Abstract
Radio Frequency Identification (RFID) technology is broadly deployed for improving trade and transactions. An RFID tag can identify the region (position) where it resides; thus, a popular trend among researchers is to deploy RFID technology for mobile robot localization. Because the intensities of signals at adjacent regions are similar to each other, it is a challenge to employ an RFID system as a sensor. In this proposed system, tags are scattered throughout a mobile robot’s environment in a constrained random pattern and are treated as landmarks. An RFID receiver is mounted on a mobile robot that can navigate such an environment. The robot senses all landmarks in the vicinity to acquire the IDs and received signal strength indicator (RSSI) measurements of the scattered tags. The robot can locate itself depending on the classification result provided by a feed-forward back-propagation artificial neural network (BPANN) supplied with a set of all RSSI measurements read by this robot at a specific location. To be acceptable, this set should only have one high RSSI measurement. The robot senses the location information from a high-valued RSSI tag and adds it to a list of tag IDs along with the corresponding location information. The robot can use this information to travel between any two identified locations. The experimental results demonstrate the efficiency of this proposed system.