A Biologically Inspired Neural Network for Autonomous Underwater Vehicles

Autonomous Underwater vehicles (AUV) with reconfigurable payloads are rapidly becoming common. Their dynamic characteristics are affected when payloads change. Typically, retuning of the controller is required to maintain good control performance. To address this situation, we develop a technique to enable rapid identification of AUV dynamics online. We demonstrate the technique with a fin-controlled single-thruster torpedo-shaped AUV. By decoupling the system according to planar and horizontal motion, mathematical models for yaw and pitch dynamics are developed. This results in a second-order transfer function with auxiliary steady state fin deflection. Identification of continuous-time model was performed to preserve the physical meaning of the parameters. Identification in continuous-time requires time-derivative terms which are reconstructed using the state variable filter (SVF). Then, recursive least-square (RLS) algorithm is used to identify the unknown parameters. The proposed identification method was validated through field deployments of our AUVs. The online estimates compare favorably with results obtained from offline identification methods requiring numerical optimization. We demonstrate how turning radius of the AUV can be estimated accurately from the identified parameters. We also show how a gain-scheduled controller, with better control performance than a constant-gain controller, can be designed using the estimated parameters.

Autonomous underwater vehicles (AUVs) have become main tools for underwater survey in scientific, military, and commercial applications. A significant amount of onboard power is needed to execute long-range missions; however, energy storage is limited in AUV. This paper presents a novel landing AUV that can land on the sea floor to perform long-term monitoring and measuring tasks and save onboard electric energy. The AUV has following characteristics. Firstly, a triangular structure of the AUV which is composed of three cabins is used to achieve stable bottom sitting. Secondly, the releasing mechanism is designed to eject and recover the AUV. Bottom sitting and recovering is verified by ocean trials. This paper provides guidance for design of similar AUVs.

Autonomous underwater vehicles (AUVs) have many, scientific, military, and commercial applications because of their potential capabilities and significant cost-performance improvements. Typical AUV development requires critical system design and many costly at-sea trials during which systems specifications can be validated. Modeling and simulation provides a cost-effective method for carrying out preliminary component or system (hardware and software) testing and verification. Due to the complexity of most AUV development and their tight schedules, the simulated systems often differ considerably from the actual embedded architecture, thereby reducing the fidelity of the entire simulation. We adopted a hardware-in-the-loop (HIL) simulation approach that includes some level of the system's hardware and software. As expected, an HIL simulation requires all components be run under hard real-time constraint. The paper presents our implementation and considerations on HIL simulation for single and multiple vehicles. A brief mention of sensor and environment modeling is also provided.

Autonomous underwater vehicles (AUVs) allow us to survey and explore globally and freely in vast deep sea. We aim to develop long cruising range AUVs (LCAUVs) for researches of the global change, ocean-trench earthquake, and biodiversity and for exploring ocean resources. We have developed the first prototype of LCAUV, Urashima since 1998. The vehicle powered by a PEFC system marked the world record of cruising distance of 317 kilometers in 2005. The vehicle, 10 m long and 10 tons in weight, has the specifications: maximum depth ratings; 3500 m, maximum cruising speed; 3.2 knots, and endurance; 60 hours. This large vehicle has large user payload of a few hundreds kilograms. In 2007, research and development of the elemental technologies which will be utilizes for development of the second generation LCAUV started to expand cruising range to 3000 kilometers. For long range cruising, technology improvement of power sources, navigations, communications, and vehicle controlling are mainly important. Since endurance of the LCAUV becomes over 600 hours, during this cruising period the vehicle controller must autonomously deal with problems which may occur in any devices. If the vehicle controller does not recover a fatal problem, the controller appropriately leads status of the vehicle to quit an executing mission and ascend itself. We have improved the vehicle controller and plan sea-trials using the controller in January 2009. On the other hand, The AUV, MR-X1, 2.4 m long and 800 kg in weight, has been developed for scientific research and the test bed of the LCAUVs since 2000. This working AUV is also needed for installing or recovering observation equipment, tracking and sampling benthos or planktons, and doing simple repetitive works. The first sea-trial of MR-X1 was carried out in 2003. After that, the MR-X1 system is only used as a test bed of the developed devices in the LCAUV project. In this year, we have developed new items, a device installer on the sea-floor and mud core sampler for the MR-X1. In the technical report, a redundant controlling system for the LCAUV installed on the MR-X1 is described. And new items and their test results will be reported.

Autonomous Underwater Vehicles (AUVs) are widely used for marine survey, in both the coastal and deep sea areas and they are applicable to both civil and defense applications. They are pre-programmed and can operate without human intervention and this makes them attractive to many marine industries. A concern with AUVs is the high energy consumption required by their thrusters for depth control, buoyancy change and manoeuvrability and that adversely affects their performance and endurance. This paper presents the design and development of novel stand-alone variable buoyancy system for AUVs and investigates its performance through numerical and experimental investigations. The design idea is based upon the Pump Driven Variable Buoyancy System (PDVBS) and uses a hydraulic based method to control the buoyancy. The VBS is integrated into a medium sized AUV of 3 m length and the performance of the vehicle in vertical plane is investigated. The results are presented for a buoyancy change requirement of 5 kg and a diaphragm type positive displacement pump, with a buoyancy change rate of 5 kg/min, is utilized. Depth control performance of the AUV and its hovering capabilities, at a desired depth of 60 m using the Linear Quadratic Regulator (LQR) controller, are analysed in detail. Finally, the results indicate that the designed and developed VBS is effective in changing the buoyancy and controlling the heave velocity. These two features are expected to provide higher endurance and better performance in AUVs involved in rescue/attack operations.

Autonomous underwater vehicles (AUVs), unmanned underwater vehicles, are cheaper to operate than remotely operated vehicles (ROVs), since an AUV does not require a trained human operator to control. As a result, in this paper, we propose the pipeline tracking algorithm using sequences of the forward-looking sonar (FLS) images installed on a preprogram AUV. The FLS is more suitable to be used in the subsurface environment than an optical camera due to the limited visibility and floating particles in the sub-sea surface environment. In our work we first employed the speckle noise reduction to the FLS images. Then, we applied the level-set method (LSM) to extract a pipeline boundary in each frame. Lastly, the post-processing step was designed to link the unconnected segments together to from a complete pipeline. Our algorithm can perform the segmentation and tracking with more than 85% accuracy.

Autonomous underwater vehicles (AUVs) are becoming commonplace in the study of inshore coastal marine habitats. Combined with shipboard systems, scientists are able to make in-situ measurements of water column and benthic properties. In CSIRO, autonomous gliders are used to collect water column data, while surface vessels are used to collect bathymetry information through the use of swath mapping, bottom grabs, and towed video systems. Although these methods have provided good data coverage for coastal and deep waters beyond 50m, there has been an increasing need for autonomous in-situ sampling in waters less than 50m deep. In addition, the collection of benthic and water column data has been conducted separately, requiring extensive post-processing to combine data streams. As such, a new AUV was developed for in-situ observations of both benthic habitat and water column properties in shallow waters. This paper provides an overview of the Starbug X AUV system, its operational characteristics including vision-based navigation and oceanographic sensor integration.

Autonomous Underwater Vehicles (AUVs) are becoming increasingly popular for ocean exploration, industrial and military application. In particular, AUVs are becoming the attractive option for underwater search and survey operation as they are inexpensive compared to manned vehicles. Most of an AUV power is utilized by its propulsion system. Since the AUV power only depends on the onboard battery, the power consumption becomes a crucial issue in optimizing the AUV performance. In this study, the MSI300 propeller was analyzed in regards to its performance by using computational fluid dynamics (CFD). At first, a 3D scanner was used to capture the surface of the propeller and the geometry was converted into a nonuniform rational B-Spline Curve (NURBS) model. Then, CFD simulation was performed to analyze the propeller in the turbulent and Bollard pull condition. It was found that the thrust and torque coefficients are descending with the increasing value of advance ratio. The propeller efficiency is at 61.05%, which occurred at a 0.8 advance ratio. It shows that the CFD simulation has successfully represented the characteristics of the propeller.

Autonomous underwater vehicles (AUVs) are becoming increasingly ubiquitous due to the growing needs in exploring Ocean resources. One of the most challenging tasks in this domain relates to the energy these vehicles require, given the increase in the number of scientific payloads and on the mission complexity. One way to potentially reduce the amount of energy consumed during vertical motion is to replace or complement the thruster action with a controlled change of the vehicles floatation, using a variable buoyancy system (VBS). This paper presents the development of an electromechanical VBS for shallow depths, up to 100 m, to be included in an existing AUV. A preliminary mechanical design is presented, along with a mathematical model allowing the calculation of the energy spent by this device, based on the components manufacturers’ data. A comparison between the energy consumption using thrusters and the designed VBS is presented.

Autonomous underwater vehicles (AUVs) are poised to become an indispensable tool for ocean exploration, underwater research and development, and military activities. One of the key elements of these vehicles is dependability; there must be some form of fault recovery/fault tolerance in the control system. In this work, we use an approach involving synthesis of motions in degrees of freedom (DOF) that are unactuated, by combining motions in DOF that are actuated. The objective is to determine the usefulness of the method for a typical streamlined vehicle which is controlled by control surfaces rather than thrusters. We find that the method has difficulties in its present form because of the righting moment designed into the vehicle, but it is functional on a modified model of the vehicle.

Autonomous Underwater Vehicles (AUV) capable of adapting their mission planning in response to sensor data have applicability in a variety of applications. For example, to find the source of a chemical in a fluid environment, an AUV could search a region until it detects the chemical plume, then steer the vehicle based on real-time chemical detections and flow information to maneuver the vehicle toward the odor source. Behavior based planning (BBP) is a reactive mission planning approach that is ideally suited for such applications. This article reviews behavior based planning, describes an example BBP designed to locate the deepest location within a test area, and includes results from in-water experiments on a REMUS AUV. This experiment was a test exercise in preparation for the use of BBP on a REMUS class vehicle to trace chemical plumes to their source.

Autonomous Underwater Vehicles (AUVs) have found their application in exploration and surveillance. This paper proposes a cooperative distributed search algorithm based on a minimum entropy approach for AUVs with capabilities like multi agent exploration. The work is motivated by the project “Thesaurus”, whose among its own purposes has the survey of marine areas of archaeological interest in the Tuscan Archipelago. The cooperative algorithm is developed to move each vehicle on the exploration area taking into account communication constraints and a prior prediction probability map, which is updated on line during the mission. The prior probability map over the exploration area is built through Gaussian kernel approximation, on the basis of previous findings and historical archival data.

Autonomous Underwater Vehicles (AUVs) are becoming indispensable for the maritime industry and defense applications. The nonlinear, time-varying, and highly coupled dynamics of AUVs, along with the parametric uncertainties and unmodeled dynamics, make the design of efficient controllers a hard task. This article explores a robust control strategy that aims at providing better tracking accuracy by reducing the switching gain in order to reduce chattering and the control error bandwidth. The performance of the proposed controller is demonstrated through rigorous simulation on an experimentally validated AUV, and superior path tracking performance is noted against sliding mode and time delay control methodologies under various uncertain conditions.

Autonomous Underwater Vehicles (AUVs) are powerful tools for exploring, investigating and managing our ocean resources. As the capabilities of these platforms continue to expand and they continue to mature as operational assets, navigation remains a fundamental technological component. This chapter presents a road map for the vehicle designer to aid in integrating the latest navigation methods into new platforms for science, industry and military platforms. Along the way, we point to emerging needs where new research can lead directly to an expansion of the operational abilities of these powerful tools. To accomplish this we start by describing the problem, explaining the needs of vehicle users and the challenges of autonomous localization. Next we explain the state of practice, how operational assets currently solve this difficult problem. To expand this explanation we present new research targeted at helping AUV builders to make the complex tradeoffs in creating a platform with the appropriate navigation solution. We conclude with an overview of the latest research and how these advances might soon become available for AUV operations in new environments such as the littoral zone, at the poles and under-ice. Throughout this chapter we attempt to reach across the disciplinary boundaries that separate the researcher from the operator.

Autonomous Underwater Vehicles have gained popularity for the last decades, especially a lot of AUVs were considered as the most suitable tool for the purpose of reducing risks of people in dangerous marine operations. This paper presents the preliminary results of the research on hardware design, the controller of an autonomous underwater vehicle model for the task of survey, search and rescue ... With a compact design, AUV can operate in limited spaces. Through a unique ducted propeller and rudder located at the aft, the AUV can perform horizontal motion. It can also control pitch angle and depth motion by an inside mass shifter mechanism (MSM) which changes the vehicle center of gravity. In addition, The AUV is integrated with powerful eletronic system, highprecision sensors helping it carries on missions from simple to complex. The use of Sliding Mode Control (SMC) to independently design the heading and depth controllers for AUV demonstrates the steady stability of the controllers with the nonlinear model, uncertainty parameters and disturbances. Finally, the simulation results show that the SMC controllers can control the AUV nonlinear model to track the desired steering angle and depth with high accuracy and stability.