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

PRIM an Open Mobile Robot Platform. Motivation, Present and Future Trends

This paper is focused on the robot mobile platform PRIM (platform robot information multimedia). This robot has been made in order to cover two main needs of our group, on one hand the need for a full open mobile robotic platform that is very useful in fulfilling the teaching and research activity of our school community, and on the other hand with the idea of introducing an ethical product which would be useful as mobile multimedia information point as a service tool. This paper introduces exactly how the system is made up and explains just what the philosophy is behind this work. The navigation strategies and sensor fusion, where machine vision system is the most important one, are oriented towards goal achievement and are the key to the behaviour of the robot

Plane-to-plane positioning from image-based visual servoing and structured light

In this paper we face the problem of positioning a camera attached to the end-effector of a robotic manipulator so that it gets parallel to a planar object. Such problem has been treated for a long time in visual servoing. Our approach is based on linking to the camera several laser pointers so that its configuration is aimed to produce a suitable set of visual features. The aim of using structured light is not only for easing the image processing and to allow low-textured objects to be treated, but also for producing a control scheme with nice properties like decoupling, stability, well conditioning and good camera trajectory

Studies about the atomic capabilities concept for linear control systems in physical multi-agent environments

This paper shows the impact of the atomic capabilities concept to include control-oriented knowledge of linear control systems in the decisions making structure of physical agents. These agents operate in a real environment managing physical objects (e.g. their physical bodies) in coordinated tasks. This approach is presented using an introspective reasoning approach and control theory based on the specific tasks of passing a ball and executing the offside manoeuvre between physical agents in the robotic soccer testbed. Experimental results and conclusions are presented, emphasising the advantages of our approach that improve the multi-agent performance in cooperative systems

Ejercicio y resultados clínicos en pacientes con enfermedad de Parkinson: una revisión sistemática y metaanálisis

Antecedentes. La enfermedad de Parkinson (EP) es la segunda enfermedad neurodegenerativa más común en el mundo, la cual afecta el componente físico, psicológico y social de los individuos que la padecen. Numerosos estudios han abordado los beneficios de diferentes programas de ejercicio, llegando a ser una estrategia no-farmacológica efectiva para aminorar el deterioro funcional de los pacientes con EP. Objetivo. Determinar los efectos de las diferentes modalidades de ejercicio físico en los principales desenlaces clínicos en pacientes con EP. Métodos. Se consultaron las bases de datos MEDLINE, EMBASE, Scopus, CENTRAL y PEDro desde febrero de 1990 hasta febrero de 2014 para identificar Ensayos Clínicos Aleatorizados (ECA) publicados. Además, se examinaron las listas de referencias de otras revisiones y de estudios identificados. La extracción de datos se realizó por dos autores independientes. Se empleó un modelo de efectos aleatorios en presencia de heterogeneidad estadística (I2>50%). El sesgo de publicación fue evaluado mediante el gráfico de embudo. Resultados: Un total de 18 estudios fueron incluidos. Se encontraron diferencias estadísticamente significativas en las intervenciones con ejercicio y las siguientes medidas de resultado, severidad de los síntomas motores (MDS-UPDRS) DME 1.44, IC 95% [-2.09 a -0.78] (p<0.001) I2= 87,9% y el equilibrio DME 0,52 IC 95% [0,30 a 0,74] (p<0.001) I2= 85,6%. En el análisis de subgrupos en la modalidad de ejercicio aeróbico, en MDS-UPDRS DME -1,28, IC 95% [-1,98 a -0,59] (p<0.001), 3 calidad de vida DME -1,91 IC 95% [-2,76 a -1,07] (p<0.001), equilibrio DME 0,54 IC 95% [0,31 a 0,77] (p<0.001), 10-m WT DME 0,15 IC 95% [0,06 a 0,25] (p<0.001) y Vo2 máximo DME -1,09 IC 95% [-1,31 a -0,88] (p=0.001), 6MWT DME 40,46 IC 95% [11,28 a 69,65] (p=0.007). Conclusiones: El ejercicio aeróbico produjo mejoras significativas en MDS UPDRS, equilibrio, calidad de vida, 10-m WT y y Vo2 máximo; mientras que el ejercicio combinado mejoró la fuerza.

Resultados de la cirugía laparoscópica comparada con la cirugía abierta en el cáncer colorrectal. Revisión sistemática

Determinar el efecto de la cirugía laparoscópica versus cirugía abierta sobre la supervivencia en el manejo de pacientes del cáncer colorectal.

Gradient-based reinforcement learning techniques for underwater robotics behavior learning

Darrerament, l'interès pel desenvolupament d'aplicacions amb robots submarins autònoms (AUV) ha crescut de forma considerable. Els AUVs són atractius gràcies al seu tamany i el fet que no necessiten un operador humà per pilotar-los. Tot i això, és impossible comparar, en termes d'eficiència i flexibilitat, l'habilitat d'un pilot humà amb les escasses capacitats operatives que ofereixen els AUVs actuals. L'utilització de AUVs per cobrir grans àrees implica resoldre problemes complexos, especialment si es desitja que el nostre robot reaccioni en temps real a canvis sobtats en les condicions de treball. Per aquestes raons, el desenvolupament de sistemes de control autònom amb l'objectiu de millorar aquestes capacitats ha esdevingut una prioritat. Aquesta tesi tracta sobre el problema de la presa de decisions utilizant AUVs. El treball presentat es centra en l'estudi, disseny i aplicació de comportaments per a AUVs utilitzant tècniques d'aprenentatge per reforç (RL). La contribució principal d'aquesta tesi consisteix en l'aplicació de diverses tècniques de RL per tal de millorar l'autonomia dels robots submarins, amb l'objectiu final de demostrar la viabilitat d'aquests algoritmes per aprendre tasques submarines autònomes en temps real. En RL, el robot intenta maximitzar un reforç escalar obtingut com a conseqüència de la seva interacció amb l'entorn. L'objectiu és trobar una política òptima que relaciona tots els estats possibles amb les accions a executar per a cada estat que maximitzen la suma de reforços totals. Així, aquesta tesi investiga principalment dues tipologies d'algoritmes basats en RL: mètodes basats en funcions de valor (VF) i mètodes basats en el gradient (PG). Els resultats experimentals finals mostren el robot submarí Ictineu en una tasca autònoma real de seguiment de cables submarins. Per portar-la a terme, s'ha dissenyat un algoritme anomenat mètode d'Actor i Crític (AC), fruit de la fusió de mètodes VF amb tècniques de PG.

A segurança estrutural relacionada com a escavação sob fundações de edifícios pré-existentes

Pretende-se no presente artigo analisar a segurança estrutural de edificações condicionadas por escavações a um nível inferior ao das suas fundações. Considerando a existência de três momentos diferentes – o período antecedente ao início dos trabalhos, o intervalo de tempo correspondente ao decurso dos trabalhos de reabilitação e o período posterior, correspondente à futura utilização do património, é sobre o segundo que incidirá a nossa análise, por ser aquele em que a estrutura se encontra mais fragilizada, implicando uma menor segurança estrutural, que tende a ser desvalorizada, por ter uma natureza temporária. Numa primeira fase descreve-se o existente, assim como as intervenções propostas. Posteriormente indicam-se os potenciais danos estruturais resultantes das alterações pretendidas e as principais medidas a considerar para os evitar. Numa fase posterior propõe-se a sequenciação dos trabalhos de modo a evitar um colapso parcial ou global e, por último, apresentam-se conclusões e sugerem-se desenvolvimentos futuros. / The present work seeks to present an analysis related to the structural safety of buildings that are object of excavations at a lower level than their foundations. Considering the existence of three different moments – a first period before the beginning of the works, a second one correspondent to the rehabilitation procedures and a last one related with the future utilization of the patrimony, this article will focus on the second period, because during that gap of time, the structure is usually weakened, which implies a lower structural safety that tends to be ignored, due to its temporary nature. In the first phase, the existing construction is described, as well as the proposed interventions. Afterwards, are referred the potential structural damages resultant of the architectonical proposals and the measures to implemented to prevent them. In the posterior phase we propose the work sequence, in order to avoid a partial or global collapse and, finally, we reach some conclusions and suggest other works to be developed in the future.

A Newton method for pose refinement of 3D models

Different optimization methods can be employed to optimize a numerical estimate for the match between an instantiated object model and an image. In order to take advantage of gradient-based optimization methods, perspective inversion must be used in this context. We show that convergence can be very fast by extrapolating to maximum goodness-of-fit with Newton's method. This approach is related to methods which either maximize a similar goodness-of-fit measure without use of gradient information, or else minimize distances between projected model lines and image features. Newton's method combines the accuracy of the former approach with the speed of convergence of the latter.

Silchester Roman Town Insula IX: the development of an urban property c. AD 40-50 - c. AD 250

The development of an urban property in the Roman town of Calleva Atrebatum (Silchester, Hampshire, England) is traced from the late 1st to the mid-3rd century AD. Three successive periods of building with their associated finds of artefacts and biological remains are described and interpreted with provisional reconstructions of the buildings. Links are provided to a copy of the Integrated Archaeological Database (IADB), archived by the Archaeology Data Service, which holds the primary excavation and finds records.

New radiocarbon accelerator dates on artefacts from the early Mesolithic site of Star Carr, North Yorkshire

For the well-known early Mesolithic site of Star Carr, dating of organic artefacts by accelerator mass spectrometry (AMS) has been hampered by treatment of bone and antler recovered during the original excavations with preservatives. Some, untreated, artefacts were, however, collected after Clark's excavation in 1950. Four of these artefacts were AMS dated in 1995, but two of the dates were significantly younger than the others, and were questionable due to their low collagen yields. These suspect samples have now been re-analysed, demonstrating that all four artefacts are of similar date. The significance of these dates for the chronology of Star Carr is discussed.

Promoting inclusion: facilitating access to the Silchester 'town life' project

It is becoming increasingly difficult to resource field archaeology outside the developer-funded context. Consequently it is difficult to engage the wider public in understanding the nature of archaeology and in the writing of its history from the study of material and environmental evidence. This paper describes a project funded by the UK's Heritage Lottery Fund designed to increase access by several means to a well-established and long-running archaeological excavation at the Iron Age and Roman Town at Silchester, Hampshire (UK).

Small-scale mining, poverty and economic development in sub-Saharan Africa: An overview

Artisanal and small-scale mining (ASM)-low tech, labour intensive mineral processing and excavation activity-is an economic mainstay in rural sub-Saharan Africa, providing direct employment to over two million people. This paper introduces a special issue on 'Small-scale mining, poverty and development in sub-Saharan Africa'. It focuses on the core conceptual issues covered in the literature, and the policy implications of the findings reported in the papers in this special issue. (C) 2009 Elsevier Ltd. All rights reserved.