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

Using petri nets to specify and execute missions for autonomous underwater vehicles

This paper presents the design and implementation of a mission control system (MCS) for an autonomous underwater vehicle (AUV) based on Petri nets. In the proposed approach the Petri nets are used to specify as well as to execute the desired autonomous vehicle mission. The mission is easily described using an imperative programming language called mission control language (MCL) that formally describes the mission execution thread. A mission control language compiler (MCL-C) able to automatically translate the MCL into a Petri net is described and a real-time Petri net player that allows to execute the resulting Petri net onboard an AUV are also presented

Dynamic modelling of an underwater vehicle

Nessie is an Autonomous Underwater Vehicle (AUV) created by a team of students in the Heriot Watt University to compete in the Student Autonomous Underwater Competition, Europe (SAUC-E) in August 2006. The main objective of the project is to find the dynamic equation of the robot, dynamic model. With it, the behaviour of the robot will be easier to understand and movement tests will be available by computer without the need of the robot, what is a way to save time, batteries, money and the robot from water inside itself. The object of the second part in this project is setting a control system for Nessie by using the model

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

An approach to vision-based station keeping for an unmanned underwater vehicle

This paper presents an automatic vision-based system for UUV station keeping. The vehicle is equipped with a down-looking camera, which provides images of the sea-floor. The station keeping system is based on a feature-based motion detection algorithm, which exploits standard correlation and explicit textural analysis to solve the correspondence problem. A visual map of the area surveyed by the vehicle is constructed to increase the flexibility of the system, allowing the vehicle to position itself when it has lost the reference image. The testing platform is the URIS underwater vehicle. Experimental results demonstrating the behavior of the system on a real environment are presented

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

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

Positioning an underwater vehicle through image mosaicking

Mosaics have been commonly used as visual maps for undersea exploration and navigation. The position and orientation of an underwater vehicle can be calculated by integrating the apparent motion of the images which form the mosaic. A feature-based mosaicking method is proposed in this paper. The creation of the mosaic is accomplished in four stages: feature selection and matching, detection of points describing the dominant motion, homography computation and mosaic construction. In this work we demonstrate that the use of color and textures as discriminative properties of the image can improve, to a large extent, the accuracy of the constructed mosaic. The system is able to provide 3D metric information concerning the vehicle motion using the knowledge of the intrinsic parameters of the camera while integrating the measurements of an ultrasonic sensor. The experimental results of real images have been tested on the GARBI underwater vehicle

Reconfigurable Architecture To Estimate The Motion Of An Underwater Vehicle

This work proposes a parallel architecture for a motion estimation algorithm. 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 numbers of data-pixel. One of the solutions to estimate motions involves detection of the correspondences between two images. Due to its regular processing scheme, parallel implementation of correspondence problem can be an adequate approach to reduce the computation time. This work introduces parallel and real-time implementation of such low-level tasks to be carried out from the moment that the current image is acquired by the camera until the pairs of point-matchings are detected

Visual SLAM for 3D large-scale seabed acquisition employing underwater vehicles

This paper presents a novel technique to align partial 3D reconstructions of the seabed acquired by a stereo camera mounted on an autonomous underwater vehicle. Vehicle localization and seabed mapping is performed simultaneously by means of an Extended Kalman Filter. Passive landmarks are detected on the images and characterized considering 2D and 3D features. Landmarks are re-observed while the robot is navigating and data association becomes easier but robust. Once the survey is completed, vehicle trajectory is smoothed by a Rauch-Tung-Striebel filter obtaining an even better alignment of the 3D views and yet a large-scale acquisition of the seabed

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

Probabilistic sonar scan matching for an AUV

This paper proposes MSISpIC, a probabilistic sonar scan matching algorithm for the localization of an autonomous underwater vehicle (AUV). The technique uses range scans gathered with a Mechanical Scanning Imaging Sonar (MSIS), the robot displacement estimated through dead-reckoning using a Doppler velocity log (DVL) and a motion reference unit (MRU). The proposed method is an extension of the pIC algorithm. An extended Kalman filter (EKF) is used to estimate the robot-path during the scan in order to reference all the range and bearing measurements as well as their uncertainty to a scan fixed frame before registering. The major contribution consists of experimentally proving that probabilistic sonar scan matching techniques have the potential to improve the DVL-based navigation. The algorithm has been tested on an AUV guided along a 600 m path within an abandoned marina underwater environment with satisfactory results

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

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