Multi-Objective Continuous-Ant-Colony-Optimized FC for Robot Wall-Following Control

This paper proposes a multi-objective, rule-coded, advanced, continuous-ant-colony optimization (MO-RACACO) algorithm for fuzzy controller (FC) design and its application to multi-objective, wall-following control for a mobile robot. In the MO-RACACO-based FC design approach, the number of rules and all free parameters in each rule are optimized using the MO-RACACO algorithm. This is a complex multi-objective optimization problem that considers both the optimization of discrete variables (number of rules) and continuous variables (rule parameters). To address this problem, the MO-RACACO uses a rule-coded individual (solution) representation and a rule-based mutation operation to find Pareto-optimal solutions with different numbers of rules. New solutions in the MO-RACACO are generated using a pheromone-level-based adaptive elite-tournament path selection strategy followed by a Gaussian sampling operation. The MO-RACACO-based FC design approach is applied to a multi-objective, wall-following problem for a mobile robot. Three objectives are defined so that the robot is collision-free, maintains a constant distance from the wall, and moves smoothly at a high speed. This automatic design approach avoids the time-consuming manual design of fuzzy rules and the exhaustive collection of input-output training pairs. The performance of the MO-RACACO-based control is verified through comparisons with various multi-objective population-based optimization algorithms (MOPOAs) in multi-objective FC optimization problems. This study also includes experiments that demonstrate robot wall-following control using an actual mobile robot.