Vehicle suspension system has a wide range of applications in the automotive industry. This paper presents a simple and robust adaptive neuro-fuzzy inference system (ANFIS) for vibration control of a vehicle active suspension system (VASS). Performance requirements such as ride comfort, suspension stroke and good road holding are considered simultaneously in the vibration control issue. In order to attain desired training data for ANFIS, the optimal PID controller is designed in which particle swarm optimization (PSO) method is employed to adjust the PID parameters. Simulation results demonstrate the effectiveness and robustness of the proposed ANFIS-based vibration control strategy.