Academic literature on the topic 'Navigation Map'

COORDENAÇÃO DE APERFEIÇOAMENTO DO PESSOAL DE ENSINO SUPERIOR<br>A utilização de visualizadores 3D é algo cada vez mais comum em diversos ramos de atividades. O surgimento de novas tecnologias, com o resultante aumento do poder de processamento dos computadores atuais, tornou possível a criação de ambientes virtuais 3D maiores e mais ricos em detalhes. No entanto, a navegação em ambientes 3D, especialmente os ambientes multiescala, ainda é um problema para muitos usuários. O objetivo deste trabalho é propor soluções para alguns problemas de navegação 3D, a fim de melhorar a experiência de uso nesse tipo de aplicação. Nesse sentido, são apresentadas técnicas que permitem ajustar automaticamente a velocidade de navegação, os planos de corte e o ponto de centro de rotação. É proposta também uma solução para a detecção e tratamento de colisão entre a câmera e os modelos da cena, além de uma técnica que visa impedir que os usuários fiquem perdidos quando nenhum objeto da cena é visualizado. Essas soluções são baseadas na construção e manutenção de uma estrutura chamada de cubo de distâncias (cube map, no original em inglês), que fornece informações sobre a localização espacial dos pontos da cena em relação à câmera. Atualmente em desenvolvimento no Tecgraf/PUC-Rio, o SiVIEP (Sistema de Visualização Integrado de Exploração e Produção) é um visualizador voltado para profissionais da área de exploração e produção de petróleo, que serviu para a detecção e entendimento dos problemas mencionados e para a validação das soluções implementadas.<br>The use of 3D viewers is becoming common in several activities. The appearance of new technologies, with the resulting increase in processing power, made possible the creation of larger and richer 3D virtual environments. However, the navigation in 3D environments, especially the multiscale ones, is still a problem for many users. The goal of this work is to propose solutions to some 3D navigation problems in order to improve the user experience with this kind of application. In this sense, techniques to automatically adjust the navigation speed, the clipping planes and the rotation center are presented. It is also proposed a solution for the detection and treatment of collision between the camera and the scene, and a technique that aims to prevent users from getting lost when no scene object is visualized. These solutions are based on the construction and maintenance of a structure called cube map, which provides information about the spatial location of the scene points relative to the camera. Currently in development at Tecgraf/PUCRio, the SiVIEP (Integrated Visualization System for Exploration and Production) is a viewer aimed at professionals in the area of oil exploration and production that was used to detect and understand the mentioned problems, and also for validating the implemented solutions.

Mobile robots are gaining increased autonomy due to advances in sensor and computing technology. In their current form however, robots still lack algorithms for rapid perception of objects in a cluttered environment and can benefit from the assistance of a human operator. Further, fully autonomous systems will continue to be computationally expensive and costly for quite some time. Humans can visually assess objects and determine whether a certain path is traversable, but need not be involved in the low-level steering around any detected obstacles as is necessary in remote-controlled systems. If only used for rapid perception tasks, the operator could potentially assist several mobile robots performing various tasks such as exploration, surveillance, industrial work and search and rescue operations. There is a need to develop better human-robot interaction paradigms that would allow the human operator to effectively control and manage one or more mobile robots. This paper proposes a method of enhancing user effectiveness in controlling multiple mobile robots through real-time map manipulation. An interface is created that would allow a human operator to add virtual obstacles to the map that represents areas that the robot should avoid. A video camera is connected to the robot that would allow a human user to view the robot's environment. The combination of real-time map editing and live video streaming enables the robot to take advantage of human vision, which is still more effective at general object identification than current computer vision technology. Experimental results show that the robot is able to plan a faster path around an obstacle when the user marks the obstacle on the map, as opposed to allowing the robot to navigate on its own around an unmapped obstacle. Tests conducted on multiple users suggest that the accuracy in placing obstacles on the map decreases with increasing distance of the viewing apparatus from the obstacle. Despite this, the user can take advantage of landmarks found in the video and in the map in order to determine an obstacle's position on the map.

Global navigation satellite systems (GNSS), such as the Global Positioning System (GPS) have been increasingly used in navigation and tracking of vehicles. Using GPS, certain positioning errors and limitations, such as multipath effects and the geometric position of the satellites (DOP) or signal obstructions by high buildings, trees and terrain, have to be considered. Generally travel on road or footpath, map-matching algorithms can be used to correlate the computed system location with a digital map network. Map Matched GPS (MMGPS) is a test-bed simulator for researching algorithms and techniques to reduce the error in position provided by a low cost stand-alone GPS receiver. In order to correctly map-match the GPS positions, a decision about the correct road can be difficult, especially at road junctions, slip roads or almost parallel roads. Investigations into the use of artificial neural networks (ANNs) for reliability and accuracy improvement of map-matched GPS positioning was initiated in previous research [Winter, 2002]. However, there are generally strong interference effects that lead to slow learning and poor generalization when a single ANN is trained to perform different subtasks on different occasions [Jacobs et al., 1991], e.g. correct transport network (TN) segment selection considering different TN geometry. Interference can be reduced by training a system composed of several different "expert" ANNs using a TN geometry indicator to decide which of the experts should be used for each training case. An aim of this research was the design, development and implementation of such a modular neural network (MNN). This work uses a new measure for indicating TN geometry, directly derived from GPS positions in MMGPS. An improvement of more than 50% to traditional map-matching techniques was achieved using the proposed MNN approach, when the correct road could not be uniquely identified by map-matching.

This thesis is on mobile robot navigation using range sensors. The two sensors types used are time-of-flight lasers and sheet-of-light range cameras, both giving densely spaced range measurements. Map generation and navi gation are achieved in indoor environments, even when there are lots of disturbing objects giving cluttered range measurements. The walls are observed in the range scans using the Range Weighted Hough Transform, (RWHT) and the estimates of the map and the robot position are maintained during motion using Extended Kalman Filtering (EKF). The calibration of sensor parameters during operation uses the relative motion given by the incremental encoders on the wheels as the absolute calibration reference. Matching of observations to previous estimates are performed using a deci sion directed classifier. The algorithms can be used both to build a map, or during navigation using an existing map. The algorithms have been verified in several experiment with the range sensors onboard actual mobile robots. The size of a large room was estimated with a standard deviation of 1 cm. The robot navigates autonomously through an open door detected by the laser. The accuracy during passage was 1 cm at a speed of 0.5 m/s. The trajectory is perpendicular to the wall within 0.5 degrees. In one experiment the robot created a map of its environment while moving at speeds from 0.5 to 1 m/s. The standard deviation in the esti mated map dimensions for a series of tests were 1 to 2 cm and 1 degree. The navigation system has also been used for an autonomous plastering robot with automatic planning to include doors and windows. The navigation is very robust against both outliers in the measurements and disturbing objects. It is not seriously disturbed even when most of the walls are occluded and there are several persons moving around during operation.

Thesis (Ph.D.)--Indiana University, Dept. of Computer Science, 2009.<br>Title from PDF t.p. (viewed on Feb. 10, 2010). Source: Dissertation Abstracts International, Volume: 70-05, Section: B, page: 3009. Adviser: David B. Leake.

Thesis: Ph. D., Massachusetts Institute of Technology, Department of Aeronautics and Astronautics, 2015.<br>Cataloged from PDF version of thesis.<br>Includes bibliographical references (pages 167-182).<br>Maps used for navigation often include a database of location descriptions for place-recognition (to enable localization or loop-closing), which permits bounded-error navigation performance. A standard localization system must describe the entire operational environment in its place-recognition database. A standard pose-graph-based simultaneous localization and mapping (SLAM) system adds a new place-recognition database entry for every new vehicle pose, which grows linearly and unbounded in time and thus becomes unsustainable. To address these issues, this thesis proposes a new map-reduction approach that pre-constructs a fixed-size place-recognition database amenable to the limited storage and processing resources of the vehicle by exploiting the high-level structure of the environment and vehicle motion. In particular, the thesis introduces the concept of location utility - which encapsulates the visitation probability of a location and its spatial distribution relative to nearby locations in the database - as a measure of the value of potential localization or loop-closure events to occur at that location. While finding the optimal reduced location database is NP-hard, an efficient greedy algorithm is developed to sort all the locations in a map based on their relative utility without access to sensor measurements or the vehicle trajectory. This enables predetermination of a generic, limited-size place-recognition database containing the N best locations in the environment. A street-map simulator using city-map data and a terrain relative navigation simulator using terrestrial rocket flight data are used to validate the approach and show that an accurate map and trajectory reconstruction (pose-graph) can be attained even when using a place-recognition database with only 1% of the entries of the corresponding full database.<br>by Theodore J. Steiner III.<br>Ph. D.