Abstract: A path planning and optimization method based on particle swarm optimization (PSO) is proposed for trajectory planning of unstructured, uncertain and complex unknown environment in coal mine. The establishment of dynamic model of robot, the key point control of robot kinematics constraints into three spline interpolation curve constraint nonlinear constrained optimization problem, using three order polynomial interpolation curve by combining particle swarm algorithm and penalty function method, using adaptive interpolation function to control convergence speed, get a satisfying real time optimal trajectory the requirements of working condition. The results show that this method has effectively solved the optimization of robot time optimal trajectory in the complex environment of coal mine.