Janét, Jason A.; Gutierrez, Ricardo; Chase, Troy A.; White, Mark W.; Sutton, John C. III Autonomous mobile robot global self-localization using Kohonen and region-feature neural networks. (English) Zbl 0876.70006 J. Rob. Syst. 14, No. 4, 263-282 (1997). We present and compare two neural network-based approaches to global self-localization (GSL) for autonomous mobile robots using: (1) a Kohonen neural network; and (2) a region-feature neural network. Both approaches categorize discrete regions of space (topographical nodes) in a manner similar to optical character recognition. Hence, it is believed that an autonomous vehicle can determine which room it is in from sensory data gathered from exploration. With a robust exploration routine, the GSL solution can be time-, translation-, and rotation-invariant. The GSL solution can also become independent of the mobile robot used to collect the sensor data. Cited in 1 Document MSC: 70B15 Kinematics of mechanisms and robots 92B20 Neural networks for/in biological studies, artificial life and related topics Keywords:topographical nodes; optical character recognition; sensor data PDFBibTeX XMLCite \textit{J. A. Janét} et al., J. Rob. Syst. 14, No. 4, 263--282 (1997; Zbl 0876.70006) Full Text: DOI