Human interactive robots continue to improve human quality of life with their diverse applications. Their field includes, but is not limited to, haptic devices, force feedback tele-manipulation, surgical co-manipulation, medical rehabilitation, and various multi-degree of freedom robotic devices where the human operator and robot are often required to simultaneously execute tasks and collaborate with a specific share of forces/energy. More than tuning mechanical design, the robot control enhancement with a force sensor, is the key for increasing transparency (i.e the capacity for a robot to follow human movements without any human-perceptible resistive forces). With ail ideal robot control, the interaction between robot and human Would be extremely natural and fluid that the comanipulation of tasks Would seem to be achieved with a transparent aid from the robot. For Such, the classical force feedback control in certain cases still seems insufficient as is often limited by various factors (noise, bandwidth limitation, stability, sensor cost..etc). Our experiments are focused on evaluating the performance increase in terms of transparency of controller by using human motion predictions. We evaluate several ways to use predictive informations in the control to overcome present transparency limitations during a simple comanipulation pointing task.