Investigating the Influence of Counterflow Regions on the Hydrodynamic Performance of Biomimetic Robotic Fish.

Biomimetic robotic fish are a novel approach to studying quiet, highly agile, and efficient underwater propulsion systems, attracting significant interest from experts in robotics and engineering. These versatile robots showcase their ability to operate effectively in various water conditions. Nevertheless, the comprehension of the swimming mechanics and the evolution of the flow field of flexible robots in counterflow regions is still unknown. This paper presents a framework for the self-propulsion of robotic fish that imitates biological characteristics. The method utilizes computational fluid dynamics to analyze the hydrodynamic efficiency of the organisms at different frequencies of tail movement, under both still and opposing flow circumstances. Moreover, this study clarifies the mechanisms that explain how changes in the aquatic environment affect the speed and efficiency of propulsion. It also examines the most effective swimming tactics for places with counterflow. The results suggest that the propulsion effectiveness of robotic fish in counterflow locations does not consistently correspond to various tail-beat frequencies. By utilizing vorticity maps, a comparative analysis can identify situations when counterflow zones improve the efficiency of propulsion.

A Novel Obstacle Traversal Method for Multiple Robotic Fish Based on Cross-Modal Variational Autoencoders and Imitation Learning.

Precision control of multiple robotic fish visual navigation in complex underwater environments has long been a challenging issue in the field of underwater robotics. To address this problem, this paper proposes a multi-robot fish obstacle traversal technique based on the combination of cross-modal variational autoencoder (CM-VAE) and imitation learning. Firstly, the overall framework of the robotic fish control system is introduced, where the first-person view of the robotic fish is encoded into a low-dimensional latent space using CM-VAE, and then different latent features in the space are mapped to the velocity commands of the robotic fish through imitation learning. Finally, to validate the effectiveness of the proposed method, experiments are conducted on linear, S-shaped, and circular gate frame trajectories with both single and multiple robotic fish. Analysis reveals that the visual navigation method proposed in this paper can stably traverse various types of gate frame trajectories. Compared to end-to-end learning and purely unsupervised image reconstruction, the proposed control strategy demonstrates superior performance, offering a new solution for the intelligent navigation of robotic fish in complex environments.