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

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

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

A mission control system for an autonomous underwater vehicle

The presented work focuses on the theoretical and practical aspects concerning the design and development of a formal method to build a mission control system for autonomous underwater vehicles bringing systematic design principles for the formal description of missions using Petri nets. The proposed methodology compounds Petri net building blocks within it to de_ne a mission plan for which it is proved that formal properties, such as reachability and reusability, hold as long as these same properties are also guaranteed by each Petri net building block. To simplify the de_nition of these Petri net blocks as well as their composition, a high level language called Mission Control Language has been developed. Moreover, a methodology to ensure coordination constraints for teams of multiple robots as well as the de_nition of an interface between the proposed system and an on-board planner able to plan/replan sequences of prede_ned mission plans is included as well. Results of experiments with several real underwater vehicles and simulations involving an autonomous surface craft and an autonomous underwater vehicles are presented to show the system's capabilities.

Hybrid coordination of reinforcement learning-based behaviors for AUV control

This paper proposes a hybrid coordination method for behavior-based control architectures. The hybrid method takes advantages of the robustness and modularity in competitive approaches as well as optimized trajectories in cooperative ones. This paper shows the feasibility of applying this hybrid method with a 3D-navigation to an autonomous underwater vehicle (AUV). The behaviors are learnt online by means of reinforcement learning. A continuous Q-learning implemented with a feed-forward neural network is employed. Realistic simulations were carried out. The results obtained show the good performance of the hybrid method on behavior coordination as well as the convergence of the behaviors

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

On AUV control architecture

This paper surveys control architectures proposed in the literature and describes a control architecture that is being developed for a semi-autonomous underwater vehicle for intervention missions (SAUVIM) at the University of Hawaii. Conceived as hybrid, this architecture has been organized in three layers: planning, control and execution. The mission is planned with a sequence of subgoals. Each subgoal has a related task supervisor responsible for arranging a set of pre-programmed task modules in order to achieve the subgoal. Task modules are the key concept of the architecture. They are the main building blocks and can be dynamically re-arranged by the task supervisor. In our architecture, deliberation takes place at the planning layer while reaction is dealt through the parallel execution of the task modules. Hence, the system presents both a hierarchical and an heterarchical decomposition, being able to show a predictable response while keeping rapid reactivity to the dynamic environment

Active control of structures with uncertain coupled subsystems and actuator dynamics

This paper deals with the problem of stabilizing a class of structures subject to an uncertain excitation due to the temporary coupling of the main system with another uncertain dynamical subsystem. A Lyapunov function based control scheme is proposed to attenuate the structural vibration. In the control design, the actuator dynamics is taken into account. The control scheme is implemented by using only feedback information of the main system. The effectiveness of the control scheme is shown for a bridge platform with crossing vehicle

Disseny d’un comportament en ROS per a mantenir la posició d’un vehicle autònom submarí a partir de referències visuals

En el Centre d'Investigació en Robòtica Submarina (CIRS) de la Universitat de Gironaes disposa de diferents robots submarins els quals utilitzen una arquitectura software anomenada Component Oriented Layered-based Architecture for Autonomy ( COLA2 ), la qual ha estat desenvolupada per estudiants i professors del mateix centre. Per tal de fer aquesta arquitectura més accessible per a professors i estudiant d’altres centres la COLA2 s’està adaptant al Robot Operative System (ROS) que és un framework genèric per al desenvolupament d’aplicacions amb robots. Aquest projecte pretén dissenyar un comportament per al robot Girona500 que estigui desenvolupat dins la versió ROS de l’arquitectura COLA2. El comportament haurà de fer mantenir una determinada posició al robot amb informació visual de la càmera del robot i amb dades de navegació. La tasca de mantenir la posició es de vital importància per a poder realitzar intervencions submarines que requereixen de precisió i, precisament, el medi on es treballa no ajuda

A Multi-agent Architecture with Distributed Coordination for an Autonomous Robot

Aquest treball proposa una nova arquitectura de control amb coordinació distribuïda per a un robot mòbil (ARMADiCo). La metodologia de coordinació distribuïda consisteix en dos passos: el primer determina quin és l'agent que guanya el recurs basat en el càlcul privat de la utilitat i el segon, com es fa el canvi del recurs per evitar comportaments abruptes del robot. Aquesta arquitectura ha estat concebuda per facilitar la introducció de nous components hardware i software, definint un patró de disseny d'agents que captura les característiques comunes dels agents. Aquest patró ha portat al desenvolupament d'una arquitectura modular dins l'agent que permet la separació dels diferents mètodes utilitzats per aconseguir els objectius, la col·laboració, la competició i la coordinació de recursos. ARMADiCo s'ha provat en un robot Pioneer 2DX de MobileRobots Inc.. S'han fet diversos experiments i els resultats han demostrat que s'han aconseguit les característiques proposades per l'arquitectura.

Introspection on control-grounded capabilities. An agent inspired approach for control

Introspecció sobre la dinàmica dels agents té un important impacte en decisions individuals i cooperatives en entorns multi-agent. Introspecció, una habilitat cognitiva provinent de la metàfora "agent", permet que els agents siguin conscients de les seves capacitats per a realitzar correctament les tasques. Aquesta introspecció, principalment sobre capacitats relacionades amb la dinàmica, proporciona als agents un raonament adequat per a assolir compromisos segurs en sistemes cooperatius. Per a tal fi, les capacitats garanteixen una representació adequada i explícita de tal dinàmica. Aquest enfocament canvia i millora la manera com els agents poden coordinar-se per a portar a terme tasques i com gestionar les seves interaccions i compromisos en entorns cooperatius. L'enfocament s'ha comprovat en escenaris on la coordinació és important, beneficiosa i necessària. Els resultats i les conclusions són presentats ressaltant els avantatges de la introspecció en la millora del rendiment dels sistemes multi-agent en tasques coordinades i assignació de tasques.

Semiactive control strategies for vibration mitigation in adaptronic structures equipped with magnetorheological dampers

Los sistemas tales como edificios y veh¨ªculos est¨¢n sujetos a vibraciones que pueden causar mal funcionamiento, incomodidad o colapso. Para mitigar estas vibraciones, se suelen instalar amortiguadores. Estas estructuras se convierten en sistemas adaptr¨®nicos cuando los amortiguadores son controlables. Esta tesis se enfoca en la soluci¨®n del problema de vibraciones en edificios y veh¨ªculos usando amortiguadores magnetoreol¨®gicos (MR). Estos son unos amortiguadores controlables caracterizados por una din¨¢mica altamente no lineal. Adem¨¢s, los sistemas donde se instalan se caracterizan por la incertidumbre param¨¦trica, la limitaci¨®n de medidas y las perturbaciones desconocidas, lo que obliga al uso de t¨¦cnicas complejas de control. En esta tesis se usan Backstepping, QFT y H2/H¡Þ mixto para resolver el problema. Las leyes de control se verifican mediante simulaci¨®n y experimentaci¨®n.