Evaluating the Impact of the Number of Access Points in Mobile Robots Localization Using Artificial Neural Networks Gustavo Pessin, Fernando S. Osório, Jó Ueyama, Jefferson R. Souza, Denis F. Wolf Institute of Mathematics and Computer Science (ICMC) University of São Paulo (USP) – São Carlos, SP, Brazil {pessin, fosorio, joueyama, jrsouza, denis}@icmc.usp.br Torsten Braun Institute of Computer Science and Applied Mathematics University of Bern – Bern, Switzerland braun@iam.unibe.ch Patrícia A. Vargas School of Maths and Computer Science (MACS) Heriot-Watt University – Edinburgh, Scotland p.a.vargas@hw.ac.uk ABSTRACT Localization is information of fundamental importance to carry out various tasks in the mobile robotic area. The ex- act degree of precision required in the localization depends on the nature of the task. The GPS provides global po- sition estimation but is restricted to outdoor environments and has an inherent imprecision of a few meters. In indoor spaces, other sensors like lasers and cameras are commonly used for position estimation, but these require landmarks (or maps) in the environment and a fair amount of compu- tation to process complex algorithms. These sensors also have a limited field of vision. Currently, Wireless Networks (WN) are widely available in indoor environments and can allow efficient global localization that requires relatively low computing resources. However, the inherent instability in the wireless signal prevents it from being used for very ac- curate position estimation. The growth in the number of Access Points (AP) increases the overlap signals areas and this could be a useful means of improving the precision of the localization. In this paper we evaluate the impact of the number of Access Points in mobile nodes localization using Artificial Neural Networks (ANN). We use three to eight APs as a source signal and show how the ANNs learn and generalize the data. Added to this, we evaluate the robustness of the ANNs and evaluate a heuristic to try to decrease the error in the localization. In order to validate our approach several ANNs topologies have been evaluated in experimental tests that were conducted with a mobile Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. To copy otherwise, to republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. COMSWARE ’11, July 4th - 5th 2011, Verona, Italy Copyright 2011 ACM 978-1-4503-0560-0/11/07 ...$10.00. node in an indoor space. 1. INTRODUCTION The ability to estimate position correctly is a prerequisite to undertake a number of tasks in the autonomous mobile robotic area. Moreover, knowledge about localization can be used to track animals and people (e.g. to track the move- ment of people while practicing sports). Sensors like GPS can be used to provide global position estimation but this is restricted to outdoor environments and has an inherent imprecision of a few meters. While the use of GPS is quite common outdoors as a primary source for locating a posi- tion, a more accurate estimation can be obtained through a fusion of other sensors, like lasers and cameras [1]. In indoor spaces, sensors like lasers and cameras can be used for pose estimation [12, 16], but they require landmarks (or maps) in the environment and a fair amount of compu- tation to process complex algorithms. These sensors also have a limited field of vision, which makes the task of local- ization harder. In the case of video cameras, the variation of light is also a serious issue. Another commonly used sen- sor is the encoder, which provides odometry. Odometry is a useful source of information in some cases [2, 14] but it has an incremental error that usually invalidates its use in real systems. Wireless Networks are widely available in indoor environ- ments and allow efficient global localization, while requir- ing relatively low computing resources. Other advantages of this approach are scalability, robustness, and independence of specific features of the environment. However, the in- herent instability of the wireless signal does not allow it to be used directly for accurate position estimation. One ma- chine learning technique that could reduce the instability of the signals of the WN is the Artificial Neural Networks; this is due to its capacity to learn from examples, as well as the generalization and adaptation of the outputs. It is a method that is widely used in applications that require