Simulative Experiments, Verifications, and Comparisons of Discrete Zhang Neuronet Algorithms for SCR (Soft Continuum Robot) Position-Orientation (PO) Tracking Control Under Constant, Linear, or Random Noise

Soft continuum robot (SCR), commonly known as soft robot, holds promise for a myriad of future applications due to their inherent flexibility and adaptability. The realm of position-orientation (PO) tracking control for the SCR is a growing body of research. Besides, the majority of research efforts in PO predominantly yield continuous models and discrete algorithms. Discrete algorithms exhibit compatibility with digital computers and microchips, making them the preferred choice for practical implementation usually under noise conditions. Consequently, the development of discrete algorithms for PO tracking control in SCR is of significant importance. In this paper, we use Zhang neuronet (ZN) method to develop discrete ZN (DZN) algorithms for the PO tracking control of SCR under different noise conditions. On the basis of previous research, three DZN algorithms of three-section SCR are presented in this paper. The three DZN algorithms illustrate exceptional adaptability in noisy environments, particularly in conditions with constant noise. We conduct a number of simulative experiments to provide detailed evidence that underscores the effectiveness and robustness of these DZN algorithms under three noise conditions, including constant, linear, and random noise situations. These experiments serve to verify the theoretical foundations of our algorithms and also provide a practical comparison with traditional discrete algorithms. The results from these experiments evidently illustrate that the DZN algorithms developed in this paper outperform three traditional discrete algorithms in handling the challenges posed by various noise environments.