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

Policy gradient based Reinforcement Learning for real autonomous underwater cable tracking

This paper proposes a field application of a high-level reinforcement learning (RL) control system for solving the action selection problem of an autonomous robot in cable tracking task. The learning system is characterized by using a direct policy search method for learning the internal state/action mapping. Policy only algorithms may suffer from long convergence times when dealing with real robotics. In order to speed up the process, the learning phase has been carried out in a simulated environment and, in a second step, the policy has been transferred and tested successfully on a real robot. Future steps plan to continue the learning process on-line while on the real robot while performing the mentioned task. We demonstrate its feasibility with real experiments on the underwater robot ICTINEU AUV

Autonomous underwater vehicle control using reinforcement learning policy search methods

Autonomous underwater vehicles (AUV) represent a challenging control problem with complex, noisy, dynamics. Nowadays, not only the continuous scientific advances in underwater robotics but the increasing number of subsea missions and its complexity ask for an automatization of submarine processes. This paper proposes a high-level control system for solving the action selection problem of an autonomous robot. The system is characterized by the use of reinforcement learning direct policy search methods (RLDPS) for learning the internal state/action mapping of some behaviors. We demonstrate its feasibility with simulated experiments using the model of our underwater robot URIS in a target following task

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

Correction of shading effects in vision-based UUV localization

This paper describes the improvements achieved in our mosaicking system to assist unmanned underwater vehicle navigation. A major advance has been attained in the processing of images of the ocean floor when light absorption effects are evident. Due to the absorption of natural light, underwater vehicles often require artificial light sources attached to them to provide the adequate illumination for processing underwater images. Unfortunately, these flashlights tend to illuminate the scene in a nonuniform fashion. In this paper a technique to correct non-uniform lighting is proposed. The acquired frames are compensated through a point-by-point division of the image by an estimation of the illumination field. Then, the gray-levels of the obtained image remapped to enhance image contrast. Experiments with real images are presented

A review of sensor fusion techniques for underwater vehicle navigation

This work provides a general description of the multi sensor data fusion concept, along with a new classification of currently used sensor fusion techniques for unmanned underwater vehicles (UUV). Unlike previous proposals that focus the classification on the sensors involved in the fusion, we propose a synthetic approach that is focused on the techniques involved in the fusion and their applications in UUV navigation. We believe that our approach is better oriented towards the development of sensor fusion systems, since a sensor fusion architecture should be first of all focused on its goals and then on the fused sensors

Mission control system for dam inspection with an AUV

This paper presents a complete control architecture that has been designed to fulfill predefined missions with an autonomous underwater vehicle (AUV). The control architecture has three levels of control: mission level, task level and vehicle level. The novelty of the work resides in the mission level, which is built with a Petri network that defines the sequence of tasks that are executed depending on the unpredictable situations that may occur. The task control system is composed of a set of active behaviours and a coordinator that selects the most appropriate vehicle action at each moment. The paper focuses on the design of the mission controller and its interaction with the task controller. Simulations, inspired on an industrial underwater inspection of a dam grate, show the effectiveness of the control architecture

ICTINEUAUV wins the First SAUC-E competition

A pioneer team of students of the University of Girona decided to design and develop an autonomous underwater vehicle (AUV) called ICTINEU-AUV to face the Student Autonomous Underwater Challenge-Europe (SAUC-E). The prototype has evolved from the initial computer aided design (CAD) model to become an operative AUV in the short period of seven months. The open frame and modular design principles together with the compatibility with other robots previously developed at the lab have provided the main design philosophy. Hence, at the robot's core, two networked computers give access to a wide set of sensors and actuators. The Gentoo/Linux distribution was chosen as the onboard operating system. A software architecture based on a set of distributed objects with soft real time capabilities was developed and a hybrid control architecture including mission control, a behavioural layer and a robust map-based localization algorithm made ICTINEU-AUV the winning entry

Neptune: a hil simulator for multiple UUVs

This paper overviews the field of graphical simulators used for AUV development, presents the taxonomy of these applications and proposes a classification. It also presents Neptune, a multivehicle, real-time, graphical simulator based on OpenGL that allows hardware in the loop simulations

Graphical simulators for AUV development

A long development time is needed from the design to the implementation of an AUV. During the first steps, simulation plays an important role, since it allows for the development of preliminary versions of the control system to be integrated. Once the robot is ready, the control systems are implemented, tuned and tested. The use of a real-time simulator can help closing the gap between off-line simulation and real testing using the already implemented robot. When properly interfaced with the robot hardware, a real-time graphical simulation with a "hardware in the loop" configuration, can allow for the testing of the implemented control system running in the actual robot hardware. Hence, the development time is drastically reduced. These paper overviews the field of graphical simulators used for AUV development proposing a classification. It also presents NEPTUNE, a multi-vehicle, real-time, graphical simulator based on OpenGL that allows hardware in the loop simulations

Integració i estudi d’un conjunt de propulsors per un robot submarí

L’objectiu d’aquest projecte/treball fi de carrera es estudiar els propulsors i el seu protocol de comunicació proporcionant informació útil a l’hora de dissenyar i construir el robot subaquàtic que implementi els propulsors

Odometria i planificació de trajectòries amb el robot e-puck

En el laboratori docent de robòtica s'utilitzen robots mòbils autònoms per treballar aspectes relacionats amb el posicionament, el control de trajectòries, la construcció de mapes... Es disposa de cinc robots comercials anomenats “e-puck”, que es caracteritzen per les seves dimensions reduïdes, dos motors i un conjunt complet de sensors. Aquests robots es programen en C++ utilitzant el simulador Webots, que disposa d'un conjunt de llibreries per programar el robot. També es disposa d'un entorn de proves on els robots es poden moure i evitar obstacles. Donat el poc temps que disposen els estudiants que realitzen pràctiques en aquest laboratori, és d'interès desenvolupar un software que contingui ja el posicionament del robot mitjançant odometria i també varis algoritmes de control de trajectòries. Per últim, en el laboratori es disposa de càmeres i targes d'adquisició de dades. Així doncs els objectius que s'han proposat per el projecte són: 1. Estudi de la documentació i software proporcinats pels fabricants del robot i de l'entorn Webots; 2. Programació del software de l'odometria i realització de proves per comprovar-ne la precisió; 3. Disseny, programació i verificació del software dels algoritmes de planificació de trajectòries. Realització d'experiments per a comprovar-ne el funcionament i 4. Disseny, programació i verificació d'un sistema de visió artificial que permeti conèixer la posició absoluta del robot en l'entorn

Programació del robot e-puck amb Microsoft Robotics Studio

Microsoft Robotics Studio (MRS) és un entorn per a crear aplicacions per a robots utilitzant una gran varietat de plataformes hardware. Conté un entorn de simulació en el que es pot modelar i simular el moviment del robot. Permet també programar el robot, i executar-lo en l’entorn simulat o bé en el real. MRS resol la comunicació entre elsdiferents processos asíncrons que solen estar presents en el software de control d’unrobot: processos per atendre sensors, actuadors, sistemes de control, comunicacions amb l’exterior,... MRS es pot utilitzar per modelar nous robots utilitzant components que ja estiguin disponibles en les seves llibreries, o també permet crear component nous. Per tal de conèixer en detall aquesta eina, seria interessant utilitzar-la per programa els robots e-pucks, uns robots mòbils autònoms de petites dimensions que disposen de dos motors i un complet conjunt de sensors. El que es vol és simular-los, realitzar un programa de control, realitzar la interfície amb el robot i comprovar el funcionament amb el robot real

A la llum de les matrius: projecte d'exposició temporal

El treball presenta el projecte d'una exposició temporal al Museu d'Art sobre el fons de xilografies procedents de la Impremta Carreras