Abstract: The trajectory control of cantilever tunneling machine can be regarded as an independent optimization problem in the solution space. However, the underground working environment is complex and ever-changing, and the tunneling machine may encounter various uncertain factors during its movement. It is easy to fall into local optimal solutions when solving complex optimization problems, resulting in poor optimal solution results and affecting the tracking and control of the tunneling machine trajectory. In order to improve the accuracy and stability of trajectory tracking control, ensure excavation efficiency and operational safety, this study proposes a cantilever tunneling machine trajectory tracking control method based on an improved particle swarm optimization algorithm. This study obtained the deviation between the actual pose and the expected pose by tracking the current travel state of the cantilever tunneling machine. On this basis, particle swarm optimization algorithm is used to adjust the movement speed and steering angular velocity of the excavator body, to compensate for the pose deviation during the excavator’s movement process, and to achieve trajectory tracking control of the excavator through pose deviation compensation. In this process, to avoid the particle swarm optimization algorithm getting stuck in local optima, a niche evolution strategy is used to optimize the fitness of particles. The particles are divided into different subpopulations （niches）, and the algorithm converges to the optimal solution faster by narrowing the search range, thereby improving the effectiveness of trajectory tracking control. Verify the control effect of this method through simulation experiments, it is found that after applying this method, the directional angle values and corresponding expected angle values of the cantilever tunneling machine at different positions are basically consistent, and the actual turning angular velocity values are basically the same as the expected values. The movement trajectory of the cantilever tunneling machine on the X-axis and Y-axis matches the expected trajectory, indicating that this method has a good control effect on the directional angle and turning angular velocity of the tunneling machine, and the performance of trajectory tracking control is high.