3D Goods allocation in warehouse with L-GEM based 3-D RFID positioning

Radio frequency identification (RFID) technology has a wide range of industrial applications because of its low cost. In this paper, RFID is used for indoor object positioning system and we focus on the scenario of goods allocation in a warehouse. An Radial Basis Function Neural Network (RBFNN) is trained via a minimization of the Localized Generalization Error (L-GEM) to learn the object location based on received RFID signals from multiple RFID readers. Goods are stacked in 3-Dimensional ways in a warehouse, the RBFNN outputs 3-D vectors as the predicted locations of target goods. The proposed method is robust to uncertainty and changes in environment. Using MATLAB simulations, the experimental result shows that the proposed method yields an efficient indoor positioning.