In planning tasks a Robotic Agent (RA) must know a priori the environment map where it is located, which is a problem if the same RA faces a different environment. To overcome this problem, the RA must perform the task of Simultaneous Localization and Mapping (SLAM), to locate the agent in the environment while simultaneously generate the geometric or topological map. This article presents the design of a decentralized online system for SLAM by an autonomous RA, responsible for placing wireless sensor nodes based on its Received Signal Strength Indication (RSSI) and programming them with the estimated position by processing the RA odometry, creating a Multi-Agent System (MAS) by the construction of a Wireless Sensor Network (WSN). The validation of this system is driven in a non-uniform two-dimensional environment with respect to RA, showing the generation of an online topological map with an error of 8%, without the dependence of a central unit.