Friendly interaction between robot and human is vital in the design of a human centered system. Among several interaction technologies, the intention reading of the user plays an important role for the human centered system. We focus on the aspect of intention reading in rehabilitation robots, and implement its capability for the wheelchair-based robotic arm system, called KARES (KAIST Rehabilitation Engineering Service System) II. An effective intention reading scheme is proposed on the basis of several soft computing techniques to handle uncertainty of the user's intention. Two application examples of intention reading in KARES II are discussed: one is visual servoing of the user's face, and the other is emergency stop of the robot by using EMG signals of the user's arm.