TY - JOUR
T1 - FPGA implementation of improved ant colony optimization algorithm based on pheromone diffusion mechanism for path planning
AU - Hsu, Chen Chien
AU - Wang, Wei Yen
AU - Chien, Yi Hsing
AU - Hou, Ru Yu
N1 - Funding Information:
This research is supported by the “Aim for the Top University Project” of National Taiwan Normal University (NTNU), sponsored by the Ministry of Education, Taiwan, and Ministry of Science and Technology, Taiwan, under Grants no. MOST 106- 2221-E-003-007-MY2, MOST 106-2221-E-003-008-MY2, MOST 107-2634-F-003-002, and MOST 107-2634-F-003-001.
Publisher Copyright:
© National Taiwan Ocean University. All rights reserved.
PY - 2018
Y1 - 2018
N2 - An improved ant colony optimization (ACO) algorithm is proposed in this paper for improving the accuracy of path planning. The main idea of this paper is to avoid local minima by continuously tuning a setting parameter and the establishment of novel mechanisms by means of partial pheromone updating and opposite pheromone updating. As a result, the global search of the proposed ACO algorithm can be significantly enhanced to derive an optimal path compared to the conventional ACO algorithm. The simulation results of the proposed approach perform better in terms of the short distance, mean distance, and success rate towards optimal paths. To further reduce the computation time, the proposed ACO algorithm for path planning is realized on a FPGA chip to verify its practicalities. Experimental results indicate that the efficiency of the path planning is considerably improved by the hardware design for embedded applications.
AB - An improved ant colony optimization (ACO) algorithm is proposed in this paper for improving the accuracy of path planning. The main idea of this paper is to avoid local minima by continuously tuning a setting parameter and the establishment of novel mechanisms by means of partial pheromone updating and opposite pheromone updating. As a result, the global search of the proposed ACO algorithm can be significantly enhanced to derive an optimal path compared to the conventional ACO algorithm. The simulation results of the proposed approach perform better in terms of the short distance, mean distance, and success rate towards optimal paths. To further reduce the computation time, the proposed ACO algorithm for path planning is realized on a FPGA chip to verify its practicalities. Experimental results indicate that the efficiency of the path planning is considerably improved by the hardware design for embedded applications.
KW - Ant colony optimization (ACO)
KW - Field-programmable gate array (FPGA)
KW - Global path planning
KW - Pheromone diffusion mechanism
UR - http://www.scopus.com/inward/record.url?scp=85048938225&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85048938225&partnerID=8YFLogxK
U2 - 10.6119/JMST.2018.04_(2).0004
DO - 10.6119/JMST.2018.04_(2).0004
M3 - Article
AN - SCOPUS:85048938225
SN - 1023-2796
VL - 26
SP - 170
EP - 179
JO - Journal of Marine Science and Technology (Taiwan)
JF - Journal of Marine Science and Technology (Taiwan)
IS - 2
ER -