Sliding Mode Observer-Based Heading Control for a Gliding Robotic Dolphin

Yuan, Jun; Wu, Zhengxing; Yu, Junzhi; Tan, Min

doi:10.1109/tie.2017.2674606

Cited by 54 publications

(12 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Inspired by nature animals, scientists designed bionic robots such as sharks, jellyfish, dolphins, etc. to explore marine resources [1]- [4]. Similarly, we got inspiration from fish and then introduced a new type of autonomous unmanned vehicle -hybrid robotic fish (HRF) that contains two different motion modes, including wave drive mode and sail drive mode, which could assist the robot in achieving long-range monitoring with little energy cost.…”

Section: Introductionmentioning

confidence: 99%

A Hybrid Forecasting Model for the Velocity of Hybrid Robotic Fish Based on Back-Propagation Neural Network With Genetic Algorithm Optimization

2020

View full text Add to dashboard Cite

Marine unmanned vehicle is a novel robot widely used in ocean observation, and its accurate control is of significance to their path planning. We want to find a method to predict the velocity and course of this robot, which can help us realize the accurate control of it. The paper proposed a promising type of hybrid robotic fish (HRF), which can realize two kinds of motion modes on the sea surface. Firstly, the configuration and dynamic model of the HRF were analyzed elaborately. Then, to realize accurate velocity prediction under two kinds of motion modes of HRF, the influence factors are presented in a complex marine environment. Based on the influence factors to its maneuverability, such as wind or wave parameters, a velocity prediction algorithm based on back-propagation neural network (BPNN) was introduced. However, BPNN has the disadvantages of extended learning and training time, easily falling into local optimum. Then we found that genetic algorithm (GA), which is a kind of evolutionary algorithm, is suitable for our problem. Therefore, the accuracy and efficiency of the prediction algorithm were improved by adopting the genetic algorithm to optimize the weight and threshold of BPNN. Taking the experimental data from the pool test, the back-propagation neural network with genetic algorithm (GA-BPNN) forecasting model was established. Besides, the other prediction methods were compared and evaluated under the same assessment criterion to validate the proposed forecasting model. The experimental results demonstrate that the GA-BPNN model has higher accuracy and efficiency compared with other prediction algorithms, which verifies the feasibility of the velocity prediction model for hybrid robotic fish in complex ocean environments.

show abstract

Section: Introductionmentioning

confidence: 99%

A Hybrid Forecasting Model for the Velocity of Hybrid Robotic Fish Based on Back-Propagation Neural Network With Genetic Algorithm Optimization

2020

View full text Add to dashboard Cite

show abstract

“…Therefore, these small-scale biomimetic robots have been receiving increasing interest from academia. Most researchers have focused on a prototype design [3][4][5] and the control methods of the driving system [6][7][8][9]. However, the closed-loop motion control (such as trajectory tracking, etc.)…”

Section: Introductionmentioning

confidence: 99%

Improved Model Predictive-Based Underwater Trajectory Tracking Control for the Biomimetic Spherical Robot under Constraints

et al. 2020

View full text Add to dashboard Cite

To improve the autonomy of the biomimetic sphere robot (BSR), an underwater trajectory tracking problem was studied. Considering the thrusters saturation of the BSR, an improved model predictive control (MPC) algorithm that features processing multiple constraints was designed. With the proposed algorithm, the kinematic and dynamic models of the BSR are combined in order to establish the predictive model, and a new state-space model is designed that is based on an increment of the control input. Furthermore, to avoid the infeasibility of the cost function in the MPC controller design, a new term with a slack variable is added to the objective function, which enables the constraints to be imposed as soft constraints. The simulation results illustrate that the BSR was able to track the desired trajectory accurately and stably while using the improved MPC algorithm. Furthermore, a comparison with the traditional MPC shows that the designed MPC-based increment of the control input is small. In addition, a comparative simulation using the backstepping method verifies the effectiveness of the proposed method. Unlike previous studies that only focused on the simulation validations, in this study a series of experiments were carried out that further demonstrate the effectiveness of the improved MPC for underwater trajectory tracking of the BSR. The experimental results illustrate that the improved MPC is able to drive the BSR to quickly track the reference trajectory. When compared with a traditional MPC and the backstepping method used in the experiment, the proposed MPC-based trajectory is closer to the reference trajectory.

show abstract

“…A numerical method for minimum time heading control of an fixed speed UMV is proposed by Rhoads et al [24], while a Sugeno fuzzy inference system and Kalman filter are integrated into the heading control system by Toe et al [25], and a self-tuning fuzzy control algorithm is proposed by Fang et al [26]. Artificial neural network control [27], [28], sliding mode control [29], dynamic surface control [30], global finite time control [31], backstepping control [32]- [34], visual feedback control [35], network based hybrid control [36], sliding mode observer based control [37], linear feedback control [38], artificial fish swarm algorithm [39], are all designed by researchers for the UMV's heading control system.…”

Section: Introductionmentioning

confidence: 99%

Heading Control of Unmanned Marine Vehicles Based on an Improved Robust Adaptive Fuzzy Neural Network Control Algorithm

et al. 2019

View full text Add to dashboard Cite

A robust adaptive fuzzy neural network control (RAFNNC) algorithm is proposed based on a generalized dynamic fuzzy neural network (GDFNN), proportion-integral-differential (PID), and improved bacterial foraging optimization (BFO) algorithm, for heading the control of the unmanned marine vehicle (UMV) in the presence of a complex environment disturbance. First, the inverse dynamic model of the motion control of UMV is established based on the GDFNN for the uncertain disturbance caused by the complex environment disturbance. Then, the adaptive rate of the fuzzy neural network is designed based on the error between the real UMV heading angle and designed reference heading angle, so as to further adjust the weight parameter of the GDFNN, and then, the output control value of the neural network is obtained. In order to further reduce the computation amount and computation time of the RAFNNC, the parameters of the PID control algorithm were optimized in advance by using the improved BFO algorithm. The fractal dimension step size and the intelligent probe operation are integrated into the BFO algorithm, in order to optimize the operation time and accuracy of the algorithm. Stability of the designed RAFNNC algorithm for the heading control of the UMV in the presence of complex marine environment disturbance is proved by the Lyapunov stability theory, and the effectiveness and accuracy of the control algorithm proposed are verified by semi-physical simulation experiment carried out in our laboratory. INDEX TERMS Unmanned marine vehicle (UMV), heading control, robust adaptive fuzzy neural network control (RAFNNC), generalized dynamic fuzzy neural network (GDFNN), bacterial foraging optimization (BFO).

show abstract

Sliding Mode Observer-Based Heading Control for a Gliding Robotic Dolphin

Cited by 54 publications

References 29 publications

A Hybrid Forecasting Model for the Velocity of Hybrid Robotic Fish Based on Back-Propagation Neural Network With Genetic Algorithm Optimization

A Hybrid Forecasting Model for the Velocity of Hybrid Robotic Fish Based on Back-Propagation Neural Network With Genetic Algorithm Optimization

Improved Model Predictive-Based Underwater Trajectory Tracking Control for the Biomimetic Spherical Robot under Constraints

Heading Control of Unmanned Marine Vehicles Based on an Improved Robust Adaptive Fuzzy Neural Network Control Algorithm

Contact Info

Product

Resources

About