Online flexible operation of a car-like mobile vehicle with non-holonomic constraints in dynamic environment is still a very challenging problem because the surrounding situations are not qualified in static, knowledge is only partial and the execution is often associated with uncertainty. The difficulty lies in the setting of appropriate moving sub-targets in real-time to obtain a collision-free and low-cost path. In this paper, we present a new approach for the autonomous motion control of mobile vehicle in a narrow area with static and dynamic obstacles. It is based on the selection of sub-target points of vehicle's movement called ‘soft target’ which is a target set defined as all possible and reachable via-points in a navigation space. The soft target is acquired by online learning based on the final target and environment information. Each element of it has its membership value in [0, 1] denoting its evaluation degree. With the acquired soft target, soft decision is made like human's decision process by predictive fuzzy control (PFC) to achieve final target safely and economically. The simulation results show the effectiveness and flexibility of the proposed vehicle motion control method. © 2009 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.