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

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

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

Perspectives of auto-correcting lens distortions in mosaic-based underwater navigation

When unmanned underwater vehicles (UUVs) perform missions near the ocean floor, optical sensors can be used to improve local navigation. Video mosaics allow to efficiently process the images acquired by the vehicle, and also to obtain position estimates. We discuss in this paper the role of lens distortions in this context, proving that degenerate mosaics have their origin not only in the selected motion model or in registration errors, but also in the cumulative effect of radial distortion residuals. Additionally, we present results on the accuracy of different feature-based approaches for self-correction of lens distortions that may guide the choice of appropriate techniques for correcting distortions

On the way to solve lighting problems in underwater imaging

A major obstacle to processing images of the ocean floor comes from the absorption and scattering effects of the light in the aquatic environment. Due to the absorption of the natural light, underwater vehicles often require artificial light sources attached to them to provide the adequate illumination. Unfortunately, these flashlights tend to illuminate the scene in a nonuniform fashion, and, as the vehicle moves, induce shadows in the scene. For this reason, the first step towards application of standard computer vision techniques to underwater imaging requires dealing first with these lighting problems. This paper analyses and compares existing methodologies to deal with low-contrast, nonuniform illumination in underwater image sequences. The reviewed techniques include: (i) study of the illumination-reflectance model, (ii) local histogram equalization, (iii) homomorphic filtering, and, (iv) subtraction of the illumination field. Several experiments on real data have been conducted to compare the different approaches

Towards a real-time vision-based navigation system for a small-class UUV

This paper deals with the problem of navigation for an unmanned underwater vehicle (UUV) through image mosaicking. It represents a first step towards a real-time vision-based navigation system for a small-class low-cost UUV. We propose a navigation system composed by: (i) an image mosaicking module which provides velocity estimates; and (ii) an extended Kalman filter based on the hydrodynamic equation of motion, previously identified for this particular UUV. The obtained system is able to estimate the position and velocity of the robot. Moreover, it is able to deal with visual occlusions that usually appear when the sea bottom does not have enough visual features to solve the correspondence problem in a certain area of the trajectory

Detection of matchings in a sequence of underwater images through texture analysis

This paper presents an approach to ameliorate the reliability of the correspondence points relating two consecutive images of a sequence. The images are especially difficult to handle, since they have been acquired by a camera looking at the sea floor while carried by an underwater robot. Underwater images are usually difficult to process due to light absorption, changing image radiance and lack of well-defined features. A new approach based on gray-level region matching and selective texture analysis significantly improves the matching reliability

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

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

Proposal of a parallel architecture for a motion detection algorithm

This paper proposes a parallel architecture for estimation of the motion of an underwater robot. 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. In a motion estimation algorithm, correspondences between two images have to be solved at the low level. In the underwater imaging, normalised correlation can be a solution in the presence of non-uniform illumination. Due to its regular processing scheme, parallel implementation of the correspondence problem can be an adequate approach to reduce the computation time. Taking into consideration the complexity of the normalised correlation criteria, a new approach using parallel organisation of every processor from the architecture is proposed