This paper proposes a method for controlling posture of a robot manipulator by fuzzy voice commands. Humanfriendly robotic system should be able to understand the fuzzy linguistic information based on the user's guidance and the environmental conditions. The contextual meaning of fuzzy linguistic information depends on the conditions of the environment. Therefore, the user's feedback is evaluated to understand the fuzzy linguistic information related to the posture movements. The primitive posture movements are evaluated by the behavior evaluation network (BEN). Feedback evaluation system (FES) is introduced to evaluate the user's feedback to correct the robot perception by adapting the BEN. The capability of evaluating fuzzy linguistic information based on the current context is enhanced. A selected set of posture movements are used to illustrate the system by using a PA-10 robot manipulator.