to a robot programming language based on qualitative descriptions of the target locations in configuration space (e.g., Near Blue Goal with the Goal on its Left). Simulation results of the method application are presented, using a realistic simulator.

We describe advances in automating the 3D modeling pipeline to create rich 3D textured models. Our work is aimed at large scale site modeling, where much manual effort is often needed to create complete models. We present i) an automatic 2D-3D registration method for texture using cast shadows as a cue to refine the registration parameters, ii) methods for change detection in an acquired model, and iii) a new mobile robot that can be used to automatically acquire data for modeling. 1.

Abstract. Robot self-localization using a hemispherical camera system can be done without correspondences. We present a view-based approach using view descriptors, which enables us to efficiently compare the image signal taken at different locations. A compact representation of the image signal can be computed using Spherical Harmonics as orthonormal basis functions defined on the sphere. This is particularly useful because rotations between two representations can be found easily. Compact view descriptors stored in a database enable us to compute a likelihood for the current view corresponding to a particular position and orientation in the map. 1