Adaptive online prediction of operator position in teleoperation with unknown time-varying delay: simulation and experiments

One of the most important problems in teleoperation systems is time delay and packet loss in the communication channel, which can affect transparency and stability. One way to overcome the time delay effects in a teleoperation system is to predict the master-side motion. In this way, when data is received in the slave side, it will be considered as the current position of the master robot and, thus, complete transparency could be achieved. The majority of the previous works regarding operator position prediction have considered known and constant time delay in the system; however, in the real applications, time delay is unknown and variable. In this paper, an adaptive online prediction approach based on artificial neural network (NN) is proposed. The time delay of the communication channel is estimated using an observer based on the dynamics of the master and slave sides. Then an artificial NN predicts the master-side motion based on the current available data of the master robot and the variable time delay estimated by the observer. This adaptive prediction approach is utilized in simulations and experiments on Phantom Omni haptic devices. The simulation results indicate the feasibility of this approach. It is revealed that this approach can predict an alternative human's hand motion in a teleoperation system with unknown and variable time delay. Finally, the simulation results would be supported by experimental results.

Automated summary

An adaptive online prediction approach based on neural network is proposed to overcome time delay in teleoperation systems, with simulation and experimental results supporting its feasibility in predicting human hand motion effectively.