Author(s): Ju MY, Wang SE, Guo JH
Abstract Share this page
Abstract A hybrid evolutionary algorithm using scalable encoding method for path planning is proposed in this paper. The scalable representation is based on binary tree structure encoding. To solve the problem of hybrid genetic algorithm and particle swarm optimization, the "dummy node" is added into the binary trees to deal with the different lengths of representations. The experimental results show that the proposed hybrid method demonstrates using fewer turning points than traditional evolutionary algorithms to generate shorter collision-free paths for mobile robot navigation.
This article was published in ScientificWorldJournal
and referenced in Advances in Robotics & Automation