DocumentCode
617902
Title
Robot path planning in an environment with many terrains based on interval multi-objective PSO
Author
Na Geng ; Dunwei Gong ; Yong Zhang
Author_Institution
Sch. of Inf. & Electr. Eng., China Univ. of Min. & Technol., Xuzhou, China
fYear
2013
fDate
20-23 June 2013
Firstpage
813
Lastpage
820
Abstract
In order to solve the problem of path planning in an environment with many terrains, we propose a method based on interval multi-objective Particle Swarm Optimization (PSO). First, the environment is modeled by the line partition method, and then, according to the distribution of the polygonal lines which form the robot path and taking the velocity´s disturbance into consideration, robot´s passing time is formulated as an interval by combining Local Optimal Criterion (LOC), and the path´s danger degree is estimated through the area ratio between the robot path and the danger source. In addition, the path length is also calculated as an optimization objective. As a result, the robot path planning problem is modeled as an optimization problem with three objectives. Finally, the interval multiobjective PSO is employed to solve the problem above. Simulation and experimental results verify the effectiveness of the proposed method.
Keywords
mobile robots; particle swarm optimisation; path planning; LOC; interval multiobjective PSO; line partition method; local optimal criterion; particle swarm optimization; path danger degree; polygonal line distribution; robot passing time; robot path planning problem; terrain; velocity disturbance; Educational institutions; Evolutionary computation; Mathematical model; Optimization; Path planning; Robot kinematics; interval multi-objective optimization; many terrains; mobile robot; particle swarm optimization; path planning;
fLanguage
English
Publisher
ieee
Conference_Titel
Evolutionary Computation (CEC), 2013 IEEE Congress on
Conference_Location
Cancun
Print_ISBN
978-1-4799-0453-2
Electronic_ISBN
978-1-4799-0452-5
Type
conf
DOI
10.1109/CEC.2013.6557652
Filename
6557652
Link To Document