Section forming is an important process in the tunneling process. Traditional section trajectory only aims at the shortest trajectory and it will not change once determined, which restricts the development of tunneling robots. For this reason, this paper proposes a multi-objective optimization method for the cutting trajectory of the cantilever roadheader for common and complex structural sections. Firstly, taking efficiency and safety as the goal, a multi-objective optimization model of the cutting trajectory is established. Considering the actual cutting conditions, the decision variables, objective functions and constraints in the model are determined. Secondly, in order to further improve the convergence and distribution of the optimized solution, a multi-objective particle swarm optimization based on fitness distance to simplify knowledge base ( FDMOPSO) is proposed. Finally, the multi-objective optimization model of the cutting trajectory is solved based on the FDMOPSO algorithm. Simulation results show that the convergence and distribution of the algorithm are improved by about 90% and 40% , respectively. It also verified that the cutting trajectory solution set can be planned for complex structure roadway sections of different shapes and sizes. Based on efficiency, safety and cutting smoothness, the optimal trajectory can be finally determined. The optimized cutting trajectory not only improves the cutting efficiency, but also avoids dirt band trapping and increases the safety of cutting.