Research on the Calibration Method for the Heading Errors of Mobile Robot Based on Evolutionary Neural Network Prediction

Conference PaperinLecture Notes in Computer Science · May 2005with5 Reads
Impact Factor: 0.51 · DOI: 10.1007/11427469_42 · Source: DBLP
Conference: Advances in Neural Networks - ISNN 2005, Second International Symposium on Neural Networks, Chongqing, China, May 30 - June 1, 2005, Proceedings, Part III

Fiber optic gyros (FOG) is the important sensor for measuring the heading of mobile robot. Combined with measured data of E-Core RD1100 interferometric FOG made by American KVH company, the paper analyses the common calibration for the heading errors of mobile robot caused by the drift of FOG, and uses the method of evolutionary neural networks prediction to compensate it. By the experiments of mobile robot prototype, the paper also proves this method can reduce the error influence of FOG on the heading of mobile robot and enhance the localization precision of mobile robot navigation.

  • [Show abstract] [Hide abstract] ABSTRACT: This paper presents a visual navigation method based on guideline visual recognition for wheeled robot to inspect equipment and instrument in unattended substation. Wheeled robot collects the road information via camera and recognizes the guideline. According the deviation of the guideline's actual location and intended location use the PID control technology controls the left and right wheel's speed to control the robot moving direction. The practical application in substation shows that the navigation method is simple and reliable, fully able to meet the navigation requirements of substation patrol robot.
    No preview · Article · Jun 2010
    0Comments 2Citations