In this work we propose a new adaptive bilateral control scheme of teleoperation system based on four channels structure. This scheme is organized on two control strategies, the first one consists on a force/Impedance control approach applied to the master robot, whereas the second one consists on a parallel force/position control approach applied to the N-degrees of freedom nonlinear slave robot. An online environment estimation based on forgetting factor recursive least squares method (FFRLS) is used to estimate the unknown stiffness characteristics of the environment and extract the noise generated from poor quality force sensors installed on end-effector terminal while a neural network (NN) compensator is applied to eliminate the effects of uncertainties in dynamic model of the slave robot. Simulation results using Labview show the effectiveness of the proposed scheme in force / position trajectories of both master and slave manipulators assuring system stability and achievable transparency performance under unknown position, time varying stiffness of environment in the presence of uncertainties in the model's robot as well as the noise generated by the force sensors.