Longxin Lin

Supervised Neural Q_learning based Motion Control for Bionic Underwater Robots

Bionic underwater robots have been a hot research area in recent years. The motion control methods for a kind of bionic underwater robot with two undulating fins are discussed in this paper. The equations of motion for the bionic underwater robot are described. To apply the reinforcement learning to the actual robot control, a Supervised Neural Q_learning (SNQL) algorithm is put forward. This algorithm is based on conventional Q_learning algorithm, but has three remarkable distinctions: (1) using a feedforward neural network to approximate the Q_function table; (2) adopting a learning sample database to speed up learning and improve the stability of learning system; (3) introducing a supervised control in the earlier stage of learning for safety and to speed up learning again. Experiments of swimming straightforward are carried out with SNQL algorithm. Results indicate that the SNQL algorithm is more effective than pure neural Q_learning or supervised control. It is a feasible approach to figure out the motion control for bionic underwater robots.

Effective motion control of the biomimetic undulating fin via iterative learning

The biomimetic undulating fin, RoboGnilos, is inspired by natural fish that generally swim via undulations of a long dorsal or anal fin. However, the present performance of this fin-type underwater propulsor can hardly be satisfactory in velocity, efficiency, or maneuverability, and retains a long distance to practical applications. This paper examines the dynamics of the undulating fin, and proposes an iterative learning approach based motion control to improve its steady propulsion velocity. This iterative learning controller is cooperated with a filter, to reduce the measurement noise, and a curve fitting component, to keep the necessary phase difference between neighbored fin rays. The detailed iterative learning based motion control algorithm is designed and implemented in the biomimetic undulating fin. The experimental results validate that the proposed learning motion control can effectively improve the propulsion of RoboGnilos. For instance, the steady propulsion velocity may be enhanced by over 40% with specified parameters.

Learning Control for Biomimetic Undulating Fins: An Experimental Study

Learning control should focus on imitating natural fish’s adaptability to complex and dynamic environment to some extent, rather than mimicking streamlined shapes or specific actuators to develop more mechanical prototypes. In this paper, an experimental study on a proposed learning control of the robotic undulating fin, RoboGnilos, is suggested and explored. This study takes inspirations from biological world to practical control algorithms. In detail, an iterative learning scheme based control is studied with the cooperation of a filter to reduce the measurement noise, and a curve fitting component to keep the necessary phase difference between neighboring fin rays. Moreover, the iterative learning control algorithm is designed and implemented for practical applications. The experimental results validate that the proposed learning control can effectively improve the propulsion of RoboGnilos. For instance, the steady propulsion velocity may be enhanced by over 40% with some specified parameters.

Bionic bladder based depth control for bionic underwater robots

Depth control of underwater robots is an indispensably function, especially when robots are stationary in water. A bionic bladder system was designed to control the depth of the robots in water. It was composed of a cylinder and a piston. The dynamic models of how the bionic bladder system controls underwater robots were established and based on which a dual-velocity control system was designed. The results of simulation showed that a good control performance could be achieved with proper control parameters. The experiments have been done in water tank to test and validate the performance of the control system.

The Data Collection and Transmission System of Undulated Biomimetic Propulsor Based on CAN Bus

The data collection and transmission system based on CAN bus is designed and realized in order to implement the real-time data collection and reliable transmission in distributed control system of undulated biomimetic propulsor. 1-wire A/D DS2450 and Serial D/A converter AD5551 are used to implement data collection and transmission. The architecture of the system is introduced from the viewpoint of the hardware. The software realization methods of DS2450 and AD5551 are also explained. Many experiments demonstrate that the proposed system has characteristic of high reliability and real time performance.