Reverse logistics research is used to analyze the processes associated with the flows of products, components and materials from end users to re-users in different industries. The products and components collected for reverse logistics are often widely dispersed, which complicates efforts to efficiently collect, reuse and reassemble used components for reprocessing and remanufacturing. Therefore, Radio Frequency Identification (RFID) technology combined with the EPCglobal network architecture is applied to facilitate product and component data collection and data transmission. This research proposes a decision support model that integrates fuzzy cognitive maps trained using a genetic algorithm. The advantage of using fuzzy cognitive maps is that the model and the relationships among nodes (states) can be linguistically expressed both quantitatively and qualitatively. Furthermore, to diminish the subjective effects of the weights, the genetic algorithm is applied. The model and the information system integrate the EPCglobal network architecture with the RFID technology. Finally, a case concerning automobile repair reverse logistics is used to demonstrate the usefulness of the approach.