Controlling a Humanoid Robot Arm for Grasping and Manipulating a Moving Object without Cameras

Authors

  • Ali Chaabaani, Mohamed Sahbi Bellamine, and Moncef Gasmi Author

Keywords:

Grasping, moving object, trajectory planning, robot hand, obstacles.

Abstract

Many of researchers working on robotic grasping 
tasks assume a stationary or fixed object, others have focused 
on dynamic moving objects using cameras to record images of 
the moving object and then they treated their images to estimate 
the position to grasp it. This method is quite difficult, requiring 
a lot of computing, image processing… Hence, it should be 
sought more simple handling method. Moreover, the majorities 
of robotic arms available for humanoid applications are 
complex to control and yet expensive. In this paper, we are 
going to detail the requirements to manupilating a humanoid 
robot arm with 7 degree-of-freedom to grasp and handle any 
moving objects in the 3-D environment in the presence or not of 
obstacles and without using the cameras. We used the 
OpenRAVE simulation environment and a robot arm equipped 
with the Barrett hand. We also describe a randomized planning 
algorithm capable of planning. This algorithm is an extension of 
RRT-JT that interleaves exploration using a Rapidly-exploring 
Random Tree with exploitation using Jacobian-based gradient 
descent to control a 7-DoF WAM robotic arm to avoid the 
obstacles, track a moving object, and grasp planning. We 
present results in which a moving mug is tracked, stably 
grasped with a maximum rate of success in a reasonable time 
and picked up by the Barret hand to a desired position. 

Downloads

Download data is not yet available.

Downloads

Published

06.07.2015

How to Cite

Controlling a Humanoid Robot Arm for Grasping and Manipulating a Moving Object without Cameras . (2015). International Journal of Information and Electronics Engineering, 5(4), 286-294. https://www.ijiee.org/index.php/ijiee/article/view/429