Environment mapping for mobile robots navigation using hierarchical neural network and omnivision

Autonomous robots must be able to learn and maintain models of their environments. In this context, the present work considers techniques for the classification and extraction of features from images in joined with artificial neural networks in order to use them in the system of mapping and localization of the mobile robot of Laboratory of Automation and Evolutive Computer (LACE). To do this, the robot uses a sensorial system composed for ultrasound sensors and a catadioptric vision system formed by a camera and a conical mirror. The mapping system is composed by three modules. Two of them will be presented in this paper: the classifier and the characterizer module. The first module uses a hierarchical neural network to do the classification; the second uses techiniques of extraction of attributes of images and recognition of invariant patterns extracted from the places images set. The neural network of the classifier module is structured in two layers, reason and intuition, and is trained to classify each place explored for the robot amongst four predefine classes. The final result of the exploration is the construction of a topological map of the explored environment. Results gotten through the simulation of the both modules of the mapping system will be presented in this paper. © 2008 IEEE.

Validation of novel 3-dimensional electrocardiographic mapping of atrial tachycardias by invasive mapping and ablation: a multicenter study

OBJECTIVES This study prospectively evaluated the role of a novel 3-dimensional, noninvasive, beat-by-beat mapping system, Electrocardiographic Mapping (ECM), in facilitating the diagnosis of atrial tachycardias (AT). BACKGROUND Conventional 12-lead electrocardiogram, a widely used noninvasive tool in clinical arrhythmia practice, has diagnostic limitations. METHODS Various AT (de novo and post-atrial fibrillation ablation) were mapped using ECM followed by standard-of-care electrophysiological mapping and ablation in 52 patients. The ECM consisted of recording body surface electrograms from a 252-electrode-vest placed on the torso combined with computed tomography-scan-based biatrial anatomy (CardioInsight Inc., Cleveland, Ohio). We evaluated the feasibility of this system in defining the mechanism of AT-macro-re-entrant (perimitral, cavotricuspid isthmus-dependent, and roof-dependent circuits) versus centrifugal (focal-source) activation-and the location of arrhythmia in centrifugal AT. The accuracy of the noninvasive diagnosis and detection of ablation targets was evaluated vis-à-vis subsequent invasive mapping and successful ablation. RESULTS Comparison between ECM and electrophysiological diagnosis could be accomplished in 48 patients (48 AT) but was not possible in 4 patients where the AT mechanism changed to another AT (n = 1), atrial fibrillation (n = 1), or sinus rhythm (n = 2) during the electrophysiological procedure. ECM correctly diagnosed AT mechanisms in 44 of 48 (92%) AT: macro-re-entry in 23 of 27; and focal-onset with centrifugal activation in 21 of 21. The region of interest for focal AT perfectly matched in 21 of 21 (100%) AT. The 2:1 ventricular conduction and low-amplitude P waves challenged the diagnosis of 4 of 27 macro-re-entrant (perimitral) AT that can be overcome by injecting atrioventricular node blockers and signal averaging, respectively. CONCLUSIONS This prospective multicenter series shows a high success rate of ECM in accurately diagnosing the mechanism of AT and the location of focal arrhythmia. Intraprocedural use of the system and its application to atrial fibrillation mapping is under way.

Electroanatomic mapping of the endocardium. Implication for catheter ablation of ventricular tachycardia.

The electroanatomic mapping system Carto((R)) with its combination of anatomic and electrophysiologic information has substantially improved our understanding of arrhythmia mechanisms and substrates in patients with ventricular tachycardia (VT) and structural heart disease. Identification of the individual arrhythmogenic substrate and successful ablation guided by the combination of sinus rhythm voltage mapping and conventional electrophysiologic techniques like pace and activation/entrainment mapping are best described for patients with recurrent VT in remote myocardial infarction. In about 75-90% of the patients, the target VT can be ablated with acute success and the patients remain free of any VT recurrence in up to 75%. First results of electroanatomically guided ablation in patients with arrhythmogenic right ventricular dysplasia are promising. Data on ablation of VT in other structural heart diseases are very limited, since the arrhythmogenic substrate is very diffuse, e. g., in dilated cardiomyopathy, or there are only small patient numbers, e. g., for cardiac sarcoidosis or monomorphic VT after repair of congenital heart disease. In this article, the current status of electroanatomically guided endocardial mapping and ablation of VT in patients with structural heart disease is described.

The Canyon System off Fimbulisen

In der vorliegenden Arbeit werden Daten einer systematischen Vermessung in der Lazarev Sea nahe des Fimbul-Ice-Shelfs (Fimbulisen) genutzt, die während der Expedition ANT XIX-2 mit dem Fächersonarsystem Hydrosweep DS-2 und dem Sedimentecholot Parasound erhoben wurden. Nach kurzer Darstellung der Hintergründe dieser durchgeführten Untersuchungen in dem Messgebiet wird allgemein auf wesentliche Aspekte der Hydroakustik hinsichtlich der Anwendung von Echolotsystemen eingegangen. Schwerpunktmäßig soll dabei der parametrischen Effekt, das Messprinzip parametrischer Sedimentecholote, behandelt werden. Nach anschließender Anführung zweier praktischer Anwendungen hydroakustischer Messverfahren anhand des Hydrosweep DS-2 und des Parasound-Systems wird eingehend deren Positionierung auf FS 'Polarstern' dargestellt, da sich bei der Aufbereitung der Messungen zeigte, dass sich das größte Problem der Daten beider Systeme in der minderwertigen Qualität der Navigationsdaten abzeichnete. Aus den bereinigten Tiefendaten der Fächersonarmessung wird ein digitales Geländemodell (DGM) mit einer Rasterweite von 100 m generiert. Dieses Modell liegt für die weitere Bearbeitung digital und in Form einer bathymetrischen Karte im Maßstab 1:250,000 vor, bei der die Topographie des Canyon-Systems nahe dem Fimbulisen durch Isolinien mit einer Aquidistanz von 50 m dargestellt wird. Die als Ergebnis der prozessierten Parasound-Daten erhaltenen Seismogramme, die gefiltert im digitalen Bildformat mit bekannter Start- und Endposition für einen definierten Tiefenbereich vorliegen, können zusammen mit dem DGM in einem dreidimensionalen Modell dargestellt werden. Dieses in digitaler Form vorliegende Modell kann durch den Nutzer interaktiv durchschritten und die darin enthaltenen Messergebnisse in ihrer Gesamtheit sowie in Detailansichten aus verschiedenen Perspektiven betrachtet werden, was das gegenseitige Verständnis und Einschätzung der Ergebnisse aus den beiden Messverfahren fördert. Diese gemeinsame Darstellungsweise eines digitalen Geländemodells in Kombination mit den Seismogramm-Bildern des Sedimentecholotes Parasound bietet sich auch hinsichtlich einer geologischen Klassifizierung der verschiedenen Echotypen und einer anschließenden Interpretation der Sedimentationsvorgänge in einem flächenhaft vermessenen Gebiet an.

Efficient high-resolution genetic mapping of mouse interspersed repetitive sequence PCR products, toward integrated genetic and physical mapping of the mouse genome.

The ability to carry out high-resolution genetic mapping at high throughput in the mouse is a critical rate-limiting step in the generation of genetically anchored contigs in physical mapping projects and the mapping of genetic loci for complex traits. To address this need, we have developed an efficient, high-resolution, large-scale genome mapping system. This system is based on the identification of polymorphic DNA sites between mouse strains by using interspersed repetitive sequence (IRS) PCR. Individual cloned IRS PCR products are hybridized to a DNA array of IRS PCR products derived from the DNA of individual mice segregating DNA sequences from the two parent strains. Since gel electrophoresis is not required, large numbers of samples can be genotyped in parallel. By using this approach, we have mapped > 450 polymorphic probes with filters containing the DNA of up to 517 backcross mice, potentially allowing resolution of 0.14 centimorgan. This approach also carries the potential for a high degree of efficiency in the integration of physical and genetic maps, since pooled DNAs representing libraries of yeast artificial chromosomes or other physical representations of the mouse genome can be addressed by hybridization of filter representations of the IRS PCR products of such libraries.

Portable 3D laser-camera calibration system with color fusion for SLAM

Nowadays, the use of RGB-D sensors have focused a lot of research in computer vision and robotics. These kinds of sensors, like Kinect, allow to obtain 3D data together with color information. However, their working range is limited to less than 10 meters, making them useless in some robotics applications, like outdoor mapping. In these environments, 3D lasers, working in ranges of 20-80 meters, are better. But 3D lasers do not usually provide color information. A simple 2D camera can be used to provide color information to the point cloud, but a calibration process between camera and laser must be done. In this paper we present a portable calibration system to calibrate any traditional camera with a 3D laser in order to assign color information to the 3D points obtained. Thus, we can use laser precision and simultaneously make use of color information. Unlike other techniques that make use of a three-dimensional body of known dimensions in the calibration process, this system is highly portable because it makes use of small catadioptrics that can be placed in a simple manner in the environment. We use our calibration system in a 3D mapping system, including Simultaneous Location and Mapping (SLAM), in order to get a 3D colored map which can be used in different tasks. We show that an additional problem arises: 2D cameras information is different when lighting conditions change. So when we merge 3D point clouds from two different views, several points in a given neighborhood could have different color information. A new method for color fusion is presented, obtaining correct colored maps. The system will be tested by applying it to 3D reconstruction.

Examination of myocardial electrophysiology using novel panoramic optical mapping techniques

Optical mapping of voltage signals has revolutionised the field and study of cardiac electrophysiology by providing the means to visualise changes in electrical activity at a high temporal and spatial resolution from the cellular to the whole heart level under both normal and disease conditions. The aim of this thesis was to develop a novel method of panoramic optical mapping using a single camera and to study myocardial electrophysiology in isolated Langendorff-perfused rabbit hearts. First, proper procedures for selection, filtering and analysis of the optical data recorded from the panoramic optical mapping system were established. This work was followed by extensive characterisation of the electrical activity across the epicardial surface of the preparation investigating time and heart dependent effects. In an initial study, features of epicardial electrophysiology were examined as the temperature of the heart was reduced below physiological values. This manoeuvre was chosen to mimic the temperatures experienced during various levels of hypothermia in vivo, a condition known to promote arrhythmias. The facility for panoramic optical mapping allowed the extent of changes in conduction timing and pattern of ventricular activation and repolarisation to be assessed. In the main experimental section, changes in epicardial electrical activity were assessed under various pacing conditions in both normal hearts and in a rabbit model of chronic MI. In these experiments, there was significant changes in the pattern of electrical activation corresponding with the changes in pacing regime. These experiments demonstrated a negative correlation between activation time and APD, which was not maintained during ventricular pacing. This suggests that activation pattern is not the sole determinant of action potential duration in intact hearts. Lastly, a realistic 3D computational model of the rabbit left ventricle was developed to simulate the passive and active mechanical properties of the heart. The aim of this model was to infer further information from the experimental optical mapping studies. In future, it would be feasible to gain insight into the electrical and mechanical performance of the heart by simulating experimental pacing conditions in the model.

Experiments in outdoor operation of RatSLAM

This paper shows initial results in deploying the biologically inspired Simultaneous Localisation and Mapping system, RatSLAM, in an outdoor environment. RatSLAM has been widely tested in indoor environments on the task of producing topologically coherent maps based on a fusion of odometric and visual information. This paper details the changes required to deploy RatSLAM on a small tractor equipped with odometry and an omnidirectional camera. The principal changes relate to the vision system, with others required for RatSLAM to use omnidirectional visual data. The initial results from mapping around a 500 m loop are promising, with many improvements still to be made.

A navigating rat animat

This paper presents a new rat animat, a rat-sized bio-inspired robot platform currently being developed for embodied cognition and neuroscience research. The rodent animat is 150mm x 80mm x 70mm and has a different drive, visual, proximity, and odometry sensors, x86 PC, and LCD interface. The rat animat has a bio-inspired rodent navigation and mapping system called RatSLAM which demonstrates the capabilities of the platform and framework. A case study is presented of the robot's ability to learn the spatial layout of a figure of eight laboratory environment, including its ability to close physical loops based on visual input and odometry. A firing field plot similar to rodent 'non-conjunctive grid cells' is shown by plotting the activity of an internal network. Having a rodent animat the size of a real rat allows exploration of embodiment issues such as how the robot's sensori-motor systems and cognitive abilities interact. The initial observations concern the limitations of the deisgn as well as its strengths. For example, the visual sensor has a narrower field of view and is located much closer to the ground than for other robots in the lab, which alters the salience of visual cues and the effectiveness of different visual filtering techniques. The small size of the robot relative to corridors and open areas impacts on the possible trajectories of the robot. These perspective and size issues affect the formation and use of the cognitive map, and hence the navigation abilities of the rat animat.

Modeling of a magneto-rheological (MR) fluid damper using a self tuning fuzzy mechanism

A magneto-rheological (MR) fluid damper is a semi-active control device that has recently begun to receive more attention in the vibration control community. However, the inherent nonlinear nature of the MR fluid damper makes it challenging to use this device to achieve high damping control system performance. Therefore the development of an accurate modeling method for a MR fluid damper is necessary to take advantage of its unique characteristics. Our goal was to develop an alternative method for modeling a MR fluid damper by using a self tuning fuzzy (STF) method based on neural technique. The behavior of the researched damper is directly estimated through a fuzzy mapping system. In order to improve the accuracy of the STF model, a back propagation and a gradient descent method are used to train online the fuzzy parameters to minimize the model error function. A series of simulations had been done to validate the effectiveness of the suggested modeling method when compared with the data measured from experiments on a test rig with a researched MR fluid damper. Finally, modeling results show that the proposed STF interference system trained online by using neural technique could describe well the behavior of the MR fluid damper without need of calculation time for generating the model parameters.

Training-free probability models for whole-image based place recognition

Whole-image descriptors such as GIST have been used successfully for persistent place recognition when combined with temporal filtering or sequential filtering techniques. However, whole-image descriptor localization systems often apply a heuristic rather than a probabilistic approach to place recognition, requiring substantial environmental-specific tuning prior to deployment. In this paper we present a novel online solution that uses statistical approaches to calculate place recognition likelihoods for whole-image descriptors, without requiring either environmental tuning or pre-training. Using a real world benchmark dataset, we show that this method creates distributions appropriate to a specific environment in an online manner. Our method performs comparably to FAB-MAP in raw place recognition performance, and integrates into a state of the art probabilistic mapping system to provide superior performance to whole-image methods that are not based on true probability distributions. The method provides a principled means for combining the powerful change-invariant properties of whole-image descriptors with probabilistic back-end mapping systems without the need for prior training or system tuning.

Autonomous multisensor calibration and closed-loop fusion for SLAM

The vast majority of current robot mapping and navigation systems require specific well-characterized sensors that may require human-supervised calibration and are applicable only in one type of environment. Furthermore, if a sensor degrades in performance, either through damage to itself or changes in environmental conditions, the effect on the mapping system is usually catastrophic. In contrast, the natural world presents robust, reasonably well-characterized solutions to these problems. Using simple movement behaviors and neural learning mechanisms, rats calibrate their sensors for mapping and navigation in an incredibly diverse range of environments and then go on to adapt to sensor damage and changes in the environment over the course of their lifetimes. In this paper, we introduce similar movement-based autonomous calibration techniques that calibrate place recognition and self-motion processes as well as methods for online multisensor weighting and fusion. We present calibration and mapping results from multiple robot platforms and multisensory configurations in an office building, university campus, and forest. With moderate assumptions and almost no prior knowledge of the robot, sensor suite, or environment, the methods enable the bio-inspired RatSLAM system to generate topologically correct maps in the majority of experiments.

Acoustic signatures of the seafloor: Tools for predicting grouper habitat

Groupers are important components of commercial and recreational fisheries. Current methods of diver-based grouper census surveys could potentially benefit from development of remotely sensed methods of seabed classification. The goal of the present study was to determine if areas of high grouper abundance have characteristic acoustic signatures. A commercial acoustic seabed mapping system, QTC View Series V, was used to survey an area near Carysfort Reef, Florida Keys. Acoustic data were clustered using QTC IMPACT software, resulting in three main acoustic classes covering 94% of the area surveyed. Diver-based data indicate that one of the acoustic classes corresponded to hard substrate and the other two represented sediment. A new measurement of seabed heterogeneity, designated acoustic variability, was also computed from the acoustic survey data in order to more fully characterize the acoustic response (i.e., the signature) of the seafloor. When compared with diver-based grouper census data, both acoustic classification and acoustic variability were significantly different at sites with and without groupers. Sites with groupers were characterized by hard bottom substrate and high acoustic variability. Thus, the acoustic signature of a site, as measured by acoustic classification or acoustic variability, is a potentially useful tool for stratifying diver sampling effort for grouper census.

人口统计信息空间可视化系统研究

Population research is a front area concerned by domestic and overseas, especially its researches on its spatial visualization and its geo-visualization system design, which provides a sound base for understanding and analysis of the regional difference in population distribution and its spatial rules. With the development of GIS, the theory of geo-visualization more and more plays an important role in many research fields, especially in population information visualization, and has been made the big achievements recently. Nevertheless, the current research is less attention paid to the system design for statistical-geo visualization for population information. This paper tries to explore the design theories and methodologies for statistical-geo-visualization system for population information. The researches are mainly focused on the framework, the methodologies and techniques for the system design and construction. The purpose of the research is developed a platform for population atlas by the integration of the former owned copy software of the research group in statistical mapping system. As a modern tool, the system will provide a spatial visual environment for user to analyze the characteristics of population distribution and differentiate the interrelations of the population components. Firstly, the paper discusses the essentiality of geo-visualization for population information and brings forward the key issue in statistical-geo visualization system design based on the analysis of inland and international trends. Secondly, the geo-visualization system for population design, including its structure, functionality, module, user interface design, is studied based on the concepts of theory and technology of geo-visualization. The system design is proposed and further divided into three parts: support layer, technical layer, user layer. The support layer is a basic operation module and main part of the system. The technical layer is a core part of the system, supported by database and function modules. The database module mainly include the integrated population database (comprises spatial data, attribute data and geographical features information), the cartographic symbol library, the color library, the statistical analysis model. The function module of the system consists of thematic map maker component, statistical graph maker component, database management component and statistical analysis component. The user layer is an integrated platform, which provides the functions to design and implement a visual interface for user to query, analysis and management the statistic data and the electronic map. Based on the above, China's E-atlas for population was designed and developed by the integration of the national fifth census data with 1:400 million scaled spatial data. The atlas illustrates the actual development level of the population nowadays in China by about 200 thematic maps relating with 10 map categories(environment, population distribution, sex and age, immigration, nation, family and marriage, birth, education, employment, house). As a scientific reference tool, China's E-atlas for population has already received the high evaluation after published in early 2005. Finally, the paper makes the deep analysis of the sex ratio in China, to show how to use the functions of the system to analyze the specific population problem and how to make the data mining. The analysis results showed that: 1. The sex ratio has been increased in many regions after fourth census in 1990 except the cities in the east region, and the high sex ratio is highly located in hilly and low mountain areas where with the high illiteracy rate and the high poor rate; 2. The statistical-geo visualization system is a powerful tool to handle population information, which can be used to reflect the regional differences and the regional variations of population in China and indicate the interrelations of the population with other environment factors. Although the author tries to bring up a integrate design frame of the statistical-geo visualization system, there are still many problems needed to be resolved with the development of geo-visualization studies.

A location-based communication platform: integrating file sharing with interpersonal contact

Gemstone Team FLIP (File Lending in Proximity)