This work presents an adaptive fuzzy cerebellar model articulation controller (AFCMAC) for solving the tracking control problem for an omni-directional mobile robot. First, fuzzy logic and CMAC are combined, coupled with a triangular basis function that is embedded in the hypercube receptive-field space to yield non-constant differentiable basis functions, which simplify the complex structure and reduce the number of input space dimensions of CMAC. Both adaptive and control laws are developed to tune all of the control parameters online, accommodating uncertainty in tracking control for an omni-directional mobile robot. Hardware agencies and drive circuits are developed. This proposed AFCMAC is implemented in a highperformance field-programmable gate array (FPGA) chip using a hardware/software co-design method and the Qsys design concept with a reusable user IP (Intellectual Property) core library. An omni-directional mobile robot is thus produced. Finally, the trajectory tracking controllability of the robot along both straight and elliptical paths is simulated to evaluate the effectiveness of the proposed AFCMAC and establish the feasibility and performance of uncertain tracking control.