Showing papers by "Takashi Kubota published in 1991"

Self-Organizing Visual Servo System based on Neural Networks

Abstract: This paper proposes a neural network based self-organing control concept for a robotic manipulator. The end-effector position and orientation control loop is closed using visual data to generate the necessary manipulator control inputs. The objective is to move the end-effector to a place, where the manipulator can easily grip a given object. Instead of processing inverse kinematics, the nonlinear mapping between image data and joint angles is learned using two neural networks. The system organizes itself for any manipulator configuration by this learning process. The effectiveness of the proposed system is confirmed by computer simulations.

A scheme for visual tracking of robot manipulator using neural network

Abstract: The authors describe a control scheme and a strategy for a robotic manipulator using visual information to track a moving object. The proposed system directly integrates the visual data into the control process without calculating a transformation from world coordinate to workpiece coordinate, and without solving the inverse kinematics of the manipulator. Neural networks are used for learning the reproduction of the nonlinear relationship between image data and control signal in the joint angle space to achieve the desired pose. After they have finished learning such a task, the neural networks are used as a controller to track a moving object. >

Visual Control of Robotic Manipulator Based on Artificial Neural Network

Abstract: This paper describes a control scheme for a robotic manipulator system which uses visual information to position and orientate the end-effector. In the scheme the position and the orientation of the target workpiece with respect to the base frame of the robot are assumed to be unknown, but the desired relative position and orientation of the end-effector to the target workpiece are given in advance. The control system directly integrates visual data into the servoing process without subdi-viding the process into determination of the position and orientation of the workpiece and inverse kinematic calculation. An artificial neural network system is used for determining the change in joint angles required in order to achieve the desired position and orientation. The proposed system can control the robot so that it approach the desired position and orientation from arbitrary initial ones. Simulation for the robotic manipulator with six degrees of freedom is done. The validity and the effectiveness of the proposed control scheme are verified by computer simulations.