A neural network-based approach for variable admittance control in human–robot cooperation: online adjustment of the virtual inertia

Principle of Neural Network and Its Main Types: Review

“…The cost function to be minimized is therefore, the total instantaneous error energy ( ). The on-line training of the MLFFNN was used for tuning the control parameters as presented in references [6,7,[36][37][38].…”

“…The trained MLFFNN presented in these cases highly desired performance. This work was extended and widely presented in [7]. In [7], the generalization ability was presented using three different cases than the ones used for the training process, as follows:  Different lengths of movements were tested.…”

“…The RNN distinguishes itself from a feedforward neural network in that it has at least one feedback loop, as shown in Fig. (7).…”

“…The NNs are widely used by many researchers in many different applications such as robotics [2][3][4][5][6][7], speech recognition [8,9], human face recognition [10,11], medical applications [12][13][14], manufacturing [15,16], and economics [17,18].…”

“…In this admittance controller, the variable damping was adjusted. In [7], the virtual inertia of the robot admittance controller based also on MLFFNN.…”