Controlling a Humanoid Robot Arm for Grasping and Manipulating a Moving Object in the Presence of Obstacles without Cameras

—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 manipulating a 7-DoF WAM robotic arm equipped with the Barrett hand to grasp and handle any moving objects in the 3-D environment in the presence of obstacles and without using the cameras. We used the OpenRAVE simulation environment. We use an extension of RRT-JT algorithm that interleaves exploration using a Rapidly-exploring Random Tree with exploitation using Jacobian-based gradient descent to control the 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.