This dissertation proposes an improved artificial bee colony (lABC) algorithm for designing a compensatory fuzzy logic controller (CLFC) in order to achieve an actual mobile robot wall-following task. During the wall-following task, the CFLC inputs measure the distance between the ultrasonic sensors and the wall, and the outputs of the CFLC are the robot's left-wheel and right-wheel speeds. A cost function is defined to evaluate the performance of the CFLC in the wall-following task. The cost function includes three control factors (CF) which are defined as follows: maintaining a user-defined robot-wall distance, avoiding robot-wall collision, and ensuring that the robot can successfully negotiate the venue. The original artificial bee colony algorithm (ABC) simulates the intelligent foraging behavior of honey-bee swarms, which are good at exploration but poor at exploitation. An improved ABC algorithm, the IABC algorithm, is proposed that adopts the mutation strategies of differential evolution to balance exploration and exploitation. The IABC algorithm applies a new reward-based roulette wheel selection where an obtained a better solution by gains a reward during the learning stage. To demonstrate the performance of the IABC designed CFLC, the method was compared with other population-based algorithms with respect to the efficiency of the wall-following task.