• 한국해양공학회:학술대회논문집
• /
• 한국해양공학회 2004년도 학술대회지
• /
• pp.204-209
• /
• 2004

This paper describes dynamic manipulability analysis of robotic arms moving in viscous fluid. The Manipulability is a functionality of manipulator system in a given configuration and under the limits of joint ability with respect to the tasks required to bt performed. To investigate the manipulability of underwater robotic arms, a modeling and analysis method are presented. The dynamic equation of motion of underwater manipulator is derived from the Lagrange - Euler equation considering with the hydraulic forces caused by added mass, buoyancy and hydraulic drag. The hydraulic drag term in the equation: is established as analytical form using Denavit - Hartenberg (D-H) link coordination of manipulator. Two analytical approaches based on Manipulability Ellipsoid are presented to visualize the manipulability of robotic arm moving in viscous fluid. The one is scaled ellipsoid which transforms the boundary of joint torque to acceleration boundary of end-effector by normalizing the torque in joint space while the other is shifted ellipsoid which depicts total acceleration boundary of end-effector by shifting the ellipsoid in work space. An analysis example of 2-link manipulator with proposed analysis scheme is presented to validate the method.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 하계종합학술대회 논문집(5)
• /
• pp.153-156
• /
• 2002

The remotely operated underwater robotic vehicle system has been required to inspect some objects such as baffle former bolts and remove foreign objects in reactor vessel of nuclear power plant. In this paper, we have designed the remotely operated underwater robotic vehicle system that includes a long reach arm that is composed of 4 joints to remove foreign objects in a narrow space, a camera for visual test, instrument sensors for vehicle positioning, 4 thrusters for underwater navigation of vehicle, and supervisory control system implemented with industrial PC that includes robot simulator that has the functions of real time visualization, robot work planning and etc.

• 제어로봇시스템학회논문지
• /
• 제11권8호
• /
• pp.688-695
• /
• 2005

This paper describes dynamic manipulability analysis of robotic arms moving in viscous fluid. The manipulability is a functionality of manipulator system in a given configuration under the limits of joint ability with respect to the task required to be performed. To investigate the manipulability of underwater robotic arms, a modeling and analysis method is presented. The dynamic equation of motion of underwater manipulator is derived based on the Lagrange-Euler equation considering with the hydrodynamic forces caused by added mass, buoyancy and hydraulic drag. The hydrodynamic drag term in the equation is established as analytical form using Denavit-Hartenberg (D-H) link coordination of manipulator. Two analytical approaches based oil manipulability ellipsoid are presented to visualize the manipulability of robotic arm moving in viscous fluid. The one is scaled ellipsoid which transforms the boundary of joint torque to acceleration boundary of end-effector by normalizing the torques in joint space, while the other is shifted ellipsoid which depicts total acceleration boundary of end-effector by shifting the ellipsoid as much as gravity and velocity dependent forces in work space. An analysis example of 2-link manipulator with proposed analysis scheme is presented to validate the method.

• Journal of Advanced Research in Ocean Engineering
• /
• 제3권3호
• /
• pp.136-148
• /
• 2017

The paper presents dual arm ROV manipulation using deep reinforcement learning. The purpose of this underwater manipulator is to investigate and excavate natural resources in ocean, finding lost aircraft blackboxes and for performing other extremely dangerous tasks without endangering humans. This research work emphasizes on a self-learning approach using Deep Reinforcement Learning (DRL). DRL technique allows ROV to learn the policy of performing manipulation task directly, from raw image data. Our proposed architecture maps the visual inputs (images) to control actions (output) and get reward after each action, which allows an agent to learn manipulation skill through trial and error method. We have trained our network in simulation. The raw images and rewards are directly provided by our simple Lua simulator. Our simulator achieve accuracy by considering underwater dynamic environmental conditions. Major goal of this research is to provide a smart self-learning way to achieve manipulation in highly dynamic underwater environment. The results showed that a dual robotic arm trained for a 3DOF movement successfully achieved target reaching task in a 2D space by considering real environmental factor.