Hybrid-Input Convolutional Neural Network-Based Underwater Image Quality Assessment.

Since precisely sensing the underwater environment is a challenging prerequisite for safe and reliable underwater operation, interest in underwater image processing is growing at a rapid pace. In engineering applications, there are redundant underwater images addressed in real-time on the remotely operated vehicle (ROV). It puts the equipment or operators under great pressure. To relieve this pressure by transmitting images selectively according to the degradation degree, we propose an end-to-end hybrid-input convolutional neural network (HI-CNN) to predict the degradation of underwater images. First, we propose a feature extraction module to extract the features of original underwater images and saliency maps concurrently, which is composed of two branches with the same structure and shared parameters. Second, we design an end-to-end model to predict the quality scores of original images, which consists of a feature extraction module and a prediction module. Finally, we establish a real-world dataset to make the proposed model be duplicated in the practical underwater environment. Through several experiments, we demonstrate that the proposed model outperforms existing models in predicting underwater image quality.

Sideslip-Compensated Guidance-Based Adaptive Neural Control of Marine Surface Vessels.

This article presents an improved guidance law for underactuated marine vessels that compensates cross-track error caused by external disturbances through its sideslip. The proposed guidance law demonstrates improved path-following performance regardless of disturbances, such as waves, winds, and ocean currents. This article also presents an adaptive neural-network (NN) control law for the partially known vessel dynamics with state constraints. For satisfying the state constraints, this control scheme adopts an integral barrier Lyapunov function (iBLF)-based backstepping control technique. It is shown that the closed-loop system remains bounded, and state constraints are always satisfied. Finally, the efficacy of the improved guidance law and iBLF-based adaptive control strategy was verified in simulation and experiments using an autonomous surface vessel.

Broad Learning With Reinforcement Learning Signal Feedback: Theory and Applications.

Broad learning systems (BLSs) have attracted considerable attention due to their powerful ability in efficient discriminative learning. In this article, a modified BLS with reinforcement learning signal feedback (BLRLF) is proposed as an efficient method for improving the performance of standard BLS. The main differences between our research and BLS are as follows. First, we add weight optimization after adding additional nodes or new training samples. Motivated by the weight iterative optimization in the convolution neural network (CNN), we use the output of the network as feedback while employing value iteration (VI)-based adaptive dynamic programming (ADP) to facilitate calculation of near-optimal increments of connection weights. Second, different from the homogeneous incremental algorithms in standard BLS, we integrate those broad expansion methods, and the heuristic search method is used to enable the proposed BLRLF to optimize the network structure autonomously. Although the training time is affected to a certain extent compared with BLS, the newly proposed BLRLF still retains a fast computational nature. Finally, the proposed BLRLF is evaluated using popular benchmarks from the UC Irvine Machine Learning Repository and many other challenging data sets. These results show that BLRLF outperforms many state-of-the-art deep learning algorithms and shallow networks proposed in recent years.

Reinforcement Learning-Based Nearly Optimal Control for Constrained-Input Partially Unknown Systems Using Differentiator.

In this article, a synchronous reinforcement-learning-based algorithm is developed for input-constrained partially unknown systems. The proposed control also alleviates the need for an initial stabilizing control. A first-order robust exact differentiator is employed to approximate unknown drift dynamics. Critic, actor, and disturbance neural networks (NNs) are established to approximate the value function, the control policy, and the disturbance policy, respectively. The Hamilton-Jacobi-Isaacs equation is solved by applying the value function approximation technique. The stability of the closed-loop system can be ensured. The state and weight errors of the three NNs are all uniformly ultimately bounded. Finally, the simulation results are provided to verify the effectiveness of the proposed method.

Event-Triggered Reinforcement Learning-Based Adaptive Tracking Control for Completely Unknown Continuous-Time Nonlinear Systems.

In this paper, event-triggered reinforcement learning-based adaptive tracking control is developed for the continuous-time nonlinear system with unknown dynamics and external disturbances. The critic and action neural networks are designed to approximate an unknown long-term performance index and controller, respectively. The dead-zone event-triggered condition is developed to reduce communication and computational costs. Rigorous theoretical analysis is provided to show that the closed-loop system can be stabilized. The weight errors and the filtered tracking error are all uniformly ultimately bounded. Finally, to demonstrate the developed controller, the simulation results are provided using an autonomous underwater vehicle model.

Admittance-Based Adaptive Cooperative Control for Multiple Manipulators With Output Constraints.

This paper proposes a novel adaptive control methodology based on the admittance model for multiple manipulators transporting a rigid object cooperatively along a predefined desired trajectory. First, an admittance model is creatively applied to generate reference trajectory online for each manipulator according to the desired path of the rigid object, which is the reference input of the controller. Then, an innovative integral barrier Lyapunov function is utilized to tackle the constraints due to the physical and environmental limits. Adaptive neural networks (NNs) are also employed to approximate the uncertainties of the manipulator dynamics. Different from the conventional NN approximation method, which is usually semiglobally uniformly ultimately bounded, a switching function is presented to guarantee the global stability of the closed loop. Finally, the simulation studies are conducted on planar two-link robot manipulators to validate the efficacy of the proposed approach.

Robot Learning System Based on Adaptive Neural Control and Dynamic Movement Primitives.

This paper proposes an enhanced robot skill learning system considering both motion generation and trajectory tracking. During robot learning demonstrations, dynamic movement primitives (DMPs) are used to model robotic motion. Each DMP consists of a set of dynamic systems that enhances the stability of the generated motion toward the goal. A Gaussian mixture model and Gaussian mixture regression are integrated to improve the learning performance of the DMP, such that more features of the skill can be extracted from multiple demonstrations. The motion generated from the learned model can be scaled in space and time. Besides, a neural-network-based controller is designed for the robot to track the trajectories generated from the motion model. In this controller, a radial basis function neural network is used to compensate for the effect caused by the dynamic environments. The experiments have been performed using a Baxter robot and the results have confirmed the validity of the proposed methods.

Neural Networks Enhanced Adaptive Admittance Control of Optimized Robot-Environment Interaction.

In this paper, an admittance adaptation method has been developed for robots to interact with unknown environments. The environment to be interacted with is modeled as a linear system. In the presence of the unknown dynamics of environments, an observer in robot joint space is employed to estimate the interaction torque, and admittance control is adopted to regulate the robot behavior at interaction points. An adaptive neural controller using the radial basis function is employed to guarantee trajectory tracking. A cost function that defines the interaction performance of torque regulation and trajectory tracking is minimized by admittance adaptation. To verify the proposed method, simulation studies on a robot manipulator are conducted.

A Sampling-Based Bayesian Approach for Cooperative Multiagent Online Search With Resource Constraints.

This paper presents a cooperative multiagent search algorithm to solve the problem of searching for a target on a 2-D plane under multiple constraints. A Bayesian framework is used to update the local probability density functions (PDFs) of the target when the agents obtain observation information. To obtain the global PDF used for decision making, a sampling-based logarithmic opinion pool algorithm is proposed to fuse the local PDFs, and a particle sampling approach is used to represent the continuous PDF. Then the Gaussian mixture model (GMM) is applied to reconstitute the global PDF from the particles, and a weighted expectation maximization algorithm is presented to estimate the parameters of the GMM. Furthermore, we propose an optimization objective which aims to guide agents to find the target with less resource consumptions, and to keep the resource consumption of each agent balanced simultaneously. To this end, a utility function-based optimization problem is put forward, and it is solved by a gradient-based approach. Several contrastive simulations demonstrate that compared with other existing approaches, the proposed one uses less overall resources and shows a better performance of balancing the resource consumption.

Carbon Cloth Supported Nano-Mg(OH)2 for the Enrichment and Recovery of Rare Earth Element Eu(III) From Aqueous Solution.

Nano-Mg(OH)2 is attracting great attention as adsorbent for pre-concentration and recovery of rare earth elements (REEs) from low-concentration solution, due to its superior removal efficiency for REEs and environmental friendliness. However, the nanoparticles also cause some severe problems during application, including aggregation, blockage in fixed-bed column, as well as the difficulties in separation and reuse. Herein, in order to avoid the mentioned problems, a carbon cloth (CC) supported nano-Mg(OH)2 (nano-Mg(OH)2@CC) was synthesized by electrodeposition. The X-ray diffraction and scanning electron microscopy analysis demonstrated that the interlaced nano-sheet of Mg(OH)2 grew firmly and uniformly on the surface of carbon cloth fibers. Batch adsorption experiments of Eu(III) indicated that the nano-Mg(OH)2@CC composite maintained the excellent adsorption performance of nano-Mg(OH)2 toward Eu(III). After adsorption, the Eu containing composite was calcined under nitrogen atmosphere. The content of Eu2O3 in the calcined material was as high as 99.66%. Fixed-bed column experiments indicated that no blockage for Mg(OH)2@CC composite was observed during the treatment, while the complete blockage of occurred to nano-Mg(OH)2 at an effluent volume of 240 mL. Moreover, the removal efficiency of Mg(OH)2@CC was still higher than 90% until 4,200 mL of effluent volume. This work provides a promising method for feasible application of nanoadsorbents in fixed-bed process to recycle low-concentration REEs from wastewater.

Neural network-based motion control of an underactuated wheeled inverted pendulum model.

In this paper, automatic motion control is investigated for one of wheeled inverted pendulum (WIP) models, which have been widely applied for modeling of a large range of two wheeled modern vehicles. First, the underactuated WIP model is decomposed into a fully actuated second order subsystem Σa consisting of planar movement of vehicle forward and yaw angular motions, and a nonactuated first order subsystem Σb of pendulum motion. Due to the unknown dynamics of subsystem Σa and the universal approximation ability of neural network (NN), an adaptive NN scheme has been employed for motion control of subsystem Σa . The model reference approach has been used whereas the reference model is optimized by the finite time linear quadratic regulation technique. The pendulum motion in the passive subsystem Σb is indirectly controlled using the dynamic coupling with planar forward motion of subsystem Σa , such that satisfactory tracking of a set pendulum tilt angle can be guaranteed. Rigours theoretic analysis has been established, and simulation studies have been performed to demonstrate the developed method.

Terminal sliding mode tracking control for a class of SISO uncertain nonlinear systems.

In this paper, the terminal sliding mode tracking control is proposed for the uncertain single-input and single-output (SISO) nonlinear system with unknown external disturbance. For the unmeasured disturbance of nonlinear systems, terminal sliding mode disturbance observer is presented. The developed disturbance observer can guarantee the disturbance approximation error to converge to zero in the finite time. Based on the output of designed disturbance observer, the terminal sliding mode tracking control is presented for uncertain SISO nonlinear systems. Subsequently, terminal sliding mode tracking control is developed using disturbance observer technique for the uncertain SISO nonlinear system with control singularity and unknown non-symmetric input saturation. The effects of the control singularity and unknown input saturation are combined with the external disturbance which is approximated using the disturbance observer. Under the proposed terminal sliding mode tracking control techniques, the finite time convergence of all closed-loop signals are guaranteed via Lyapunov analysis. Numerical simulation results are given to illustrate the effectiveness of the proposed terminal sliding mode tracking control.