Modular robot path planning using genetic algorithm based on gene pool

Authors:
Huaming Zhong;Zhenhua Li;Hao Zhang;Chao Yu;Ni Li
Affiliations:
School of Computer Science, China University of Geosciences, Wuhan, China;School of Computer Science, China University of Geosciences, Wuhan, China and State Key Laboratory of Geological Processes and Mineral Resources, China University of Geosciences, Wuhan, China;School of Computer Science, China University of Geosciences, Wuhan, China;School of Computer Science, China University of Geosciences, Wuhan, China;School of Computer Science, China University of Geosciences, Wuhan, China
Venue:
ISICA'10 Proceedings of the 5th international conference on Advances in computation and intelligence
Year:
2010

Citing 4
Cited 0

Robotics: modular robots

IEEE Spectrum - Modular robots change shape to conquer tasks and tough terrain
Modular Reconfigurable Robots in Space Applications

Autonomous Robots
Autonomous Self-Assembly in Swarm-Bots

IEEE Transactions on Robotics
Evolved and Designed Self-Reproducing Modular Robotics

IEEE Transactions on Robotics

Quantified Score

Hi-index	0.00

Visualization

Abstract

As a new generation of robotics, a modular robot is flexible enough to achieve self-replication by attaching a new modular, or perform self-assembly by transferring into different shapes. However, the path planning for modular robots, the fundamental function is seldom studied until now. In this paper, we improve the path schedule method of Molecubes, by designing a gene pool, to speed the convergence and avoid the uncertain of the original genetic algorithm (GA). Experiments show that the gene-pool based GA outperforms the old one in both success rate and speed in planning the long path.