Wall-Following Control of a Hexapod Robot Using a Data-Driven Fuzzy Controller Learned Through Differential Evolution

This paper proposes the use of evolutionary fuzzy control for a wall-following hexapod robot. The data-driven fuzzy controller (FC) is learned through an adaptive group-based differential evolution (AGDE) algorithm, which avoids the explicit usage of the robot mathematical model and time-consuming manual design effort. In the wall-following task, the inputs of the FC are measurements of three infrared distance sensors mounted on the hexapod robot. The FC controls the swing angle changes of the left- and right-middle legs of the hexapod robot for proper turning performance while simultaneously moving forward. To automate the design of the FC and to improve the performance of control, an AGDE algorithm is proposed. In the AGDE-designed FC, a cost function is defined to quantitatively evaluate the learning performance of an FC based on data generated online. In the AGDE, the solution vectors in a population are adaptively clustered into different groups based on their performances at each iteration. To improve optimization performance, the AGDE adaptively selects components from either the group-based mutant vector or a typical population-based mutant vector in the mutation operation. Simulated and experimental results are gathered to verify the effectiveness and efficiency of the data-driven AGDE-based learning approach.