Abstract: This paper takes the xArm6 robotic arm as the research object and proposes a joint space trajectory planning method based on the time-optimal 3-5-3 segmented polynomial interpolation of the improved particle swarm algorithm. The proposed method improves the operation efficiency and stability of the six-axis robotic arm. It takes the optimal running time of the robotic arm as the objective, and under the constraints of speed, acceleration and variable acceleration, the interpolation time of each segment is optimized by the improved particle swarm algorithm which introduces adaptive inertia weights and probabilistic jump characteristics. Compared with the traditional particle swarm algorithm, the improved particle swarm algorithm reaches a faster iteration speed and is less likely to fall into local optimum. Our results of robotic arm motion simulation show the robotic arm operates smoothly, and the six joints experience not abrupt, but continuous changes in positions, velocities and acceleration, demonstrating the practicality and effectiveness of the method.