In this study, a fuzzy reinforcement learning control (FRLC) is proposed to achieve trajectory tracking of a differential drive mobile robot (DDMR). The proposed FRLC approach designs fuzzy membership functions to fuzzify the relative position and heading between the current position and a prescribed trajectory. Instead of fuzzy inference rules, the relationship between the fuzzy inputs and actuator voltage outputs is built using a reinforcement learning (RL) agent. Herein, the deep deterministic policy gradient (DDPG) methodology consisted of actor and critic neural networks is employed in the RL agent. Simulations are conducted with considering varying slip ratio disturbances, different initial positions, and two different trajectories in the testing environment. In the meantime, a comparison with the classical DDPG model is presented. The results show that the proposed FRLC is capable of successfully tracking different trajectories under varying slip ratio disturbances as well as having performance superiority to the classical DDPG model. Moreover, experimental results validate that the proposed FRLC is also applicable to real mobile robots.

Experiments with a nonlinear trajectory-tracking controller for marine unmanned surface vessels are reported. The tracking controller is designed using a nonlinear robust model-based sliding mode approach. The marine vehicles can track arbitrary desired trajectories that are defined in Cartesian coordinate as continuous functions of time. The planar dynamic model used for the controller design consists of 3 degrees of freedom (DOFs) of surge, sway, and yaw. The vessel only has two actuators, so the vessel is underactuated. Therefore, only two outputs, which are functions of the 3-DOF, can be controlled. The Cartesian position of a control point on the vessel is defined as the output. The orientation dynamics is not directly controlled. It has been previously shown that the orientation dynamics, as the internal dynamics of this underactuated system, is stable. The result of field experiments show the effectiveness of tracking control laws in the presence of parameter uncertainty and disturbance. The experiments were performed in a large outdoor pond using a small test boat. This paper reports the first theoretical development and experimental verification of the proposed model-based nonlinear trajectory-tracking controller.