Search

This article presents an experimental assessment of a hash-based loop closure detection methodology specially addressed to Multi-robot underwater visual Simultaneous Localization and Mapping (SLAM). This methodology uses two diferent top quality image global descriptors, one learned (NetVLAD) and one handcrafted (HALOC). Complete tests were done to compare the performance of both hashing techniques applied in an extensive set of real underwater imagery.

This paper presents the design and assessment of an USBL-aided navigation approach for Autonomous Underwater Vehicles (AUV). The system integrates an Ultra-Short Base Line (USBL) acoustic modem and positioning device in a two-parallel Extended Kalman Filter (EKF) navigation schema, which also includes the measurements provided by an Inertial Measurement Unit (IMU), a Doppler Velocity Log (DVL), a Visual Odometer (VO), a pressure sensor, and a Global Positioning System (GPS). In order to be integrated in the estimation filter, the precision of the USBL measurements is derived experimentally. Moreover, the accuracy of the system is evaluated using a ground truth (GT) trajectory produced by a visual Simultaneous Localization and Mapping (SLAM) approach. Experimental results are obtained from marine datasets gathered in the north coast of Mallorca with an AUV, model SPARUS II.

This paper presents the new payload for Turbot, the SPARUS II AUV unit, manufactured by the University of Girona and recently acquired by the Systems, Robotics and Vision Group of the University of the Balearic Islands. The new payload has been entirely designed and integrated to host all elements necessary to perform visual 2D/3D mapping, optical (visuallaser) object reconstruction, acoustic and visual obstacle avoidance, and acoustic localization and communication. Several experiments in shallow waters of Mallorca show the validity of the sensor integration and operation for all the required tasks.

Detection and mapping of Posidonia Oceanica (P.O.) meadows in the Mediterranean sea is crucial to preserve the endemic ecosystems and to underscore the negative impact of many anthropogenic activities. Furthermore, navigating Autonomous Underwater Vehicles (AUV) in marine environments where the ground is densely colonized with P.O. is nowadays a challenging task, since this sea-grass generates dynamic and extremely textured areas, difficult to match in consecutive or loop-closing images. This paper presents two important contributions: a) a complete assessment to characterize areas of P.O. with visual features, in order to obtain visual localization data as accurate as possible; b) the automatic detection of P.O. in video sequences grabbed from the AUV Sparus II in coastal areas; the images containing the detected sea-grass will be used later to build visual mosaics showing the real extension and form of the P.O. meadow.

Starting in January 2009, the RAUVI (Reconfigurable Autonomous Underwater Vehicle for Intervention Missions) project is a 3-year coordinated research action funded by the Spanish Ministry of Research and Innovation. In this paper, the state of progress after 2 years of continuous research is reported. As a first experimental validation of the complete system, a search and recovery problem is addressed, consisting of finding and recovering a flight data recorder placed at an unknown position at the bottom of a water tank. An overview of the techniques used to successfully solve the problem in an autonomous way is provided. The obtained results are very promising and are the first step toward the final test in shallow water at the end of 2011 This research was partly supported by Spanish Ministry of Research and Innovation DPI2008-06548-C01-02-03 (RAUVI Project), by the European Commissions Seventh Framework Programme FP7/2007-2013 underGrant agreement 248497 (TRIDENT Project), by Fundació Caixa Castelló-Bancaixa P1-1B2009-50, and by the Spanish Ministry of Education and Science (MCINN Grant CTM2010-15216), Ramon Y Cajal Program (N. Gracias) and the FPI program (R. Campos)

not available

[eng] This part presents the motivation and the necessary background to introduce the reader in the main issues of this dissertation. Chapter 1 proceeds with the general motivation that lead to understand the importance of the algorithms presented in this dissertation, circumscribed in the context of navigation strategies for autonomous robots. Next, the principal requirements for the new algorithms are outlined. The aim is overcoming several limitations encountered in other visual approaches, and designing a system suitable in environmental conditions as general as possible. Chapter 2 examines in the first section the different types of control architectures for mobile robots, emphasizing and reviewing the concepts of deliberative, reactive, map-based or mapless systems. The second section of this chapter introduces the background of the localization problem. Chapter 3 surveys the most outstanding approaches on visual navigation from the final eighties up to nowadays. The review of all these pieces of work places the reader into the main problems encountered during all these years concerning how to extract and interpret the environmental information from digital images. Reviewing a wide range of visual navigation approaches leads to a complete comprehension of what has been done until the moment and what is still remaining to be done. Of course, all these pieces of work have been an important source of inspiration for this research.

Este trabajo analiza la idoneidad de dos de los principales métodos de asignación de tareas en entornos con restricciones temporales. Se pondrá de manifiesto que ambos tipos de mecanismos presentan carencias para tratar tareas con deadlines, especialmente cuando los robots han de formar coaliciones. Uno de los aspectos a los que esta tesis dedica mayor atención es la predicción del tiempo de ejecución, que depende, entre otros factores, de la interferencia física entre robots. Este fenómeno no se ha tenido en cuenta en los mecanismos actuales de asignación basados en subastas. Así, esta tesis presenta el primer mecanismo de subastas para la creación de coaliciones que tiene en cuenta la interferencia entre robots. Para ello, se ha desarrollado un modelo de predicción del tiempo de ejecución y un nuevo paradigma llamado subasta doble. Además, se han propuesto nuevos mecanismos basados en swarm