This article investigates the trajectory tracking control of robotic manipulators subject to system uncertainties and external disturbances. To enhance control accuracy and robustness, an adaptive super-twisting sliding mode control (ASTSMC) strategy incorporating a radial basis function (RBF) neural network and an adaptive sliding mode disturbance observer (ASMDO) is proposed. Specifically, the RBF neural network is employed to approximate system uncertainties, while the adaptive sliding mode disturbance observer estimates and compensates for unknown disturbances in real time. The super-twisting algorithm is utilized to mitigate chattering in the control input. A Lyapunov-based stability analysis is conducted to rigorously prove the system’s stability and finite-time convergence. Finally, simulation results validate the effectiveness and feasibility of the proposed control scheme.