Planning Optimal Trajectories for Mobile Robots Using an Evolutionary Method with Fuzzy Components

• Published in: Advances in Natural Computation pp. 703 - 712
• Main Authors: Aydin, Serkan, Temeltas, Hakan
• Format: Book Chapter Conference Proceeding
• Language: English
• Published: Berlin, Heidelberg Springer Berlin Heidelberg 2005; Springer
• Series: Lecture Notes in Computer Science
• Subjects: Applied sciences; Artificial intelligence; Computer science; control theory; systems; Differential Evolution; Exact sciences and technology; Fuzzy Inference System; Mobile Robot; Motion Planning; Optimal Trajectory; Fuzzy logic; Minimum time; Moving robot; Line segment; Evolutionary algorithm; Optimal trajectory; Occupation time; Optimal planning; Differential method; Mobile computing
• ISBN: 9783540283201; 354028320X; 3540283234; 9783540283232
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/11539902_87

This study describes a generation of globally time optimal trajectories for a mobile robot in predefined environment. The primary task in the study is to apply Differential Evolution (DE) method for definition of globally time-optimal trajectories under environmental and dynamical constraints. The planned trajectories are composed of line segments and curve segments. The structures of the curve segments are determined by using only two parameters such as a turn angle θ and a translation velocity on the curve vt_start. All possible curve segments in parameters range θ ∈ (0, π]°, vt_start [0,40] inch and at_turn ∈ [-at_max, at_max] inch/sec2 form a curve segments set. Then DE, is used to find time optimal trajectory from this set. Experimental results are given and the results are shown successfully.