Laser-scanner-based self-localization for autonomous mobile robots using neural network
Dongbing Gu, Zhengxun Song · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 1998
This paper presents an approach to global self-localization for autonomous mobile robots based on the laser scanner. There are some reflective beacons fixed in the operating environment and their coordination is known a prior.The laser scanner can detect the angle between the robot's heading and the beacon by rotating the laser and receiver, but fail to recognize the exact beacon from which the scanner receives the signal. The Kohonen neural networks have been developed in this approach to recognize the beacons based on the measurement of the laser scanner. With the three of the recognized beacons, the localization of the mobile robots can be estimated by the triangle calculation.