This paper mainly studies the longitudinal speed tracking problem of driverless heavy-duty trucks based on data-driven methods. A data-driven adaptive optimal control algorithm with control input saturation constraints is proposed in this paper to solve the problems of control input saturation and difficulty in establishing an accurate model in driverless heavy-duty truck systems. First, control constraints are added to the control input saturation problem of driverless heavy-duty trucks. Then, the dynamic linearization technology is used to model the nonlinear system of driverless heavy-duty trucks. After that, an appropriate index function is selected and the Newton-type optimization method is used to obtain the optimal controller. The method proposed in this paper only uses a small amount of input and output data and does not need to establish an accurate mathematical model. The simulation results show that compared with the PID algorithm, the proposed algorithm has advantages in speed tracking when applied to driverless heavy-duty truck systems.