820 ROBOT-HUMAN COOPERATION HOLDING AND HANDLING A PIECE OF FABRIC PANAGIOTIS N. KOUSTOUMPARDIS Mechanical Engineering and Aeronautics Department, University of Patras Rio Patras, 26504, Greece NIKOS A. ASPRAGATHOS Mechanical Engineering and Aeronautics Department, University of Patras Rio Patras, 26504, Greece A Neural Network force control of a robot manipulator collaborating with a human to handle a fabric is presented. A robotic gripper holds the one end of a piece of fabric while a human hand holds the opposite end. As the human moves the fabric arbitrarily, the robot tries to manipulate the fabric according to the required handling task. The task could be defined in a higher-level decision making process which is based on the artificial constrains of the handling task and influenced by the human needs. A force sensor mounted on the wrist of the robot manipulator measures the 3-components (F x , F y , F z ) of the actual force applied by the human hand to the fabric, and the formulated force errors are used in the backpropagation algorithm, which trains the Neural Network force controller. The controller is tested in a simple case of a desired handling task and the results are discussed and compared with the reversed case, i.e. the robot moves the fabric arbitrarily and the human tries to manipulate the fabric according to the handling task. The response of the controller show that the robot is capable to handle the fabric according to the desired constrains. 1. Introduction The robotic handling of non-rigid materials such as fabrics is a very complicated problem due to the unpredictable behavior of the fabrics. The very low bending resistance of the fabrics, the large deformations and the materials’ non-linearity are factors increasing the complexity and difficulty for the robotic handling of non-rigid materials, which belongs to an interesting open research field. This research field deals with robots cooperating with other robots, machines or humans and assist humans in every day domestic or industrial handling tasks. Various force control methods for handling rigid bodies appeared in the robotics literature. However, the research for handling limp materials is very limited. A PID force control has been used in [1] where the fabric is fixed in the one edge and pooled by a robot from the opposite edge. Recently, Neural Networks have