Improvements of Object Grabbing Method by Using Color Images and Neural Networks Classification

The works presented in this paper allow the improvement of an object grabbing method developed for the ARPH project (Robotic Assistance for Disabled people). The basic tool of this project is a mobile robot with an embedded MANUS arm. The main aim of the method developed here is to make a manipulator arm equipped with a gripper and two kinds of sensors (camera and sonar) able to seizure and handle several objects in the human environment. Ultrasonic echo is recovered by a neural network classifier in order to recognize the object shape. At the same time, a little wireless HF camera takes a color image of the target, which allows to compute the coordinates of the object in the image then in the camera frame. The combination of these various information about the object with the camera geometrical model and the visual servoing principle allows to adopt an iterative strategy to approach the object under good conditions and to seize it at the end. Two kinds of object are used (spherical and cylindrical) with several colors and diameters