Abstract: he optimum motion planning in joint space(OMPJS),which consists of two subproblems atclose hand, optimum path planning and optimum trajectory planning, was considered wholly instead of indi-vidually.A new method based on genetic algorithm for optimal motion planning problem is proposed,whichis more general.flexible and effective, This approach incorporates kinematics,dynamics and control con-straints of robot manipulator. The minimum time trajectory is paralneterized by splines. The simulation resuIts for a two degrees of freedom robot are presented.The simulation is based on genetic algorithm class li-brary WGAClass 1.0 developed by us with Borland C+ + 3.1.