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

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

Vision-based localization of an underwater robot in a structured environment

This paper presents a vision-based localization approach for an underwater robot in a structured environment. The system is based on a coded pattern placed on the bottom of a water tank and an onboard down looking camera. Main features are, absolute and map-based localization, landmark detection and tracking, and real-time computation (12.5 Hz). The proposed system provides three-dimensional position and orientation of the vehicle along with its velocity. Accuracy of the drift-free estimates is very high, allowing them to be used as feedback measures of a velocity-based low-level controller. The paper details the localization algorithm, by showing some graphical results, and the accuracy of the system

Towards Direct Policy Search Reinforcement Learning for Robot Control

This paper proposes a high-level reinforcement learning (RL) control system for solving the action selection problem of an autonomous robot. Although the dominant approach, when using RL, has been to apply value function based algorithms, the system here detailed is characterized by the use of direct policy search methods. Rather than approximating a value function, these methodologies approximate a policy using an independent function approximator with its own parameters, trying to maximize the future expected reward. The policy based algorithm presented in this paper is used for learning the internal state/action mapping of a behavior. In this preliminary work, we demonstrate its feasibility with simulated experiments using the underwater robot GARBI in a target reaching task

Estimating the motion of an underwater robot from a monocular image sequence

When underwater vehicles perform navigation close to the ocean floor, computer vision techniques can be applied to obtain quite accurate motion estimates. The most crucial step in the vision-based estimation of the vehicle motion consists on detecting matchings between image pairs. Here we propose the extensive use of texture analysis as a tool to ameliorate the correspondence problem in underwater images. Once a robust set of correspondences has been found, the three-dimensional motion of the vehicle can be computed with respect to the bed of the sea. Finally, motion estimates allow the construction of a map that could aid to the navigation of the robot

VLSI architecture for an Underwater Robot Vision System

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-pixel. One of the solutions to estimate motions involves detection of the correspondences between two images. For normalised correlation criteria, previous experiments shown that the result is not altered in presence of nonuniform illumination. Usually, hardware for motion estimation has been limited to simple correlation criteria. The main goal of this paper is to propose a VLSI architecture for motion estimation using a matching criteria more complex than Sum of Absolute Differences (SAD) criteria. Today hardware devices provide many facilities for the integration of more and more complex designs as well as the possibility to easily communicate with general purpose processors

Experimental Modeling and Control Strategies on an Open Mobile Robot Platform PRIM

This research work deals with the problem of modeling and design of low level speed controller for the mobile robot PRIM. The main objective is to develop an effective educational tool. On one hand, the interests in using the open mobile platform PRIM consist in integrating several highly related subjects to the automatic control theory in an educational context, by embracing the subjects of communications, signal processing, sensor fusion and hardware design, amongst others. On the other hand, the idea is to implement useful navigation strategies such that the robot can be served as a mobile multimedia information point. It is in this context, when navigation strategies are oriented to goal achievement, that a local model predictive control is attained. Hence, such studies are presented as a very interesting control strategy in order to develop the future capabilities of the system

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

Knowledge integration within an applied mobile robot summer course

This paper presents the use of a mobile robot platform as an innovative educational tool in order to promote and integrate different curriculum knowledge. Hence, it is presented the acquired experience within a summer course named ldquoapplied mobile roboticsrdquo. The main aim of the course is to integrate different subjects as electronics, programming, architecture, perception systems, communications, control and trajectory planning by using the educational open mobile robot platform PRIM. The summer course is addressed to a wide range of student profiles. However, it is of special interests to the students of electrical and computer engineering around their final academic year. The summer course consists of the theoretical and laboratory sessions, related to the following topics: design & programming of electronic devices, modelling and control systems, trajectory planning and control, and computer vision systems. Therefore, the clues for achieving a renewed path of progress in robotics are the integration of several knowledgeable fields, such as computing, communications, and control sciences, in order to perform a higher level reasoning and use decision tools with strong theoretical base

A Camera-Projector System for Robot Positioning by Visual Servoing

Positioning a robot with respect to objects by using data provided by a camera is a well known technique called visual servoing. In order to perform a task, the object must exhibit visual features which can be extracted from different points of view. Then, visual servoing is object-dependent as it depends on the object appearance. Therefore, performing the positioning task is not possible in presence of nontextured objets or objets for which extracting visual features is too complex or too costly. This paper proposes a solution to tackle this limitation inherent to the current visual servoing techniques. Our proposal is based on the coded structured light approach as a reliable and fast way to solve the correspondence problem. In this case, a coded light pattern is projected providing robust visual features independently of the object appearance

Estudi del model dinàmic d’un robot submarí d’intervenció (IAUV) composat per un vehicle i un braç manipulador

Fins a la data d’avui, el grup VICOROB de la Universitat de Girona ha desenvolupat diversos vehicles autònoms (GARBÍ, URIS i ICTINEU). El projecte que comença aquest any té com objectiu desenvolupar un nou vehicle submarí autònom amb capacitat d’intervenció (I-AUV) gràcies a un braç manipulador. Aquest projecte final de carrera té com objectiu desenvolupar en entorn MATLAB un simulador d’un I-AUV, format per un AUV i un braç manipulador de n graus de llibertat per tal d’avaluar les reaccions dels moviments del braç, amb càrrega i sense, sobre el robot, i viceversa

Predictive motion control of a mirosot mobile robot

This paper discusses predictive motion control of a MiRoSoT robot. The dynamic model of the robot is deduced by taking into account the whole process - robot, vision, control and transmission systems. Based on the obtained dynamic model, an integrated predictive control algorithm is proposed to position precisely with either stationary or moving obstacle avoidance. This objective is achieved automatically by introducing distant constraints into the open-loop optimization of control inputs. Simulation results demonstrate the feasibility of such control strategy for the deduced dynamic model

Un robot en casa : la lavadora.

Aproximación a un objeto de la vida cuotidiana como el lavadora. Se hace un recorrido histórico sobre el uso de este electrodoméstico y se comentan aspectos como el funcionamiento o los gastos que se derivan de su uso. Además se intenta relacionar la lavadora con las matemáticas.

Construcción y presentación a un concurso de un robot.

Trabajo no publicado

The big robot. 'El gran robot'.

Unidad didáctica para la enseñanza del Inglés en el Primer Ciclo de Educación Primaria. La unidad parte de un centro de interés, el cuerpo, instrumento que permite al niño relacionarse consigo mismo, con los otros y con su entorno. Los objetivos del trabajo son ayudar y motivar a los alumnos en el conocimiento progresivo de sus posibilidades motrices, perceptivas y expresivas, utilizando la lengua inglesa como medio de conocimiento, comunicación y expresión de las experiencias. La unidad se centra principalmente en el lenguaje oral e integra temas trasnversales de Educación para la Salud y de Educación para la igualdad de sexos.