17 January 2025 in IEEE Transactions on Industrial Electronics
Adaptive and efficient cooperative control is a crucial capability for multirobotic fish systems, as it can substantially enhance their performance in complex underwater tasks. The pursuit and evasion dynamics in such topics have gained significant attention from the scientific community. In this article, we present a novel adaptive algorithm tailored specifically for cooperative pursuit among multirobotic fish systems. Benefiting from the integration of attraction mechanisms and reinforcement learning techniques, the proposed method empowers the robotic fish to make adaptive decisions based on local observations and environmental cues. Meanwhile, a state transition environment has been customized to the unique dynamics of robotic fish, equipping the cooperative pursuit strategy to fulfill practical application requirements and facilitate adaptation across diverse platforms. Besides, based on the curriculum learning approach, a decentralized pursuit policy is also formulated and implemented within the developed robotic fish system. Simulations and real-world experiments have validated the efficiency and adaptability of this cooperative pursuit strategy. This research offers valuable insights and contributions to the exploration of cooperative control in multirobotic fish systems, addressing the critical challenge of achieving adaptive and efficient coordination in complex underwater environments.
21 July 2025 in IEEE Transactions on Automation Science and Engineering
Directly learning the swimming behaviors of real fish can significantly enhance the swimming performance of bionic robotic fish. This paper presents a novel transfer learning method based on a dynamic trajectory control approach for the robotic fish to learn swimming skills from real fish. First, we develop a fish motion capture system and a crucial motion extraction approach to realize precise decomposition of fish motions and collect abundant meaningful features from a snakehead fish as pre-training data. Next, we construct a two-stage transfer learning method based on Deep Deterministic Policy Gradient (DDPG), including an offline and an online stage. Specifically, in the offline stage, the obtained pre-training data is processed for experience learning within a DDPG-based network, whereas in the online stage, a dynamic trajectory tracking method is utilized to refine the robotic fish’s motions in real time based on the learned strategies. Experimental results on a self-developed four-joint robotic fish show that the proposed method effectively extracts and transfers biological motion features into the motion control of the robotic fish. Compared to the conventional CPG method, the proposed approach exhibits stronger acceleration capabilities and more efficient swimming, resulting in enhanced maneuverability of the robotic fish. Overall, this approach provides a technical foundation for bionic robotics to learn from nature.
24 September 2025 in IEEE Transactions on Industrial Electronics
The ability to execute rapid 3-D turning maneuvers is essential for robotic fish to evade threats and perform complex underwater tasks. This article proposes a 3-D fast-start posture control method inspired by the hunting maneuvers of the pike. Initially, we develop a four-joint robotic fish equipped with a gravity-center adjustment mechanism and a flexible tail. Building on this design, we establish the dynamic and hydrodynamic models of the robotic fish, offering a reliable simulation environment for validating the proposed method. Subsequently, taking into account the pitch moment generated by the tail fin during fast-start maneuvers, we introduce a sliding-block position control model based on model predictive path integral (MPPI) control. A novel slider-position compensation approach is further proposed to address gravity-center instability observed in physical experiments. Finally, simulation and underwater experimental results demonstrate that the proposed method effectively predicts pitch disturbances caused by tail-fin motion and adjusts the slider position in real time to maintain stability. Compared with existing approaches, our method substantially improves the efficiency and stability of 3-D fast-start maneuvers, providing valuable guidance for enhancing the high maneuverability of underwater robots in complex underwater environments.
1 January 2026 in IEEE Transactions on Automation Science and Engineering
10 November 2025 in IEEE Robotics and Automation Letters
Biological adhesion represents a remarkable evolutionary adaptation, as exemplified by remoras using dorsal suction cups for hitchhiking and octopuses employing independently controllable suction cups to adhere to complex surfaces. Therefore, this study focuses on the design, quantitative analysis, and system-level construction of their artificial counterparts. Firstly, a reversible, low preload requirement, and multi-sensory suction cup array is fabricated and mounted on the dorsal of a bionic robotic fish. Notably, each channel of the suction cup array is independently controlled to enhance adaptability. Subsequently, five metrics are proposed to systematically measure and analyze the adhesion system. Specifically, the optimal structural parameters enable the miniaturized suction cup to achieve a pull-off force of 16 N on an acrylic plane, with the capability to adapt to varying surface radius and roughness. Furthermore, by leveraging sensory information and a hierarchical control strategy, we develop an autonomous adhesion method that enables the robotic fish to fine-tune the adhesion system according to varying surface characteristics and dynamically adjust under disturbed conditions. Finally, various aquatic experiments are conducted to validate the effectiveness and adaptability of the proposed adhesion system.