Position tracking and control using bioelectric signals are emerging as promising techniques. Surface electromyographic (EMG) signals are being researched for tracking human movements, direct proportional control of teleoperators, and object manipulation in VR environments. This study investigates the use of surface EMG to track elbow joint angle during flexion-extension of the arm applied to control of a virtual environment or an anthropomorphic telemanipulator. An intelligent system based on neural networks and fuzzy logic has been developed to use the processed surface EMG signal and predict the joint angle. The intelligent system has been tested on normal subjects performing flexion-extension of the arm of various angles and at several speeds. The joint angles predicted by the intelligent system were input to a computer-simulated model of an elbow manipulator. Preliminary results show the average root mean squared (RMS) error between the actual elbow joint angle measured with a goniometer and the joint angle reproduced by the robot model to be less than 20%. The technique of using EMG as an interface for tracking and direct biocontrol has great potential in VR and telemanipulation.