Semi-online neural-Q_leaming for real-time robot learning

Reinforcement learning (RL) is a very suitable technique for robot learning, as it can learn in unknown environments and in real-time computation. The main difficulties in adapting classic RL algorithms to robotic systems are the generalization problem and the correct observation of the Markovian state. This paper attempts to solve the generalization problem by proposing the semi-online neural-Q_learning algorithm (SONQL). The algorithm uses the classic Q_learning technique with two modifications. First, a neural network (NN) approximates the Q_function allowing the use of continuous states and actions. Second, a database of the most representative learning samples accelerates and stabilizes the convergence. The term semi-online is referred to the fact that the algorithm uses the current but also past learning samples. However, the algorithm is able to learn in real-time while the robot is interacting with the environment. The paper shows simulated results with the "mountain-car" benchmark and, also, real results with an underwater robot in a target following behavior

The Role of the online learner: onsite students becoming online learners

As universities are offering tuition through online learning environments, “onsite students” in higher education are increasingly becoming “online learners”. Since the medium for learning (and teaching) online is a digital environment, and at a distance, the role taken by students and teaching staff is different to the one these are used to in onsite, traditional settings. Therefore the Role of the Online Learner, presented in this paper, is key to onsite students who are to become online learners. This role consists of five competences: Operational, Cognitive, Collaborative, Self-directing, Course-specific. These five competences integrate the various skills, strategies, attitudes and awareness that make up the role of online learner, which learners use to perform efficiently online. They also make up the basis of a tutorial for would-be online learners, going over the Role of the Online Learner by means of concepts, examples and reflective activities. This tutorial, available to students in the author’s website, is also helpful to teaching and counselling staff in guiding their students to become online learners

Interoperabilidad del servicio de nomenclator y catálogo online del Instituto de Cartografía de Andalucía

El servicio WFS-G de Nomenclátor del Instituto de Cartografía de Andalucía (ICA) basa sus servicios en una base de datos que sigue el estándar del Modelo de Nomenclátor de España y que actualmente contiene unos 149.500 topónimos e identificadores geográficos clasificados temáticamente en áreas administrativas, entidades de población, hidrografía, orografía, patrimonio, infraestructuras, actividades industriales, extractivas, servicios y equipamientos. Este servicio OGC basado en el software libre Deegree 2.2. trata de dar servicio a otros proyectos del ICA como la IDEAndalucia, el catálogo de productos on-line LINE@ y en un futuro al buscador de cartografía histórica; por otro lado dispone de un visor propio de búsqueda de nombres geográficos con utilidades de descarga, rectificación y localización de topónimos cercanos

Efficient learning of reactive robot behaviors with a Neural-Q_learning approach

The purpose of this paper is to propose a Neural-Q_learning approach designed for online learning of simple and reactive robot behaviors. In this approach, the Q_function is generalized by a multi-layer neural network allowing the use of continuous states and actions. The algorithm uses a database of the most recent learning samples to accelerate and guarantee the convergence. Each Neural-Q_learning function represents an independent, reactive and adaptive behavior which maps sensorial states to robot control actions. A group of these behaviors constitutes a reactive control scheme designed to fulfill simple missions. The paper centers on the description of the Neural-Q_learning based behaviors showing their performance with an underwater robot in a target following task. Real experiments demonstrate the convergence and stability of the learning system, pointing out its suitability for online robot learning. Advantages and limitations are discussed

A behavior-based scheme using reinforcement learning for autonomous underwater vehicles

This paper presents a hybrid behavior-based scheme using reinforcement learning for high-level control of autonomous underwater vehicles (AUVs). Two main features of the presented approach are hybrid behavior coordination and semi on-line neural-Q_learning (SONQL). Hybrid behavior coordination takes advantages of robustness and modularity in the competitive approach as well as efficient trajectories in the cooperative approach. SONQL, a new continuous approach of the Q_learning algorithm with a multilayer neural network is used to learn behavior state/action mapping online. Experimental results show the feasibility of the presented approach for AUVs

A concurrent region growing algorithm guided by circumscribed contours

Image segmentation of natural scenes constitutes a major problem in machine vision. This paper presents a new proposal for the image segmentation problem which has been based on the integration of edge and region information. This approach begins by detecting the main contours of the scene which are later used to guide a concurrent set of growing processes. A previous analysis of the seed pixels permits adjustment of the homogeneity criterion to the region's characteristics during the growing process. Since the high variability of regions representing outdoor scenes makes the classical homogeneity criteria useless, a new homogeneity criterion based on clustering analysis and convex hull construction is proposed. Experimental results have proven the reliability of the proposed approach

Proposal of a parallel architecture for a motion detection algorithm

This paper proposes a parallel architecture for estimation of the motion of an underwater robot. It is well known that image processing requires a huge amount of computation, mainly at low-level processing where the algorithms are dealing with a great number of data. In a motion estimation algorithm, correspondences between two images have to be solved at the low level. In the underwater imaging, normalised correlation can be a solution in the presence of non-uniform illumination. Due to its regular processing scheme, parallel implementation of the correspondence problem can be an adequate approach to reduce the computation time. Taking into consideration the complexity of the normalised correlation criteria, a new approach using parallel organisation of every processor from the architecture is proposed

Pose-based SLAM with probabilistic scan matching algorithm using a mechanical scanned imaging sonar

This paper proposes a pose-based algorithm to solve the full SLAM problem for an autonomous underwater vehicle (AUV), navigating in an unknown and possibly unstructured environment. The technique incorporate probabilistic scan matching with range scans gathered from a mechanical scanning imaging sonar (MSIS) and the robot dead-reckoning displacements estimated from a Doppler velocity log (DVL) and a motion reference unit (MRU). The proposed method utilizes two extended Kalman filters (EKF). The first, estimates the local path travelled by the robot while grabbing the scan as well as its uncertainty and provides position estimates for correcting the distortions that the vehicle motion produces in the acoustic images. The second is an augment state EKF that estimates and keeps the registered scans poses. The raw data from the sensors are processed and fused in-line. No priory structural information or initial pose are considered. The algorithm has been tested on an AUV guided along a 600 m path within a marina environment, showing the viability of the proposed approach

QoS online routing and MPLS multilevel protection: a survey

A survey of MPLS protection methods and their utilization in combination with online routing methods is presented in this article. Usually, fault management methods pre-establish backup paths to recover traffic after a failure. In addition, MPLS allows the creation of different backup types, and hence MPLS is a suitable method to support traffic-engineered networks. In this article, an introduction of several label switch path backup types and their pros and cons are pointed out. The creation of an LSP involves a routing phase, which should include QoS aspects. In a similar way, to achieve a reliable network the LSP backups must also be routed by a QoS routing method. When LSP creation requests arrive one by one (a dynamic network scenario), online routing methods are applied. The relationship between MPLS fault management and QoS online routing methods is unavoidable, in particular during the creation of LSP backups. Both aspects are discussed in this article. Several ideas on how these actual technologies could be applied together are presented and compared

Fast calculation of the CAC convolution algorithm using the multinomial distribution function

The authors focus on one of the methods for connection acceptance control (CAC) in an ATM network: the convolution approach. With the aim of reducing the cost in terms of calculation and storage requirements, they propose the use of the multinomial distribution function. This permits direct computation of the associated probabilities of the instantaneous bandwidth requirements. This in turn makes possible a simple deconvolution process. Moreover, under certain conditions additional improvements may be achieved

Online Robust 3D Mapping Using Structure from Motion Cues

This paper presents a complete solution for creating accurate 3D textured models from monocular video sequences. The methods are developed within the framework of sequential structure from motion, where a 3D model of the environment is maintained and updated as new visual information becomes available. The camera position is recovered by directly associating the 3D scene model with local image observations. Compared to standard structure from motion techniques, this approach decreases the error accumulation while increasing the robustness to scene occlusions and feature association failures. The obtained 3D information is used to generate high quality, composite visual maps of the scene (mosaics). The visual maps are used to create texture-mapped, realistic views of the scene

A Label space reduction algorithm for P2MP LSPs using asymmetric tunnels

The aim of traffic engineering is to optimise network resource utilization. Although several works on minimizing network resource utilization have been published, few works have focused on LSR label space. This paper proposes an algorithm that uses MPLS label stack features in order to reduce the number of labels used in LSPs forwarding. Some tunnelling methods and their MPLS implementation drawbacks are also discussed. The algorithm described sets up the NHLFE tables in each LSR, creating asymmetric tunnels when possible. Experimental results show that the algorithm achieves a large reduction factor in the label space. The work presented here applies for both types of connections: P2MP and P2P

Speculative parallelization of multipath radiosity algorithm

In computer graphics, global illumination algorithms take into account not only the light that comes directly from the sources, but also the light interreflections. This kind of algorithms produce very realistic images, but at a high computational cost, especially when dealing with complex environments. Parallel computation has been successfully applied to such algorithms in order to make it possible to compute highly-realistic images in a reasonable time. We introduce here a speculation-based parallel solution for a global illumination algorithm in the context of radiosity, in which we have taken advantage of the hierarchical nature of such an algorithm

A Monte Carlo-Based Fiber Tracking Algorithm using Diffusion Tensor MRI

Diffusion tensor magnetic resonance imaging, which measures directional information of water diffusion in the brain, has emerged as a powerful tool for human brain studies. In this paper, we introduce a new Monte Carlo-based fiber tracking approach to estimate brain connectivity. One of the main characteristics of this approach is that all parameters of the algorithm are automatically determined at each point using the entropy of the eigenvalues of the diffusion tensor. Experimental results show the good performance of the proposed approach

De la Presencialitat i de l'online, on acaba una i comença l´altra? Propostes per a plantejar-les, disfrutar-les i valorar-les'

Hi ha dos tipus d'interrogants que ens plantegem en aquesta presentació: En primer lloc exposem un seguit de realitats que afecten directament al disseny de la nostra assignatura: els professors assumim habilitats apreses en tècniques de treball dels nostres estudiants: treball en equip, presentacions, debats.... Els uns i els altres entenem el mateix, del què i el com s'ha de treballar? Ho comprovarem. Alhora, ens preguntarem si els estudiants assumim habilitats tecnològiques del professorat? Moodle, wikis, Twitter, xats..... tots entenem el mateix i els fem servir de la mateixa manera? Fixem-nos en les dues perspectives, la del professor i la de l'estudiant, tant referent a dinamiques com a recursos, i ens adonarem que cal tenir en compte tant la una com l'altra. Aquestes reflexions afecten al plantejament de l'assignatura i ens deixen clar que hi ha molta feina a fer per trobar les respostes (conèixer als estudiants que tenim a les aules, explicar convenientment el que esperem dels estudiants, com plantegem l'assignatura i com l'avaluarem... ) No ens referim exclusivament a tenir un pla docent detallat a la maxima expresió, sinó que ens referim a reconèixer el com, el quan i el que expliquem als nostres estudiants, de manera que les regles del joc quedin enteses de la mateixa manera per una part i per l'altra. A partir d'aquí, i com a segon interrogant, ens plantejarem l'estructura que combina la part presencial i la part no presencial de l'assignatura: Quines són les activitats de les que puc treure més rendiment en la part presencial de l'assignatura i quines en la part no presencial? Quant temps i com calcular-lo, cal invertir en les activitats, tant per part dels estudiants com per part del professorat? Com podem avaluar una activitat que ha estat realitzada en part presencial i en part no presencial