Reinforcement Learning applied to the control of an Autonomous Underwater Vehicle

نویسندگان

  • Chris Gaskett
  • David Wettergreen
  • Alexander Zelinsky
چکیده

At the Australian National University we are developing an autonomous underwater vehicle for exploration and inspection. Our aim is to develop on-board intelligent control. We intend that the vehicle will learn to control its thrusters in response to command and sensor inputs. Algorithms based on reinforcement learning with continuous state and actions are being developed for this purpose.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Reinforcement Learning for a Visually-guided Autonomous Underwater Vehicle

Reinforcement learning uses a scalar reward signal and much interaction with the environment to form a policy of correct behavior. We have applied this technique to the problem of developing a controller for an autonomous underwater vehicle and have achieved reliable off-line development of stable controllers. Many important underwater tasks rely upon on visual observation of underwater feature...

متن کامل

Design of Robust Finite-Time Nonlinear Controllers for a 6-DOF Autonomous Underwater Vehicle for Path Tracking Objective

In this paper, kinematic and dynamic equations of a 6-DOF (Degrees Of Freedom) autonomous underwater vehicle (6-DOF AUV) are introduced and described completely. By developing the nonsingular terminal sliding mode control method, three separate groups of control inputs are proposed for the autonomous underwater vehicle subjected to uncertainties including parametric uncertainties, unmodeled dyn...

متن کامل

OPTIMIZED FUZZY CONTROL DESIGN OF AN AUTONOMOUS UNDERWATER VEHICLE

In this study, the roll, yaw and depth fuzzy control of an Au- tonomous Underwater Vehicle (AUV) are addressed. Yaw and roll angles are regulated only using their errors and rates, but due to the complexity of depth dynamic channel, additional pitch rate quantity is used to improve the depth loop performance. The discussed AUV has four aps at the rear of the vehicle as actuators. Two rule bases...

متن کامل

Identification of an Autonomous Underwater Vehicle Dynamic Using Extended Kalman Filter with ARMA Noise Model

In the procedure of designing an underwater vehicle or robot, its maneuverability and controllability must be simulated and tested, before the product is finalized for manufacturing. Since the hydrodynamic forces and moments highly affect the dynamic and maneuverability of the system, they must be estimated with a reasonable accuracy. In this study, hydrodynamic coefficients of an autonomous un...

متن کامل

Autonomous Underwater Vehicle Hull Geometry Optimization Using a Multi-objective Algorithm Approach

Abstarct In this paper, a new approach to optimize an Autonomous Underwater Vehicle (AUV) hull geometry is presented. Using this methode, the nose and tail of an underwater vehicle are designed, such that their length constraints due to the arrangement of different components in the AUV body are properly addressed. In the current study, an optimal design for the body profile of a torpedo-shaped...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1999