There is an increasing demand for human body motion data. Motion capture and physical animation have been used to generate such data. It is, however, apparent that such methods cannot automatically generate arbitrary human body motions. A human body is a redundant multi-linked body controlled by a number of muscles. For this reason, the muscles must work appropriately and cooperatively for controlling the whole body. It is well-known that the human body control system is composed of two parts: The open-loop feed-forward control system and the closed-loop feedback control system. Many researchers have investigated the characteristics of the latter by analyzing the response of a human body to various external perturbations. However, for the former, very few studies have been done. This paper proposes an open-loop feed-forward model of the lower extremities which includes postural control for accurate animation of a human body. Assumptions are made here that the feed-forward controller minimizes a certain objective value while keeping the balance of the body stable. The actual human motion data obtained using a motion capturing technique is compared with the trajectory calculated using our method for verification. The best criteria which is based on muscle dynamics is proposed. Using our method, dynamically correct human animation can be created by merely specifying a few key postures.