Aiming at the problem of time optimal trajectory planning of six-degree-of-freedom manipulator,a 4-3-4 mixed polynomial interpolation trajectory planning algorithm based on improved particle swarm optimization was proposed.Adaptive inertia weight was adopted in the algorithm,it could adopt corresponding weights according to each stage of the search process,which was helpful to jump out of the local optimal trap and keep the diversity of particle swarm.Replacing the fixed learning factors in the traditional particle swarm optimization with nonlinear learning factors could effectively improve the convergence speed and solution accuracy of the algorithm.The simulation results in MATLAB show that the convergence speed of the improved particle swarm optimization algorithm is increased by 46%,the optimization accuracy is increased by 38%,and the trajectory planning time of the manipulator is shortened by about 36%,which fully proves the reliability and superiority of the trajectory planning algorithm.