No abstract

No abstract

The ocean covers about two-thirds of the earth and has a great effect on the future existence of all human beings. About 37% of the world's population lives within 100 km of the ocean. The ocean is generally overlooked as we focus our attention on land and atmospheric issues; we have not been able to explore the full depths of the ocean and its abundant living and non-living resources. For example, it is estimated that there are about 2,000 billion tons of manganese nodules on the floor of the Pacific Ocean near the Hawaiian Islands. We discovered, by using manned submersibles, that a large amount of carbon dioxide comes from the seafloor and extraordinary groups of organisms live in hydrothermal vent areas. Marine robots including unmanned surface vehicles and unmanned underwater vehicles can help us better understand marine and other environmental issues, protect the ocean resources of the earth from pollution, and efficiently utilize them for human welfare. This paper briefly presents some exemplary models of recent developments in marine robots in different application areas.

Abstmct-Underwater robotic vehicles have become an important tool to explore the secret life undersea. They are used for various purposes: Inspection, recovery, construction, etc. With the increased utilization of the vehicles in subsea applications, the development of autonomous vehicles becomes highly desirable to enhance operator efficiency. However, engineering problems associated with the high density, nonuniform, and unstructured seawater environment and the nonlinear response of the vehicle make a high degree of autonomy difficult to achieve. In this paper, results of the recent study on the application of neural networks to the underwater robotic vehicle control system are presented. The robustness of the control system with respect to the nonlinear dynamic behavior and parameter uncertainties is investigated by computer simulation. The results show the feasibility of using neural networks to control the vehicle in the presence of unpredictable changes in the dynamics of the vehicle and its environment.

In autonomous system, it is important to establish a control scheme that works with stability even near singularity conJigurations. In this article, we describe an on-line trajectory control scheme that uses the manipulability measure as a distance criteria to avoid manipulator singularities.The proposed approach consists in a method for limiting the minimum value of the distance criteria. The pe$ormance is simply affected by the choice of the lower limit. Based on a real-time evaluation of the measure of manipulability, this method does not require a preliminary knowledge of the singular configurations. The proposed algorithm is validated by experimental results.

During the last decade, the first autonomous under-In this paper, details of the development of ODIN-Ill are water robot Of the Autonomous system Laboratory Of the UNversity of Hawaii, ODIN (0"-Directional Intelligent Navigator) built in 1991 has produced a lot of valuable results in development control methods 11-51. Recently, ODIN was bo,.,, again in the 3rd eeneration with unioue features under recent techuoloeies described,-as well as the basic algorithm for the framework, and experimental results for a fine motion control scheme using a null motion solution considering practical issues such as energy consumption and thruster saturation. such-as abundant system resources owing to a PC104+, iew vehicle system software architectures with an object-oriented concept and its implementation, a graphical user interface and an independent algorithm module using a dynamic linking library (DLL) based on the Windows operating system. These give us an ideal enrimnment for developing various algorithms which are needed for developing an advanced underwater mbotic vehicle. This paper describes details of the development of ODIN-111 and presents Initial experimental results for fine motion control.

No abstract

Abstract-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.Index Terms-Autonomous underwater vehicle (AUV), behavior-based control, neural networks, reinforcement learning.