Multimodal swimming control of a robotic fish with pectoral fins using a CPG network

Control of movement of underwater swimmers: Animals, simulated animates and swimming robots

The control of movement in living organisms represents a fundamental task that the brain has evolved to solve. One crucial aspect is how the nervous system organizes the transformation of sensory information into motor commands. These commands lead to muscle activation and subsequent animal movement, which can exhibit complex patterns. One example of such movement is locomotion, which involves the translation of the entire body through space. Central Pattern Generators (CPGs) are neuronal circuits that provide control signals for these movements. Compared to the intricate circuits found in the brain, CPGs can be simplified into networks of neurons that generate rhythmic activation, coordinating muscle movements. Since the 1990s, researchers have developed numerous models of locomotive circuits to simulate different types of animal movement, including walking, flying, and swimming. Initially, the primary goal of these studies was to construct biomimetic robots. However, it became apparent that simplified CPGs alone were not sufficient to replicate the diverse range of adaptive locomotive movements observed in living organisms. Factors such as sensory modulation, higher-level control, and cognitive components related to learning and memory needed to be considered. This necessitated the use of more complex, high-dimensional circuits, as well as novel materials and hardware, in both modeling and robotics. With advancements in high-power computing, artificial intelligence, big data processing, smart materials, and electronics, the possibility of designing a new generation of true bio-mimetic robots has emerged. These robots have the capability to imitate not only simple locomotion but also exhibit adaptive motor behavior and decision-making. This motivation serves as the foundation for the current review, which aims to analyze existing concepts and models of movement control systems. As an illustrative example, we focus on underwater movement and explore the fundamental biological concepts, as well as the mathematical and physical models that underlie locomotion and its various modulations.

Bioinspired Central Pattern Generator and T-S Fuzzy Neural Network-Based Control of a Robotic Manta for Depth and Heading Tracking

Aiming at the difficult problem of motion control of robotic manta with pectoral fin flexible deformation, this paper proposes a control scheme that combines the bioinspired Central Pattern Generator (CPG) and T-S Fuzzy neural network(NN)-based control. An improved CPG drive network is presented for the multi-stage fin structure of the robotic manta. Considering the unknown dynamics and the external environmental disturbances, a sensor-based classic T-S Fuzzy NN controller is designed for heading and depth control. Finally, a pool test demonstrates the effectiveness and robustness of the proposed controller: the robotic manta can track the depth and heading with an error of ±6 cm and ±6°, satisfying accuracy requirements.

Reinforcement learning-based optimization of locomotion controller using multiple coupled CPG oscillators for elongated undulating fin propulsion

This article proposes a locomotion controller inspired by black Knifefish for undulating elongated fin robot. The proposed controller is built by a modified CPG network using sixteen coupled Hopf oscillators with the feedback of the angle of each fin-ray. The convergence rate of the modified CPG network is optimized by a reinforcement learning algorithm. By employing the proposed controller, the undulating elongated fin robot can realize swimming pattern transformations naturally. Additionally, the proposed controller enables the configuration of the swimming pattern parameters known as the amplitude envelope, the oscillatory frequency to perform various swimming patterns. The implementation processing of the reinforcement learning-based optimization is discussed. The simulation and experimental results show the capability and effectiveness of the proposed controller through the performance of several swimming patterns in the varying oscillatory frequency and the amplitude envelope of each fin-ray.

A survey on CPG-inspired control models and system implementation

This paper surveys the developments of the last 20 years in the field of central pattern generator (CPG) inspired locomotion control, with particular emphasis on the fast emerging robotics-related applications. Functioning as a biological neural network, CPGs can be considered as a group of coupled neurons that generate rhythmic signals without sensory feedback; however, sensory feedback is needed to shape the CPG signals. The basic idea in engineering endeavors is to replicate this intrinsic, computationally efficient, distributed control mechanism for multiple articulated joints, or multi-DOF control cases. In terms of various abstraction levels, existing CPG control models and their extensions are reviewed with a focus on the relative advantages and disadvantages of the models, including ease of design and implementation. The main issues arising from design, optimization, and implementation of the CPG-based control as well as possible alternatives are further discussed, with an attempt to shed more light on locomotion control-oriented theories and applications. The design challenges and trends associated with the further advancement of this area are also summarized.