Underwater slam for estructured environments using and imaging sonar

Aquesta tesi tracta sobre el problema de la navegació per a vehicles submarins autònoms que operen en entorns artificials estructurats com ara ports, canals, plataformes marines i altres escenaris similars. A partir d'una estimació precisa de la posició en aquests entorns, les capacitats dels vehicles submarins s'incrementen notablement i s'obre una porta al seu funcionament autònom. El manteniment, inspecció i vigilància d'instal lacions marines són alguns exemples de possibles aplicacions. Les principals contribucions d'aquesta tesi consisteixen per una banda en el desenvolupament de diferents sistemes de localització per a aquelles situacions on es disposa d'un mapa previ de l'entorn i per l'altra en el desenvolupament d'una nova solució al problema de la Localització i Construcció Simultània de Mapes (SLAM en les seves sigles en anglès), la finalitat del qual és fer que un vehicle autònom creï un mapa de l'entorn desconegut que el rodeja i, al mateix temps, utilitzi aquest mapa per a determinar la seva pròpia posició. S'ha escollit un sonar d'imatges d'escaneig mecànic com a sensor principal per a aquest treball tant pel seu relatiu baix cost com per la seva capacitat per produir una representació detallada de l'entorn. Per altra banda, les particularitats de la seva operació i, especialment, la baixa freqúència a la que es produeixen les mesures, constitueixen els principals inconvenients que s'han hagut d'abordar en les estratègies de localització proposades. Les solucions adoptades per aquests problemes constitueixen una altra contribució d'aquesta tesi. El desenvolupament de vehicles autònoms i el seu ús com a plataformes experimentals és un altre aspecte important d'aquest treball. Experiments portats a terme tant en el laboratori com en escenaris reals d'aplicació han proporcionat les dades necessàries per a provar i avaluar els diferents sistemes de localització proposats.

A Parallel Hardware Architecture for Scale and Rotation Invariant Feature Detection

This paper proposes a parallel hardware architecture for image feature detection based on the Scale Invariant Feature Transform algorithm and applied to the Simultaneous Localization And Mapping problem. The work also proposes specific hardware optimizations considered fundamental to embed such a robotic control system on-a-chip. The proposed architecture is completely stand-alone; it reads the input data directly from a CMOS image sensor and provides the results via a field-programmable gate array coupled to an embedded processor. The results may either be used directly in an on-chip application or accessed through an Ethernet connection. The system is able to detect features up to 30 frames per second (320 x 240 pixels) and has accuracy similar to a PC-based implementation. The achieved system performance is at least one order of magnitude better than a PC-based solution, a result achieved by investigating the impact of several hardware-orientated optimizations oil performance, area and accuracy.

Combining visual features and Growing Neural Gas networks for robotic 3D SLAM

The use of 3D data in mobile robotics provides valuable information about the robot’s environment. Traditionally, stereo cameras have been used as a low-cost 3D sensor. However, the lack of precision and texture for some surfaces suggests that the use of other 3D sensors could be more suitable. In this work, we examine the use of two sensors: an infrared SR4000 and a Kinect camera. We use a combination of 3D data obtained by these cameras, along with features obtained from 2D images acquired from these cameras, using a Growing Neural Gas (GNG) network applied to the 3D data. The goal is to obtain a robust egomotion technique. The GNG network is used to reduce the camera error. To calculate the egomotion, we test two methods for 3D registration. One is based on an iterative closest points algorithm, and the other employs random sample consensus. Finally, a simultaneous localization and mapping method is applied to the complete sequence to reduce the global error. The error from each sensor and the mapping results from the proposed method are examined.

Towards Mapping of Rock Walls Using a UAV-Mounted 2D Laser Scanner in GPS Denied Environments

In geotechnical engineering, the stability of rock excavations and walls is estimated by using tools that include a map of the orientations of exposed rock faces. However, measuring these orientations by using conventional methods can be time consuming, sometimes dangerous, and is limited to regions of the exposed rock that are reachable by a human. This thesis introduces a 2D, simulated, quadcopter-based rock wall mapping algorithm for GPS denied environments such as underground mines or near high walls on surface. The proposed algorithm employs techniques from the field of robotics known as simultaneous localization and mapping (SLAM) and is a step towards 3D rock wall mapping. Not only are quadcopters agile, but they can hover. This is very useful for confined spaces such as underground or near rock walls. The quadcopter requires sensors to enable self localization and mapping in dark, confined and GPS denied environments. However, these sensors are limited by the quadcopter payload and power restrictions. Because of these restrictions, a light weight 2D laser scanner is proposed. As a first step towards a 3D mapping algorithm, this thesis proposes a simplified scenario in which a simulated 1D laser range finder and 2D IMU are mounted on a quadcopter that is moving on a plane. Because the 1D laser does not provide enough information to map the 2D world from a single measurement, many measurements are combined over the trajectory of the quadcopter. Least Squares Optimization (LSO) is used to optimize the estimated trajectory and rock face for all data collected over the length of a light. Simulation results show that the mapping algorithm developed is a good first step. It shows that by combining measurements over a trajectory, the scanned rock face can be estimated using a lower-dimensional range sensor. A swathing manoeuvre is introduced as a way to promote loop closures within a short time period, thus reducing accumulated error. Some suggestions on how to improve the algorithm are also provided.

Sistema de modelização tridimensional de galerias subterrâneas

A presente dissertação apresenta uma solução para o problema de modelização tridimensional de galerias subterrâneas. O trabalho desenvolvido emprega técnicas provenientes da área da robótica móvel para obtenção um sistema autónomo móvel de modelização, capaz de operar em ambientes não estruturados sem acesso a sistemas de posicionamento global, designadamente GPS. Um sistema de modelização móvel e autónomo pode ser bastante vantajoso, pois constitui um método rápido e simples de monitorização das estruturas e criação de representações virtuais das galerias com um elevado nível de detalhe. O sistema de modelização desloca-se no interior dos túneis para recolher informações sensoriais sobre a geometria da estrutura. A tarefa de organização destes dados com vista _a construção de um modelo coerente, exige um conhecimento exacto do percurso praticado pelo sistema, logo o problema de localização da plataforma sensorial tem que ser resolvido. A formulação de um sistema de localização autónoma tem que superar obstáculos que se manifestam vincadamente nos ambientes underground, tais como a monotonia estrutural e a já referida ausência de sistemas de posicionamento global. Neste contexto, foi abordado o conceito de SLAM (Simultaneous Loacalization and Mapping) para determinação da localização da plataforma sensorial em seis graus de liberdade. Seguindo a abordagem tradicional, o núcleo do algoritmo de SLAM consiste no filtro de Kalman estendido (EKF { Extended Kalman Filter ). O sistema proposto incorpora métodos avançados do estado da arte, designadamente a parametrização em profundidade inversa (Inverse Depth Parametrization) e o método de rejeição de outliers 1-Point RANSAC. A contribuição mais importante do método por nós proposto para o avanço do estado da arte foi a fusão da informação visual com a informação inercial. O algoritmo de localização foi testado com base em dados reais, adquiridos no interior de um túnel rodoviário. Os resultados obtidos permitem concluir que, ao fundir medidas inerciais com informações visuais, conseguimos evitar o fenómeno de degeneração do factor de escala, comum nas aplicações de localização através de sistemas puramente monoculares. Provámos simultaneamente que a correcção de um sistema de localização inercial através da consideração de informações visuais é eficaz, pois permite suprimir os desvios de trajectória que caracterizam os sistemas de dead reckoning. O algoritmo de modelização, com base na localização estimada, organiza no espaço tridimensional os dados geométricos adquiridos, resultando deste processo um modelo em nuvem de pontos, que posteriormente _e convertido numa malha triangular, atingindo-se assim uma representação mais realista do cenário original.

Exploração da Point Cloud Library aplicada à percepção em sistemas autónomos

A navegação e a interpretação do meio envolvente por veículos autónomos em ambientes não estruturados continua a ser um grande desafio na actualidade. Sebastian Thrun, descreve em [Thr02], que o problema do mapeamento em sistemas robóticos é o da aquisição de um modelo espacial do meio envolvente do robô. Neste contexto, a integração de sistemas sensoriais em plataformas robóticas, que permitam a construção de mapas do mundo que as rodeia é de extrema importância. A informação recolhida desses dados pode ser interpretada, tendo aplicabilidade em tarefas de localização, navegação e manipulação de objectos. Até à bem pouco tempo, a generalidade dos sistemas robóticos que realizavam tarefas de mapeamento ou Simultaneous Localization And Mapping (SLAM), utilizavam dispositivos do tipo laser rangefinders e câmaras stereo. Estes equipamentos, para além de serem dispendiosos, fornecem apenas informação bidimensional, recolhidas através de cortes transversais 2D, no caso dos rangefinders. O paradigma deste tipo de tecnologia mudou consideravelmente, com o lançamento no mercado de câmaras RGB-D, como a desenvolvida pela PrimeSense TM e o subsequente lançamento da Kinect, pela Microsoft R para a Xbox 360 no final de 2010. A qualidade do sensor de profundidade, dada a natureza de baixo custo e a sua capacidade de aquisição de dados em tempo real, é incontornável, fazendo com que o sensor se tornasse instantaneamente popular entre pesquisadores e entusiastas. Este avanço tecnológico deu origem a várias ferramentas de desenvolvimento e interacção humana com este tipo de sensor, como por exemplo a Point Cloud Library [RC11] (PCL). Esta ferramenta tem como objectivo fornecer suporte para todos os blocos de construção comuns que uma aplicação 3D necessita, dando especial ênfase ao processamento de nuvens de pontos de n dimensões adquiridas a partir de câmaras RGB-D, bem como scanners laser, câmaras Time-of-Flight ou câmaras stereo. Neste contexto, é realizada nesta dissertação, a avaliação e comparação de alguns dos módulos e métodos constituintes da biblioteca PCL, para a resolução de problemas inerentes à construção e interpretação de mapas, em ambientes indoor não estruturados, utilizando os dados provenientes da Kinect. A partir desta avaliação, é proposta uma arquitectura de sistema que sistematiza o registo de nuvens de pontos, correspondentes a vistas parciais do mundo, num modelo global consistente. Os resultados da avaliação realizada à biblioteca PCL atestam a sua viabilidade, para a resolução dos problemas propostos. Prova da sua viabilidade, são os resultados práticos obtidos, da implementação da arquitectura de sistema proposta, que apresenta resultados de desempenho interessantes, como também boas perspectivas de integração deste tipo de conceitos e tecnologia em plataformas robóticas desenvolvidas no âmbito de projectos do Laboratório de Sistemas Autónomos (LSA).

Towards a Mobile Three-dimensional Modelling System for Underground Structures

Robotica 2012: 12th International Conference on Autonomous Robot Systems and Competitions April 11, 2012, Guimarães, Portugal

Application of Visual-Inertial SLAM for 3D Mapping of Underground Environments

The underground scenarios are one of the most challenging environments for accurate and precise 3d mapping where hostile conditions like absence of Global Positioning Systems, extreme lighting variations and geometrically smooth surfaces may be expected. So far, the state-of-the-art methods in underground modelling remain restricted to environments in which pronounced geometric features are abundant. This limitation is a consequence of the scan matching algorithms used to solve the localization and registration problems. This paper contributes to the expansion of the modelling capabilities to structures characterized by uniform geometry and smooth surfaces, as is the case of road and train tunnels. To achieve that, we combine some state of the art techniques from mobile robotics, and propose a method for 6DOF platform positioning in such scenarios, that is latter used for the environment modelling. A visual monocular Simultaneous Localization and Mapping (MonoSLAM) approach based on the Extended Kalman Filter (EKF), complemented by the introduction of inertial measurements in the prediction step, allows our system to localize himself over long distances, using exclusively sensors carried on board a mobile platform. By feeding the Extended Kalman Filter with inertial data we were able to overcome the major problem related with MonoSLAM implementations, known as scale factor ambiguity. Despite extreme lighting variations, reliable visual features were extracted through the SIFT algorithm, and inserted directly in the EKF mechanism according to the Inverse Depth Parametrization. Through the 1-Point RANSAC (Random Sample Consensus) wrong frame-to-frame feature matches were rejected. The developed method was tested based on a dataset acquired inside a road tunnel and the navigation results compared with a ground truth obtained by post-processing a high grade Inertial Navigation System and L1/L2 RTK-GPS measurements acquired outside the tunnel. Results from the localization strategy are presented and analyzed.

Depth sensors in augmented reality solutions. Literature review

The emergence of depth sensors has made it possible to track – not only monocular cues – but also the actual depth values of the environment. This is especially useful in augmented reality solutions, where the position and orientation (pose) of the observer need to be accurately determined. This allows virtual objects to be installed to the view of the user through, for example, a screen of a tablet or augmented reality glasses (e.g. Google glass, etc.). Although the early 3D sensors have been physically quite large, the size of these sensors is decreasing, and possibly – eventually – a 3D sensor could be embedded – for example – to augmented reality glasses. The wider subject area considered in this review is 3D SLAM methods, which take advantage of the 3D information available by modern RGB-D sensors, such as Microsoft Kinect. Thus the review for SLAM (Simultaneous Localization and Mapping) and 3D tracking in augmented reality is a timely subject. We also try to find out the limitations and possibilities of different tracking methods, and how they should be improved, in order to allow efficient integration of the methods to the augmented reality solutions of the future.

Real-Time Visual SLAM Using Pre - Existing Floor Lines as Landmarks and a Single Camera

SANTANA, André M.; SANTIAGO, Gutemberg S.; MEDEIROS, Adelardo A. D. Real-Time Visual SLAM Using Pre-Existing Floor Lines as Landmarks and a Single Camera. In: CONGRESSO BRASILEIRO DE AUTOMÁTICA, 2008, Juiz de Fora, MG. Anais... Juiz de Fora: CBA, 2008.

Técnicas visuais de localização e mapeamento simultâneos sem extração de primitivas geométricas da imagem

In Simultaneous Localization and Mapping (SLAM - Simultaneous Localization and Mapping), a robot placed in an unknown location in any environment must be able to create a perspective of this environment (a map) and is situated in the same simultaneously, using only information captured by the robot s sensors and control signals known. Recently, driven by the advance of computing power, work in this area have proposed to use video camera as a sensor and it came so Visual SLAM. This has several approaches and the vast majority of them work basically extracting features of the environment, calculating the necessary correspondence and through these estimate the required parameters. This work presented a monocular visual SLAM system that uses direct image registration to calculate the image reprojection error and optimization methods that minimize this error and thus obtain the parameters for the robot pose and map of the environment directly from the pixels of the images. Thus the steps of extracting and matching features are not needed, enabling our system works well in environments where traditional approaches have difficulty. Moreover, when addressing the problem of SLAM as proposed in this work we avoid a very common problem in traditional approaches, known as error propagation. Worrying about the high computational cost of this approach have been tested several types of optimization methods in order to find a good balance between good estimates and processing time. The results presented in this work show the success of this system in different environments

Navegação de robôs em ambientes internos usando slam

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Scene Reconstruction And Understanding By RGB-D Sensors

This thesis investigates interactive scene reconstruction and understanding using RGB-D data only. Indeed, we believe that depth cameras will still be in the near future a cheap and low-power 3D sensing alternative suitable for mobile devices too. Therefore, our contributions build on top of state-of-the-art approaches to achieve advances in three main challenging scenarios, namely mobile mapping, large scale surface reconstruction and semantic modeling. First, we will describe an effective approach dealing with Simultaneous Localization And Mapping (SLAM) on platforms with limited resources, such as a tablet device. Unlike previous methods, dense reconstruction is achieved by reprojection of RGB-D frames, while local consistency is maintained by deploying relative bundle adjustment principles. We will show quantitative results comparing our technique to the state-of-the-art as well as detailed reconstruction of various environments ranging from rooms to small apartments. Then, we will address large scale surface modeling from depth maps exploiting parallel GPU computing. We will develop a real-time camera tracking method based on the popular KinectFusion system and an online surface alignment technique capable of counteracting drift errors and closing small loops. We will show very high quality meshes outperforming existing methods on publicly available datasets as well as on data recorded with our RGB-D camera even in complete darkness. Finally, we will move to our Semantic Bundle Adjustment framework to effectively combine object detection and SLAM in a unified system. Though the mathematical framework we will describe does not restrict to a particular sensing technology, in the experimental section we will refer, again, only to RGB-D sensing. We will discuss successful implementations of our algorithm showing the benefit of a joint object detection, camera tracking and environment mapping.

Registro global de nuvens de pontos RGB-D em tempo real usando fluxo óptico e marcadores

Registration of point clouds captured by depth sensors is an important task in 3D reconstruction applications based on computer vision. In many applications with strict performance requirements, the registration should be executed not only with precision, but also in the same frequency as data is acquired by the sensor. This thesis proposes theuse of the pyramidal sparse optical flow algorithm to incrementally register point clouds captured by RGB-D sensors (e.g. Microsoft Kinect) in real time. The accumulated errorinherent to the process is posteriorly minimized by utilizing a marker and pose graph optimization. Experimental results gathered by processing several RGB-D datasets validatethe system proposed by this thesis in visual odometry and simultaneous localization and mapping (SLAM) applications.

Real-Time Visual SLAM Using Pre - Existing Floor Lines as Landmarks and a Single Camera

SANTANA, André M.; SANTIAGO, Gutemberg S.; MEDEIROS, Adelardo A. D. Real-Time Visual SLAM Using Pre-Existing Floor Lines as Landmarks and a Single Camera. In: CONGRESSO BRASILEIRO DE AUTOMÁTICA, 2008, Juiz de Fora, MG. Anais... Juiz de Fora: CBA, 2008.