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

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

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

Model-based objects recognition in man-made environments

We describe a model-based objects recognition system which is part of an image interpretation system intended to assist autonomous vehicles navigation. The system is intended to operate in man-made environments. Behavior-based navigation of autonomous vehicles involves the recognition of navigable areas and the potential obstacles. The recognition system integrates color, shape and texture information together with the location of the vanishing point. The recognition process starts from some prior scene knowledge, that is, a generic model of the expected scene and the potential objects. The recognition system constitutes an approach where different low-level vision techniques extract a multitude of image descriptors which are then analyzed using a rule-based reasoning system to interpret the image content. This system has been implemented using CEES, the C++ embedded expert system shell developed in the Systems Engineering and Automatic Control Laboratory (University of Girona) as a specific rule-based problem solving tool. It has been especially conceived for supporting cooperative expert systems, and uses the object oriented programming paradigm

Design and development of the architecture of an agricultural mobile robot

Parameters such as tolerance, scale and agility utilized in data sampling for using in Precision Agriculture required an expressive number of researches and development of techniques and instruments for automation. It is highlighted the employment of methodologies in remote sensing used in coupled to a Geographic Information System (GIS), adapted or developed for agricultural use. Aiming this, the application of Agricultural Mobile Robots is a strong tendency, mainly in the European Union, the USA and Japan. In Brazil, researches are necessary for the development of robotics platforms, serving as a basis for semi-autonomous and autonomous navigation systems. The aim of this work is to describe the project of an experimental platform for data acquisition in field for the study of the spatial variability and development of agricultural robotics technologies to operate in agricultural environments. The proposal is based on a systematization of scientific work to choose the design parameters utilized for the construction of the model. The kinematic study of the mechanical structure was made by the virtual prototyping process, based on modeling and simulating of the tension applied in frame, using the.

Information Exchange and Fusion in Dynamic and Heterogeneous Distributed Environments

Context awareness, dynamic reconfiguration at runtime and heterogeneity are key characteristics of future distributed systems, particularly in ubiquitous and mobile computing scenarios. The main contributions of this dissertation are theoretical as well as architectural concepts facilitating information exchange and fusion in heterogeneous and dynamic distributed environments. Our main focus is on bridging the heterogeneity issues and, at the same time, considering uncertain, imprecise and unreliable sensor information in information fusion and reasoning approaches. A domain ontology is used to establish a common vocabulary for the exchanged information. We thereby explicitly support different representations for the same kind of information and provide Inter-Representation Operations that convert between them. Special account is taken of the conversion of associated meta-data that express uncertainty and impreciseness. The Unscented Transformation, for example, is applied to propagate Gaussian normal distributions across highly non-linear Inter-Representation Operations. Uncertain sensor information is fused using the Dempster-Shafer Theory of Evidence as it allows explicit modelling of partial and complete ignorance. We also show how to incorporate the Dempster-Shafer Theory of Evidence into probabilistic reasoning schemes such as Hidden Markov Models in order to be able to consider the uncertainty of sensor information when deriving high-level information from low-level data. For all these concepts we provide architectural support as a guideline for developers of innovative information exchange and fusion infrastructures that are particularly targeted at heterogeneous dynamic environments. Two case studies serve as proof of concept. The first case study focuses on heterogeneous autonomous robots that have to spontaneously form a cooperative team in order to achieve a common goal. The second case study is concerned with an approach for user activity recognition which serves as baseline for a context-aware adaptive application. Both case studies demonstrate the viability and strengths of the proposed solution and emphasize that the Dempster-Shafer Theory of Evidence should be preferred to pure probability theory in applications involving non-linear Inter-Representation Operations.

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

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

Model-based objects recognition in man-made environments

We describe a model-based objects recognition system which is part of an image interpretation system intended to assist autonomous vehicles navigation. The system is intended to operate in man-made environments. Behavior-based navigation of autonomous vehicles involves the recognition of navigable areas and the potential obstacles. The recognition system integrates color, shape and texture information together with the location of the vanishing point. The recognition process starts from some prior scene knowledge, that is, a generic model of the expected scene and the potential objects. The recognition system constitutes an approach where different low-level vision techniques extract a multitude of image descriptors which are then analyzed using a rule-based reasoning system to interpret the image content. This system has been implemented using CEES, the C++ embedded expert system shell developed in the Systems Engineering and Automatic Control Laboratory (University of Girona) as a specific rule-based problem solving tool. It has been especially conceived for supporting cooperative expert systems, and uses the object oriented programming paradigm

Local WMR navigation with monocular data

This article presents recent WMR (wheeled mobile robot) navigation experiences using local perception knowledge provided by monocular and odometer systems. A local narrow perception horizon is used to plan safety trajectories towards the objective. Therefore, monocular data are proposed as a way to obtain real time local information by building two dimensional occupancy grids through a time integration of the frames. The path planning is accomplished by using attraction potential fields, while the trajectory tracking is performed by using model predictive control techniques. The results are faced to indoor situations by using the lab available platform consisting in a differential driven mobile robot

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

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.

Upper limb robot mediated stroke therapy - GENTLE/s approach

Stroke is a leading cause of disability in particular affecting older people. Although the causes of stroke are well known and it is possible to reduce these risks, there is still a need to improve rehabilitation techniques. Early studies in the literature suggest that early intensive therapies can enhance a patient's recovery. According to physiotherapy literature, attention and motivation are key factors for motor relearning following stroke. Machine mediated therapy offers the potential to improve the outcome of stroke patients engaged on rehabilitation for upper limb motor impairment. Haptic interfaces are a particular group of robots that are attractive due to their ability to safely interact with humans. They can enhance traditional therapy tools, provide therapy "on demand" and can present accurate objective measurements of a patient's progression. Our recent studies suggest the use of tele-presence and VR-based systems can potentially motivate patients to exercise for longer periods of time. The creation of human-like trajectories is essential for retraining upper limb movements of people that have lost manipulation functions following stroke. By coupling models for human arm movement with haptic interfaces and VR technology it is possible to create a new class of robot mediated neuro rehabilitation tools. This paper provides an overview on different approaches to robot mediated therapy and describes a system based on haptics and virtual reality visualisation techniques, where particular emphasis is given to different control strategies for interaction derived from minimum jerk theory and the aid of virtual and mixed reality based exercises.