Universal Method for Enhancing Dynamics in Neural Networks via Memristor and Application in IoT-Based Robot Navigation

Special tasks in complex and extreme environments require mobile robots to possess the good capabilities of navigation and securing map data. Mobile robots driven by the chaotic properties of memristive neural networks (MNN) can offer intriguing insights. However, the expandable MNN capable of providing multiple reliable options for diverse application scenarios has yet to be thoroughly explored. Hence, this article proposes a new universal method to enhance the dynamics in neural networks for generating numerous neural networks with rich dynamics, providing multiple options for the navigation and security of IoT-based robots. The enhanced dynamics in this method benefit from expanding the number of memristive electromagnetic radiation, the number of neurons, and their integration. Many different memristive central cyclic neural network (MCCNN) are successfully derived from the newly constructed central cyclic neural network as an example. Various dynamics of memristive central cyclic neural networks (MCCNN) are numerically investigated, including bifurcation, homogeneous and heterogeneous multistability, and large-scale amplitude control. The analog circuit and digital hardware platform are built to verify the physical existence and feasibility of MCCNN. Finally, MCCNN is applied to drive the IoT-based mobile robot. To evaluate the robot's area coverage, obstacle avoidance performance, several experiments are carried out, which validate the robot's superiority.