Home /Research /Robot path planning for maze navigation
OTHER

Robot path planning for maze navigation

Dimitris C. Dracopoulos

Year
2002
Citations
22

Abstract

This paper presents the application of multilayer perceptrons to the robot path planning problem, and in particular to the task of maze navigation. Previous published results implied that the training of feedforward multilayered networks failed, because of the nonsmoothness of data. Here the same maze problem is revisited.

Keywords

Motion planningComputer scienceTask (project management)RobotPath (computing)Feed forwardArtificial intelligenceSimulationEngineeringControl engineering

Related papers

Browse all OTHER papers