Design of an interval type-2 fuzzy neural network sliding mode robust controller for higher stability of magnetic spacecraft attitude control

This paper designs an interval type-2 fuzzy neural network sliding mode robust controller (IT2FNNSMRC) to improve the stability of the vibrational angle of the orbital plane in magnetic rigid spacecraft attitude control. The control system consists of an interval type-2 fuzzy neural network (IT2FNN) controller, a PD controller, and a robust controller in parallel connection. The IT2FNN controller, as a nonlinear regulator, compensates the nonlinearity of the controlled object; the PD controller, as a feedback controller, ensures the global asymptotic stability of the control system; the robust controller inhibits input load disturbance. The IT2FNN controller hereof has a self-organizing function which enables it to automatically determine the network structure and parameters online. At the stage of IT2FNN structure learning, the standard on rule growth is set according to the incentive intensities of IT2FNN rule premises. A new rule is generated when the incentive intensities of rules are all smaller than a certain threshold; next, a significance index is set for each rule. When the significance index of some rule decays to a certain threshold, the corresponding rule shall be deleted to achieve the goals of optimizing IT2FNN structure and reducing system complexity. At the stage of parameter learning, adaptive adjustment of IT2FNN parameters is made via the sliding mode control theory learning algorithm, and the stabilities of the algorithm and control system are proven using Lyapunov function. Finally, the proposed control scheme is used in the control of a magnetic rigid spacecraft, as compared to three other designed control methods. Simulation results show that IT2FNNSMRC has superior control precision and stability. And the IT2FNN which adopts the proposed learning algorithm can address uncertainty satisfactorily, with higher computational implementability.

A Robust Control via a Fuzzy System with PID for the ROV

Uncertainty and nonlinearity in the depth control of remotely operated vehicles (ROVs) have been widely studied, especially in complex underwater environments. To improve the motion performance of ROVs and enhance their robustness, the model of ROV depth control in complex water environments was developed. The developed control scheme of interval type-2 fuzzy proportional-integral-derivative control (IT2FPID) is based on proportional-integral-derivative control (PID) and interval type-2 fuzzy logic control (IT2FLC). The performance indicators were used to evaluate the immunity of the controller type to external disturbances. The overshoot of 0.3% and settling time of 7.5 s of IT2FPID seem to be more robust compared to those of type-1 fuzzy proportional-integral-derivative (T1FPID) and PID.

Online Control for Biped Robot with Incremental Learning Mechanism

In this paper, we develop a new online walking controller for biped robots, which integrates a neural-network estimator and an incremental learning mechanism to improve the control performance in dynamic environment. With the aid of an iteration algorithm for updating, some newly incoming data can be used straightforwardly to update into the original well-trained model, in order to avoid a time-consuming retraining procedure. On the other hand, how to maintain the zero-moment-point stability and counteract the effect of yaw moment simultaneously is also a key technical problem to be addressed. To this end, an interval type-2 fuzzy weight identifier is newly developed, which assigns weight for each walking sample to deal with the imbalanced distribution problem of training data. The effectiveness of the proposed control scheme has been verified through a full-dynamics simulation and a practical robot experiment.

Multi-level control of zero-moment point-based humanoid biped robots: a review

Researchers dream of developing autonomous humanoid robots which behave/walk like a human being. Biped robots, although complex, have the greatest potential for use in human-centred environments such as the home or office. Studying biped robots is also important for understanding human locomotion and improving control strategies for prosthetic and orthotic limbs. Control systems of humans walking in cluttered environments are complex, however, and may involve multiple local controllers and commands from the cerebellum. Although biped robots have been of interest over the last four decades, no unified stability/balance criterion adopted for stabilization of miscellaneous walking/running modes of biped robots has so far been available. The literature is scattered and it is difficult to construct a unified background for the balance strategies of biped motion. The zero-moment point (ZMP) criterion, however, is a conservative indicator of stabilized motion for a class of biped robots. Therefore, we offer a systematic presentation of multi-level balance controllers for stabilization and balance recovery of ZMP-based humanoid robots.

Gait motion stabilization tuning approach of biped robot based on augmented reality

Zero moment point (ZMP) is the most popular concept that is applied to stabilize the gait motion of a biped robot. This paper utilizes ZMP with the augmented-reality (AR) method to improve the stability of gait motion of a biped robot. The 3ds Max computer software package is used to build a virtual robot. Under an achieved joint angle data of solid robot to produce an animation of the robot's trajectory, the joint angle data are transmitted to the virtual robot to analyze the offset of the trunk. Furthermore, this investigation adopts AR to allow the user to make direct comparisons between the solid and virtual robot before and after the gait motion is corrected. The animated trajectories of the virtual robot are compared and the relevant data provide feedback to the solid robot to adjust the joint angle and further correct its posture. The experimental results reveal that the proposed scheme can improve gait motion, even when the biped robot is affected by an unexpected loading disturbance. As well as improving the stability of gait motion of a biped robot, the results of this study can also be used to teach the application of the proposed method in a robotics class.

Interval type-2 fuzzy PID controller for uncertain nonlinear inverted pendulum system

In this paper, the interval type-2 fuzzy proportional-integral-derivative controller (IT2F-PID) is proposed for controlling an inverted pendulum on a cart system with an uncertain model. The proposed controller is designed using a new method of type-reduction that we have proposed, which is called the simplified type-reduction method. The proposed IT2F-PID controller is able to handle the effect of structure uncertainties due to the structure of the interval type-2 fuzzy logic system (IT2-FLS). The results of the proposed IT2F-PID controller using a new method of type-reduction are compared with the other proposed IT2F-PID controller using the uncertainty bound method and the type-1 fuzzy PID controller (T1F-PID). The simulation and practical results show that the performance of the proposed controller is significantly improved compared with the T1F-PID controller.

Energy-efficient SVM learning control system for biped walking robots

An energy-efficient support vector machine (EE-SVM) learning control system considering the energy cost of each training sample of biped dynamic is proposed to realize energy-efficient biped walking. Energy costs of the biped walking samples are calculated. Then the samples are weighed with the inverses of the energy costs. An EE-SVM objective function with energy-related slack variables is proposed, which follows the principle that the sample with the lowest energy consumption is treated as the most important one in the training. That means the samples with lower energy consumption contribute more to the EE-SVM regression function learning, which highly increases the energy efficiency of the biped walking. Simulation results demonstrate the effectiveness of the proposed method.

Walking motion generation, synthesis, and control for biped robot by using PGRL, LPI, and fuzzy logic

This paper proposes the implementation of fuzzy motion control based on reinforcement learning (RL) and Lagrange polynomial interpolation (LPI) for gait synthesis of biped robots. First, the procedure of a walking gait is redefined into three states, and the parameters of this designed walking gait are determined. Then, the machine learning approach applied to adjusting the walking parameters is policy gradient RL (PGRL), which can execute real-time performance and directly modify the policy without calculating the dynamic function. Given a parameterized walking motion designed for biped robots, the PGRL algorithm automatically searches the set of possible parameters and finds the fastest possible walking motion. The reward function mainly considered is first the walking speed, which can be estimated from the vision system. However, the experiment illustrates that there are some stability problems in this kind of learning process. To solve these problems, the desired zero moment point trajectory is added to the reward function. The results show that the robot not only has more stable walking but also increases its walking speed after learning. This is more effective and attractive than manual trial-and-error tuning. LPI, moreover, is employed to transform the existing motions to the motion which has a revised angle determined by the fuzzy motion controller. Then, the biped robot can continuously walk in any desired direction through this fuzzy motion control. Finally, the fuzzy-based gait synthesis control is demonstrated by tasks and point- and line-target tracking. The experiments show the feasibility and effectiveness of gait learning with PGRL and the practicability of the proposed fuzzy motion control scheme.