The paper proposes a differential flatness theory-based adaptive fuzzy controller for spark-ignited (SI) engines. The system's dynamic model is considered to be completely unknown. By applying a change of variables (diffeomorphism) that is based on differential flatness theory the engine's dynamic model is written in the linear canonical (Brunovsky) form. After transforming the SI-engine model into the canonical form, the resulting control inputs are shown to contain nonlinear elements which depend on the system's parameters. These nonlinear terms are approximated with the use of neuro-fuzzy networks while a suitable learning law can be defined for the aforementioned neuro-fuzzy approximators so as to preserve the closed-loop system stability. Moreover, using Lyapunov stability analysis it is shown that the adaptive fuzzy control scheme succeeds H ∞ tracking performance, which means that the influence of the modeling errors and the external disturbances on the tracking error is attenuated to an arbitrary desirable level. The efficiency of the proposed adaptive fuzzy control scheme is checked through simulation experiments.