Robot Wrist Configurations, Mechanisms and Kinematics

This paper discusses the use of multiple vision sensors and a proximity sensor to obtain three-dimensional occupancy profile of robotic workspace, identify key features, and obtain a 3-D model of the objects in the work space. The present research makes use of three identical vision sensors. Two of these sensors are mounted on a stereo rig on the sidewall of the robotic workcell. The third vision sensor is located above the workcell. The vision sensors on the stereo rig provide information about three-dimensional position of any point in the robotic workspace. The camera to robot calibration for these vision sensors in stereo configuration has been obtained with the help of a three-layered feedforward neural network. Squared Sum of Difference (SSD) algorithm has been used to obtain the stereo matching. Similarly, camera to robot transformation for the camera located above the work cell has been obtained with the help of a three-layered feedforward neural network. Three-dimensional positional information from vision sensors on stereo rig and two-dimensional positional information from a camera located above the workcell and a proximity sensor mounted on the robot wrist have been fused with the help of Bayesian technique to obtain more accurate positional information about locations in workspace.

Download Full-text

DATA FUSION OF ROBOT WRIST FORCES BASED ON FINGER FORCE SENSORS AND MLF NEURAL NETWORK

International Journal of Information Acquisition ◽

10.1142/s0219878905000507 ◽

2005 ◽

Vol 02 (02) ◽

pp. 101-111

Author(s):

LI-BIAO TONG ◽

WEN-JUN LU ◽

XIN HONG ◽

TAO MEI ◽

KE-JUN XU

Keyword(s):

Neural Network ◽

Quantitative Analysis ◽

Data Fusion ◽

Sensor Fusion ◽

Robot Control ◽

Experimental Results ◽

Force Sensors ◽

Finger Force ◽

Fusion Methods ◽

Robot Wrist

Quantitative analysis of wrist forces for robot grippers is an important issue for robot control and operation safety. An approach is proposed to deduce the wrist forces from distributed force sensors in the robot fingers. A multi-layer forward (MLF) neural network is designed to fuse the data from finger force sensors. The experimental results demonstrate that the maximum deducing error of the wrist forces is decreased to 4.8% from 18.7% comparing with previous sensor fusion methods.

Download Full-text

Transition from Sitting to Standing after Trans-Femoral Amputation

Prosthetics and Orthotics International ◽

10.1080/03093640500199612 ◽

2005 ◽

Vol 29 (2) ◽

pp. 139-151 ◽

Cited By ~ 19

Author(s):

Helena Burger ◽

Jernej Kuželički ◽

Črt Marinček

Keyword(s):

Daily Activity ◽

Healthy Subjects ◽

The Body ◽

Body Motion ◽

Prosthetic Foot ◽

Ankle Joints ◽

Standing Up ◽

Robot Wrist ◽

Healthy Side ◽

In Trans

Standing up is an important and common daily activity. It is essential for independence and a prerequisite for walking. Many elderly and many subjects with impairments have problems with transition from sitting to standing. The aim of the present study was to determine whether there was any difference between the characteristics of standing up in trans-femoral amputees and healthy subjects. Five young trans-femoral amputees and five healthy subjects were included in the study. They were asked to stand up. The body motion was recorded using an Optotrak contactless optical system. The force and moment vectors exerted on the seat were recorded by a JR3 six-axis robot wrist sensor. The force under the feet was recorded by two AMTI force plates. The trans-femoral amputees were found to stand up more slowly than the healthy subjects. The angles of the hip, knee, and ankle joints on the amputated side were different from the angles on the healthy side or in the healthy subjects. There was also a great difference in loading between the healthy and the prosthetic foot. It can be concluded that there are differences in standing up between the trans-femoral amputees and the healthy subjects. These differences may indicate a reason for problems many elderly trans-femoral amputees face when standing up.

Download Full-text

Gesture Based Control of a Simulated Robot Manipulator

Volume 9: 2015 ASME/IEEE International Conference on Mechatronic and Embedded Systems and Applications ◽

10.1115/detc2015-47419 ◽

2015 ◽

Author(s):

Sukhdeep S. Dhami ◽

Ashutosh Sharma ◽

Rohit Kumar ◽

Parveen Kalra

Keyword(s):

Inverse Kinematics ◽

Graphical Model ◽

Robot Manipulator ◽

Reference Signal ◽

Human Robot Interaction ◽

Human Hand ◽

Hand Gestures ◽

Matlab Simulink ◽

Robot Wrist ◽

Forward And Inverse Kinematics

The number of industrial and household robots is fast increasing. A simpler human-robot interaction is preferred in household robotic applications as well as in hazardous environments. Gesture based control of robots is a step in this direction. In this work, a virtual model of a 3-DOF robotic manipulator is developed using V-Realm Builder in MATLAB and the mathematical models of forward and inverse kinematics of the manipulator are coded in MATLAB/Simulink software. Human hand gestures are captured using a smartphone with accelerometer and orientation sensors. A wireless interface is provided for transferring smartphone sensory data to a laptop running MATLAB/Simulink software. The hand gestures are used as reference signal for moving the wrist of the robot. A user interface shows the instantaneous joint angles of robot manipulator and spatial coordinates of robot wrist. This simple yet effective tool aids in learning a number of aspects of robotics and mechatronics. The animated graphical model of the manipulator provides a better understanding of forward and inverse kinematics of robot manipulator. The robot control using hand gestures generates curiosity in student about interfacing of hardware with computer. It may also stimulate new ideas in students to develop virtual learning tools.

Download Full-text