Online Bilateral Predictive Control for Time-Delayed Teleoperation of Snake-like Robots

Controlling the teleoperation of snake-like robots is challenging due to complex nonlinear dynamics and communication delays. This research proposes an online bilateral predictive control architecture to address these issues. This control structure is established by predicting environment force and the user’s future motion. The former uses a model-mediated approach by creating a virtual environment on the master side and the latter adopts an artificial neural network (ANN) for online operator’s motion prediction. The slave controller utilizes transmitted data from ANN to generate required backbone lengths, which are then transformed into the slave's local bending and torsional degrees of freedom through the inverse kinematics of the robot. Motion prediction is examined in two scenarios: when the ANN predicts the trained motions, and when it predicts a different motion. Simulation studies demonstrate that the proposed online bilateral predictive teleoperation structure successfully achieves real-time position synchronization and force feedback, by effectively bypassing communication delays.