Cooperative Online Learning for Multiagent System Control via Gaussian Processes With Event-Triggered Mechanism.

In the realm of the cooperative control of multiagent systems (MASs) with unknown dynamics, Gaussian process (GP) regression is widely used to infer the uncertainties due to its modeling flexibility of nonlinear functions and the existence of a theoretical prediction error bound. Online learning, which involves incorporating newly acquired training data into GP models, promises to improve control performance by enhancing predictions during the operation. Therefore, this article investigates the online cooperative learning algorithm for MAS control. Moreover, an event-triggered data selection mechanism, inspired by the analysis of a centralized event-trigger (CET), is introduced to reduce the model update frequency and enhance the data efficiency. With the proposed learning-based control, the practical convergence of the MAS is validated with guaranteed tracking performance via the Lyapunov theory. Furthermore, the exclusion of the Zeno behavior for individual agents is shown. Finally, the effectiveness of the proposed event-triggered online learning method is demonstrated in simulations.

6-D Object Pose Estimation Based on Point Pair Matching for Robotic Grasp Detection.

The 6-D pose estimation is a critical work essential to achieve reliable robotic grasping. Currently, the prevalent method is reliant on keypoint correspondence. However, this approach hinges on the determination of object keypoint locations, alongside their detection and localization in real scenes. It also employs the random sample consensus (RANSAC)-based perspective-n-point (PnP) algorithm to solve the pose. Yet, it is nondifferentiable and incapable of backpropagation with loss during the training phase. Alternatively, the direct regression method, while speedy and differentiable, falls short in terms of pose estimation performance, and thus needs enhancement. In view of these gaps, we investigate PPM6D, a new method for 6-D object pose estimation based on regression and point pair matching. Our methodology begins with a proposed cross-fusion module, designed to achieve the fusion and complementation of RGB features and point cloud features. Subsequently, an attention module adjusts the features of the object's 3-D model. Finally, we design a point pair matching module for effective matching of points and characteristics, resulting in an integral matching and fusion. PPM6D is extensively trained and tested utilizing benchmark datasets like LINEMOD, occlusion LINEMOD (LINEMOD-occ), YCB-Video, and T-LESS dataset. Experimental results prove that PPM6D can outperform many keypoint-based pose estimation methods, given its relatively rapid speed, thereby offering novel regression-based pose estimation ideas. When applied to real-world scenarios of object pose estimation tasks and grasp tasks of an actual Baxter robot, PPM6D demonstrates superior performance as compared to most alternatives.

Resilient Neuroadaptive Distributed Fixed-Time Attitude Coordination Control for Multiple Spacecraft.

This work studies the attitude coordination tracking problem for multiple spacecraft with consideration of unintended faults (communication link faults and actuator faults), inertial uncertainties, and external disturbances under a directed communication graph. A resilient neuroadaptive distributed fixed-time control scheme is investigated to solve this challenging problem. First, an improved adaptive distributed observer is established for followers to estimate the states of the leader when considering communication link faults. The proposed observer improves the resilience against communication link faults. Subsequently, to further cope with the problem of actuator faults, inertial uncertainties, and external disturbances, based on the proposed observer and the technique of adding a power integrator, a neuroadaptive distributed fixed-time attitude coordination controller is developed. Unlike the existing controllers, the proposed one requires less information when dealing with faults and lumped uncertainties, and has a lower-computational cost. Moreover, the fixed-time stability of the closed-loop system is ensured under the designed resilient neuroadaptive distributed control scheme. Finally, comparative simulations are carried out to manifest the effectiveness of the investigated coordination control method.

Compound Learning-Based Model Predictive Control Approach for Ducted-Fan Aerial Vehicles.

Designing an efficient learning-based model predictive control (MPC) framework for ducted-fan unmanned aerial vehicles (DFUAVs) is a difficult task due to several factors involving uncertain dynamics, coupled motion, and unorthodox aerodynamic configuration. Existing control techniques are either developed from largely known physics-informed models or are made for specific goals. In this regard, this article proposes a compound learning-based MPC approach for DFUAVs to construct a suitable framework that exhibits efficient dynamics learning capability with adequate disturbance rejection characteristics. At the start, a nominal model from a largely unknown DFUAV model is achieved offline through sparse identification. Afterward, a reinforcement learning (RL) mechanism is deployed online to learn a policy to facilitate the initial guesses for the control input sequence. Thereafter, an MPC-driven optimization problem is developed, where the obtained nominal (learned) system is updated by the real system, yielding improved computational efficiency for the overall control framework. Under appropriate assumptions, stability and recursive feasibility are compactly ensured. Finally, a comparative study is conducted to illustrate the efficacy of the designed scheme.

Mobile-UI-Repair: a deep learning based UI smell detection technique for mobile user interface.

The graphical user interface (GUI) in mobile applications plays a crucial role in connecting users with mobile applications. GUIs often receive many UI design smells, bugs, or feature enhancement requests. The design smells include text overlap, component occlusion, blur screens, null values, and missing images. It also provides for the behavior of mobile applications during their usage. Manual testing of mobile applications (app as short in the rest of the document) is essential to ensuring app quality, especially for identifying usability and accessibility that may be missed during automated testing. However, it is time-consuming and inefficient due to the need for testers to perform actions repeatedly and the possibility of missing some functionalities. Although several approaches have been proposed, they require significant performance improvement. In addition, the key challenges of these approaches are incorporating the design guidelines and rules necessary to follow during app development and combine the syntactical and semantic information available on the development forums. In this study, we proposed a UI bug identification and localization approach called Mobile-UI-Repair (M-UI-R). M-UI-R is capable of recognizing graphical user interfaces (GUIs) display issues and accurately identifying the specific location of the bug within the GUI. M-UI-R is trained and tested on the history data and also validated on real-time data. The evaluation shows that the average precision is 87.7% and the average recall is 86.5% achieved in the detection of UI display issues. M-UI-R also achieved an average precision of 71.5% and an average recall of 70.7% in the localization of UI design smell. Moreover, a survey involving eight developers demonstrates that the proposed approach provides valuable support for enhancing the user interface of mobile applications. This aids developers in their efforts to fix bugs.

Emotion detection from handwriting and drawing samples using an attention-based transformer model.

Emotion detection (ED) involves the identification and understanding of an individual's emotional state through various cues such as facial expressions, voice tones, physiological changes, and behavioral patterns. In this context, behavioral analysis is employed to observe actions and behaviors for emotional interpretation. This work specifically employs behavioral metrics like drawing and handwriting to determine a person's emotional state, recognizing these actions as physical functions integrating motor and cognitive processes. The study proposes an attention-based transformer model as an innovative approach to identify emotions from handwriting and drawing samples, thereby advancing the capabilities of ED into the domains of fine motor skills and artistic expression. The initial data obtained provides a set of points that correspond to the handwriting or drawing strokes. Each stroke point is subsequently delivered to the attention-based transformer model, which embeds it into a high-dimensional vector space. The model builds a prediction about the emotional state of the person who generated the sample by integrating the most important components and patterns in the input sequence using self-attentional processes. The proposed approach possesses a distinct advantage in its enhanced capacity to capture long-range correlations compared to conventional recurrent neural networks (RNN). This characteristic makes it particularly well-suited for the precise identification of emotions from samples of handwriting and drawings, signifying a notable advancement in the field of emotion detection. The proposed method produced cutting-edge outcomes of 92.64% on the benchmark dataset known as EMOTHAW (Emotion Recognition via Handwriting and Drawing).

An Efficient Robotic Pushing and Grasping Method in Cluttered Scene.

Pushing and grasping (PG) are crucial skills for intelligent robots. These skills enable robots to perform complex grasping tasks in various scenarios. These PG methods can be categorized into single-stage and multistage approaches. Single-stage methods are faster but less accurate, while multistage methods offer high accuracy at the expense of time efficiency. To address this issue, a novel end-to-end PG method called efficient PG network (EPGNet) is proposed in this article. EPGNet achieves both high accuracy and efficiency simultaneously. To optimize performance with fewer parameters, EfficientNet-B0 is used as the backbone of EPGNet. Additionally, a novel cross-fusion module is introduced to enhance network performance in robotic PG tasks. This module fuses and utilizes local and global features, aiding the network in handling objects of varying sizes in different scenes. EPGNet consists of two branches dedicated to predicting PG actions, respectively. Both branches are trained simultaneously within a Q-learning framework. Training data is collected through trial and error, involving the robot performing PG actions. To bridge the gap between simulation and reality, a unique PG dataset is proposed. Additionally, a YOLACT network is trained on the PG dataset to facilitate object detection and segmentation. A comprehensive set of experiments is conducted in simulated environments and real-world scenarios. The results demonstrate that EPGNet outperforms single-stage methods and offers competitive performance compared to multistage methods, all while utilizing fewer parameters. A video is available at https://youtu.be/HNKJjQH0MPc.

A Two Phases Multiobjective Trajectory Optimization Scheme for Multi-UGVs in the Sight of the First Aid Scenario.

Timely delivery of first aid supplies is significant to saving lives when an accident happens. Among the promising solutions provided for such scenarios, the application of unmanned vehicles has attracted ever more attention. However, such scenarios are often very complex, while the existing studies have not fully addressed the trajectory optimization problem of multiple unmanned ground vehicles (multi-UGVs) against the scenario. This study focuses on multi-UGVs trajectory optimization in the sight of first aid supply delivery tasks in mass accidents. A two-stage completely decoupling fuzzy multiobjective optimization strategy is designed. On the first stage, with the proposed timescale involved tridimensional tunneled collision-free trajectory (TITTCT) algorithm, collision-free coarse tunnels are build within a tridimensional coordinate system, respectively, for the UGVs as the corresponding configuration space for a further multiobjective optimization. On the second stage, a fuzzy multiobjective transcription method is designed to solve the decoupled optimal control problem (OCP) within the configuration space with the consideration of priority constrains. Following the two-stage design, the computational time is significantly reduced when achieving an optimal solution of the multi-UGV trajectory planning, which is crucial in a first aid task. In addition, other objectives are optimized with the aspiration level reflected. Simulation studies and experiments have been curried out to testify the effectiveness and the improved computational performance of the proposed design.

Event-Triggered Mechanism-Based Discrete-Time Nash Equilibrium Seeking for Graphic Game With Outlier-Resistant ESO.

In this article, we consider a discrete-time Nash equilibrium (NE) seeking problem for graphic game subject to disturbances. For the first-order dynamics, the discrete-time outlier-resistant extended state observer (ESO)-based game strategy is proposed to enable the players to estimate the disturbances under effect of anomaly measurements and then compensate them. An event-triggered mechanism is applied between adjacent players to reduce the frequency of communication. The convergence of the outlier-resistant ESO and control strategy is presented. Moreover, the upper bound of ϵ -NE solution deviating from the unique point of nominal system is given analytically. Then, the addressed issues are extended to high-order game systems. The NE seeking-based control strategy for each player is designed such that the equilibrium point converges to the ϵ -NE which is also analytically calculated. Finally, in order to verify the effectiveness of the proposed game strategy, an example of satellite system is given.

The association of preconceptional folic acid supplementation with gestational age and preterm birth risk in twin pregnancies: a prospective cohort study in China.

PURPOSE: This study aims to explore the association of maternal preconceptional folic acid (FA) supplementation with gestational age and preterm birth in twin pregnancies, and whether the association varies by chorionicity or conception mode. METHODS: From November 2018 to December 2021, the information of FA supplementation and pregnancy outcomes were collected in twin pregnant women. The linear regression models and the logistic regression were used to test the association of preconceptional FA supplementation with gestational age at delivery and preterm birth and premature rupture of membranes (PROM). RESULTS: A total of 416 twin pregnancies were included. Compared with no use in twins, maternal preconceptional FA use was associated with a 0.385-week longer gestational age (95% CI 0.019-0.751) and lower risk of preterm birth < 36 weeks (adjusted OR 0.519; 95% CI 0.301-0.895) and PROM (adjusted OR 0.426; 95% CI 0.215-0.845). The protective effect on preterm birth < 36 weeks and PROM is similar whether taking FA supplements alone or multivitamins. However, the associations varied by chorionicity and conception mode of twins or compliance with supplementation. The positive associations between preconceptional FA use and gestational age only remained significant among twins via assisted reproductive technology or dichorionic diamniotic twins. Significant protective effects on preterm birth < 36 weeks and PROM were only found among women who took FA at least 4 times a week before conception. CONCLUSION: Maternal preconceptional FA supplementation was associated with longer gestation duration and lower risk of preterm birth < 36 weeks and PROM in twin pregnancies. To improve the success of their pregnancies, reproductive women should start taking FA supplements well before conception and with good compliance.

Reinforcement Learning-Based Model Predictive Control for Discrete-Time Systems.

This article proposes a novel reinforcement learning-based model predictive control (RLMPC) scheme for discrete-time systems. The scheme integrates model predictive control (MPC) and reinforcement learning (RL) through policy iteration (PI), where MPC is a policy generator and the RL technique is employed to evaluate the policy. Then the obtained value function is taken as the terminal cost of MPC, thus improving the generated policy. The advantage of doing so is that it rules out the need for the offline design paradigm of the terminal cost, the auxiliary controller, and the terminal constraint in traditional MPC. Moreover, RLMPC proposed in this article enables a more flexible choice of prediction horizon due to the elimination of the terminal constraint, which has great potential in reducing the computational burden. We provide a rigorous analysis of the convergence, feasibility, and stability properties of RLMPC. Simulation results show that RLMPC achieves nearly the same performance as traditional MPC in the control of linear systems and exhibits superiority over traditional MPC for nonlinear ones.

Category-Level 6-D Object Pose Estimation With Shape Deformation for Robotic Grasp Detection.

Category-level 6-D object pose estimation plays a crucial role in achieving reliable robotic grasp detection. However, the disparity between synthetic and real datasets hinders the direct transfer of models trained on synthetic data to real-world scenarios, leading to ineffective results. Additionally, creating large-scale real datasets is a time-consuming and labor-intensive task. To overcome these challenges, we propose CatDeform, a novel category-level object pose estimation network trained on synthetic data but capable of delivering good performance on real datasets. In our approach, we introduce a transformer-based fusion module that enables the network to leverage multiple sources of information and enhance prediction accuracy through feature fusion. To ensure proper deformation of the prior point cloud to align with scene objects, we propose a transformer-based attention module that deforms the prior point cloud from both geometric and feature perspectives. Building upon CatDeform, we design a two-branch network for supervised learning, bridging the gap between synthetic and real datasets and achieving high-precision pose estimation in real-world scenes using predominantly synthetic data supplemented with a small amount of real data. To minimize reliance on large-scale real datasets, we train the network in a self-supervised manner by estimating object poses in real scenes based on the synthetic dataset without manual annotation. We conduct training and testing on CAMERA25 and REAL275 datasets, and our experimental results demonstrate that the proposed method outperforms state-of-the-art (SOTA) techniques in both self-supervised and supervised training paradigms. Finally, we apply CatDeform to object pose estimation and robotic grasp experiments in real-world scenarios, showcasing a higher grasp success rate.

Dynamic Event-Based Adaptive Fixed-Time Control for Uncertain Strict-Feedback Nonlinear Systems With State Constraints.

In this article, the event-triggered fixed-time tracking control is investigated for uncertain strict-feedback nonlinear systems involving state constraints. By employing the universal transformed function (UTF) and coordinate transformation techniques into backstepping design procedure, the proposed control scheme ensures that all states are constrained within the time-varying asymmetric boundaries, and meanwhile, the undesired feasibility condition existing in other constrained controllers can be removed elegantly. Different from the existing static event-triggered mechanism, a dynamic event-triggered mechanism (DETM) is devised via constructing a novel dynamic function, so that the communication burden from the controller to actuator is further alleviated. Furthermore, with the aid of adaptive neural network (NN) technique and generalized first-order filter, together with Lyapunov theory, it is proved that the states of closed-loop system converge to small regions around zero with fixed-time convergence rate. The simulation results confirm the benefits of developed scheme.

Fully Distributed Event-Triggered Anti-Windup Consensus of Heterogeneous Systems With Input Saturation and an Active Leader.

This article addresses the event-based fully distributed consensus problem for linear heterogeneous multiagent systems (MASs) subject to input saturation. A leader with unknown but bounded control input is also considered. Based on an adaptive dynamic event-triggered protocol, all the agents can reach output consensus without knowing any global knowledge. Moreover, by applying a multiple-level saturation technique, the input-constrained leader-following consensus control is achieved. The given event-triggered algorithm can be utilized for the directed graph containing a spanning tree with the leader as the root. One distinct feature compared with previous works is that the proposed protocol can achieve saturated control without any a priori condition, instead, the local information is needed. Finally, the numerical simulations are illustrated to verify the performance of the proposed protocol.

Contrastive Multi-View Kernel Learning.

Kernel method is a proven technique in multi-view learning. It implicitly defines a Hilbert space where samples can be linearly separated. Most kernel-based multi-view learning algorithms compute a kernel function aggregating and compressing the views into a single kernel. However, existing approaches compute the kernels independently for each view. This ignores complementary information across views and thus may result in a bad kernel choice. In contrast, we propose the Contrastive Multi-view Kernel - a novel kernel function based on the emerging contrastive learning framework. The Contrastive Multi-view Kernel implicitly embeds the views into a joint semantic space where all of them resemble each other while promoting to learn diverse views. We validate the method's effectiveness in a large empirical study. It is worth noting that the proposed kernel functions share the types and parameters with traditional ones, making them fully compatible with existing kernel theory and application. On this basis, we also propose a contrastive multi-view clustering framework and instantiate it with multiple kernel k-means, achieving a promising performance. To the best of our knowledge, this is the first attempt to explore kernel generation in multi-view setting and the first approach to use contrastive learning for a multi-view kernel learning.

A Novel Robotic Pushing and Grasping Method Based on Vision Transformer and Convolution.

Robotic grasping techniques have been widely studied in recent years. However, it is always a challenging problem for robots to grasp in cluttered scenes. In this issue, objects are placed close to each other, and there is no space around for the robot to place the gripper, making it difficult to find a suitable grasping position. To solve this problem, this article proposes to use the combination of pushing and grasping (PG) actions to help grasp pose detection and robot grasping. We propose a pushing-grasping combined grasping network (GN), PG method based on transformer and convolution (PGTC). For the pushing action, we propose a vision transformer (ViT)-based object position prediction network pushing transformer network (PTNet), which can well capture the global and temporal features and can better predict the position of objects after pushing. To perform the grasping detection, we propose a cross dense fusion network (CDFNet), which can make full use of the RGB image and depth image, and fuse and refine them several times. Compared with previous networks, CDFNet is able to detect the optimal grasping position more accurately. Finally, we use the network for both simulation and actual UR3 robot grasping experiments and achieve SOTA performance. Video and dataset are available at https://youtu.be/Q58YE-Cc250.

Switched Model Predictive Control for Nonholonomic Mobile Robots Under Adaptive Dwell Time.

In this article, switched model predictive control (MPC) is proposed for nonholonomic mobile robots with adaptive dwell time and a dual-terminal set. The dual-terminal set is used to reduce on-line complexity of the switched MPC for the nonholonomic mobile robots with multiple constraints. By a switched signal with the adaptive dwell time, cost functions are switched to improve control performance under multiple constraints. The switched MPC with feasibility and stability can adjust a tradeoff between control performance and computational complexity for the closed-loop system. Simulation results are given to illustrate superiority of the switched MPC for nonholonomic mobile robots.

Physics-informed neural entangled-ladder network for inhalation impedance of the respiratory system.

BACKGROUND AND OBJECTIVES: The use of machine learning methods for modelling bio-systems is becoming prominent which can further improve bio-medical technologies. Physics-informed neural networks (PINNs) can embed the knowledge of physical laws that govern a system during the model training process. PINNs utilise differential equations in the model which traditionally used numerical methods that are computationally complex. METHODS: We integrate PINNs with an entangled ladder network for modelling respiratory systems by considering a lungs conduction zone to evaluate the respiratory impedance for different initial conditions. We evaluate the respiratory impedance for the inhalation phase of breathing for a symmetric model of the human lungs using entanglement and continued fractions. RESULTS: We obtain the impedance of the conduction zone of the lungs pulmonary airways using PINNs for nine different combinations of velocity and pressure of inhalation. We compare the results from PINNs with the finite element method using the mean absolute error and root mean square error. The results show that the impedance obtained with PINNs contrasts with the conventional forced oscillation test used for deducing the respiratory impedance. The results show similarity with the impedance plots for different respiratory diseases. CONCLUSION: We find a decrease in impedance when the velocity of breathing is lowered gradually by 20%. Hence, the methodology can be used to design smart ventilators to the improve flow of breathing.

Discrete-Time Control Barrier Function: High-Order Case and Adaptive Case.

This article proposes the novel concepts of the high-order discrete-time control barrier function (CBF) and adaptive discrete-time CBF. The high-order discrete-time CBF is used to guarantee forward invariance of a safe set for discrete-time systems of high relative degree. An optimization problem is then established unifying high-order discrete-time CBFs with discrete-time control Lyapunov functions to yield a safe controller. To improve the feasibility of such optimization problems, the adaptive discrete-time CBF is designed, which can relax constraints on system control input through time-varying penalty functions. The effectiveness of the proposed methods in dealing with high relative degree constraints and improving feasibility is verified on the discrete-time system of a three-link manipulator.

EMPC with adaptive APF of obstacle avoidance and trajectory tracking for autonomous electric vehicles.

In this paper, event-triggered model predictive control (EMPC) with adaptive artificial potential field (APF) is designed to realize obstacle avoidance and trajectory tracking for autonomous electric vehicles. An adaptive APF cost function is added to achieve obstacle avoidance and guarantee stability. The optimization problem for MPC is feasible by considering a special obstacle avoidance constraint. An event-triggered mechanism is proposed to reduce computational burden and ensure effectiveness of obstacle avoidance. Input and state constraints of autonomous electric vehicles are considered in both feasibility and stability by a robust terminal set. Effectiveness of both obstacle avoidance and trajectory tracking is shown by experimental results on autonomous electric vehicles.