During tower crane operation, the load induces oscillations, and the system displays traits like underdrive, nonlinearity, and strong coupling. Controlling the positioning and eliminating oscillations is challenging. Most existing control methods either neglect system's friction term or employ a static formula for its calculation. However, the friction term is highly influenced by the working environment in practical engineering applications, leading to a reduction in control effectiveness. To solve these issues, an adaptive fuzzy sliding mode controller based on fuzzy compensation was proposed. Firstly, by adjusting the original system dynamics model, a new model was formulated to address the challenge of designing a control law for the underdriven system. Subsequently, the friction term of the system was approximated using fuzzy approximation, mitigating the impact of the uncertain operating environment on this term. Secondly, the controller was designed on this basis in combination with sliding mode control theory, and the system was proved to be asymptotically stable by rigorous stability analysis. Finally, the proposed method's effectiveness was validated through simulation and experimental results.