TY - JOUR
T1 - Path planning for autonomous mobile robot navigation with ant colony optimization and fuzzy cost function evaluation
AU - Garcia, M. A.Porta
AU - Montiel, Oscar
AU - Castillo, Oscar
AU - Sepúlveda, Roberto
AU - Melin, Patricia
N1 - Funding Information:
ACKNOWLEDGEMENTS This research was supported by the Department of Electrical and Electronic Engineering, Faculty of Engineering, American International University-Bangladesh (AIUB), Dhaka-1229, Bangladesh.
PY - 2009/6
Y1 - 2009/6
N2 - In the Motion Planning research field, heuristic methods have demonstrated to outperform classical approaches gaining popularity in the last 35 years. Several ideas have been proposed to overcome the complex nature of this NP-Complete problem. Ant Colony Optimization algorithms are heuristic methods that have been successfully used to deal with this kind of problems. This paper presents a novel proposal to solve the problem of path planning for mobile robots based on Simple Ant Colony Optimization Meta-Heuristic (SACO-MH). The new method was named SACOdm, where d stands for distance and m for memory. In SACOdm, the decision making process is influenced by the existing distance between the source and target nodes; moreover the ants can remember the visited nodes. The new added features give a speed up around 10 in many cases. The selection of the optimal path relies in the criterion of a Fuzzy Inference System, which is adjusted using a Simple Tuning Algorithm. The path planner application has two operating modes, one is for virtual environments, and the second one works with a real mobile robot using wireless communication. Both operating modes are global planners for plain terrain and support static and dynamic obstacle avoidance.
AB - In the Motion Planning research field, heuristic methods have demonstrated to outperform classical approaches gaining popularity in the last 35 years. Several ideas have been proposed to overcome the complex nature of this NP-Complete problem. Ant Colony Optimization algorithms are heuristic methods that have been successfully used to deal with this kind of problems. This paper presents a novel proposal to solve the problem of path planning for mobile robots based on Simple Ant Colony Optimization Meta-Heuristic (SACO-MH). The new method was named SACOdm, where d stands for distance and m for memory. In SACOdm, the decision making process is influenced by the existing distance between the source and target nodes; moreover the ants can remember the visited nodes. The new added features give a speed up around 10 in many cases. The selection of the optimal path relies in the criterion of a Fuzzy Inference System, which is adjusted using a Simple Tuning Algorithm. The path planner application has two operating modes, one is for virtual environments, and the second one works with a real mobile robot using wireless communication. Both operating modes are global planners for plain terrain and support static and dynamic obstacle avoidance.
KW - Ant colony optimization
KW - Autonomous mobile robot navigation
KW - Fuzzy Logic
KW - Path planning
KW - Simple tuning algorithm
UR - http://www.scopus.com/inward/record.url?scp=67349090384&partnerID=8YFLogxK
U2 - 10.1016/j.asoc.2009.02.014
DO - 10.1016/j.asoc.2009.02.014
M3 - Artículo
SN - 1568-4946
VL - 9
SP - 1102
EP - 1110
JO - Applied Soft Computing Journal
JF - Applied Soft Computing Journal
IS - 3
ER -