• Le Cheng^a, b, 
• Lixin Han^a, , , 
• Xiaoqin Zeng^a, 
• Yuetang Bian^c, 
• Hong Yan^d, e

• ^a College of Computer and Information, Hohai University, Nanjing 210098, China
• ^b Department of Computer Science and Engineering, Huaian College of Information Technology, China
• ^c School of Business, Nanjing Normal University, Nanjing 210023, China
• ^d School of Electrical and Information Engineering, University of Sydney, NSW 2006, Australia
• ^e Department of Electronic Engineering, City University of Hong Kong, Tat Chee Avenue, Kowloon, Hong Kong, China

Abstract

Based on the Cockroach Swarm Optimization (CSO) algorithm, a new Cockroach Colony Optimization (CCO) algorithm is presented and applied to the Robot Path Planning (RPP) problem in this paper. In the CCO algorithm, an improved grid map is used for environment modeling, and 16-geometry and 8-geometry are introduced, respectively, in food division and cockroach search operation. Moreover, the CCO algorithm adopts a non-probabilistic search strategy, which avoids a lot of invalid searches. Furthermore, by introducing a novel rotation scheme in the above CCO algorithm, an Adaptive Cockroach Colony Optimization (ACCO) algorithm is presented for the 2-D Rod-Like Robot Path Planning (RLRPP) problem. The simulation results show that the CCO algorithm can plan an optimal or approximately optimal collision-free path with linear time complexities. With the ACCO algorithm, the robot can accomplish intelligent and adaptive rotations to avoid obstacles and pass through narrow passages along the better path.