A Learning-Based Stable Servo Control Strategy Using Broad Learning System Applied for Microrobotic Control

Motion control strategy for robotic arm using deep cascaded feature-enhancement Bayesian broad learning system with motion constraints

Intelligent control strategies can significantly enhance the efficiency of model parameter adjustment. However, existing intelligent motion control strategies for robotic arms based on the broad learning system lack sufficient accuracy and fail to account for the effects of joint motion limitations on overall control performance. To address the aforementioned challenges, this paper proposes a robotic arm motion control strategy based on a deep cascaded feature-enhanced Bayesian broad learning system with motion constraints (MC-DCBLS). Firstly, the motion control strategy based on a deep cascaded feature-enhanced Bayesian broad learning system (DCBBLS) is designed, which simplifies the modeling process and significantly improves control accuracy. Secondly, the motion constraint mechanism is introduced to optimize the control strategy to ensure that the robotic arm motion does not break through the physical limit. Finally, the parameter constraints of the control strategy network were obtained by introducing the Lyapunov theory to ensure the stability of the robotic arm motion control. The effectiveness of the proposed control strategy was validated through both simulations and physical experiments. The results demonstrated that the strategy significantly improved the accuracy of robotic arm motion control, with the root mean square error (RMSE) in position tracking reduced to 0.038 rad. This represents a 61.26% reduction in error compared to existing techniques.

Multifunctional Magnetic Catheter Robot with Triaxial Force Sensing Capability for Minimally Invasive Surgery

Magnetic continuum robots offer flexibility and controllability, making them promising for minimally invasive surgery (MIS). However, the clinical application of these robots is relatively limited due to the difficulty of integrating miniaturized triaxial force sensors and their single functionality. This paper proposes a multifunctional magnetic catheter robot with magnetic actuation steering and triaxial force-sensing capabilities. The robot features 3 channels at its tip that integrate multi-segmented magnets, a novel triaxial force sensor, and various functional instruments. The sensor is calibrated, demonstrating high sensitivity and accuracy. The steering characterization of the robot confirms that the catheter tip exhibits effective flexibility and force sensing. Palpation experiments involving various hard lumps are performed on porcine kidney, with results verifying that the robot can reliably detect abnormal hard lumps within tissues. Additionally, palpation experiments in bronchial phantom demonstrate the robot's imaging and palpation capabilities for lung nodules with an integrated endoscope. Further, the robot, equipped with biopsy forceps, successfully performs palpation and biopsy functions on simulated stomach polyps, demonstrating its capability for effective tissue manipulation. By leveraging force-sensing capabilities and integrating multifunctional instruments, the robot shows potential for expanded applications in MIS, paving the way for important advancements in clinical procedures.

Co-Training Broad Siamese-Like Network for Coupled-View Semi-Supervised Learning

Multiview semi-supervised learning is a popular research area in which people utilize cross-view knowledge to overcome the limitation of labeled data in semi-supervised learning. Existing methods mainly utilize deep neural network, which is relatively time-consuming due to the complex network structure and back propagation iterations. In this article, co-training broad Siamese-like network (Co-BSLN) is proposed for coupled-view semi-supervised classification. Co-BSLN learns knowledge from two-view data and can be used for multiview data with the help of feature concatenation. Different from existing deep learning methods, Co-BSLN utilizes a simple shallow network based on broad learning system (BLS) to simplify the network structure and reduce training time. It replaces back propagation iterations with a direct pseudo inverse calculation to further reduce time consumption. In Co-BSLN, different views of the same instance are considered as positive pairs due to cross-view consistency. Predictions of views in positive pairs are used to guide the training of each other through a direct logit vector mapping. Such a design is fast and effectively utilizes cross-view consistency to improve the accuracy of semi-supervised learning. Evaluation results demonstrate that Co-BSLN is able to improve accuracy and reduce training time on popular datasets.

Advanced Design of Soft Robots with Artificial Intelligence

A comprehensive review focused on the whole systems of the soft robotics with artificial intelligence, which can feel, think, react and interact with humans, is presented. The design strategies concerning about various aspects of the soft robotics, like component materials, device structures, prepared technologies, integrated method, and potential applications, are summarized. A broad outlook on the future considerations for the soft robots is proposed.

In recent years, breakthrough has been made in the field of artificial intelligence (AI), which has also revolutionized the industry of robotics. Soft robots featured with high-level safety, less weight, lower power consumption have always been one of the research hotspots. Recently, multifunctional sensors for perception of soft robotics have been rapidly developed, while more algorithms and models of machine learning with high accuracy have been optimized and proposed. Designs of soft robots with AI have also been advanced ranging from multimodal sensing, human–machine interaction to effective actuation in robotic systems. Nonetheless, comprehensive reviews concerning the new developments and strategies for the ingenious design of the soft robotic systems equipped with AI are rare. Here, the new development is systematically reviewed in the field of soft robots with AI. First, background and mechanisms of soft robotic systems are briefed, after which development focused on how to endow the soft robots with AI, including the aspects of feeling, thought and reaction, is illustrated. Next, applications of soft robots with AI are systematically summarized and discussed together with advanced strategies proposed for performance enhancement. Design thoughts for future intelligent soft robotics are pointed out. Finally, some perspectives are put forward.

AI-enhanced biomedical micro/nanorobots in microfluidics

Human beings encompass sophisticated microcirculation and microenvironments, incorporating a broad spectrum of microfluidic systems that adopt fundamental roles in orchestrating physiological mechanisms. In vitro recapitulation of human microenvironments based on lab-on-a-chip technology represents a critical paradigm to better understand the intricate mechanisms. Moreover, the advent of micro/nanorobotics provides brand new perspectives and dynamic tools for elucidating the complex process in microfluidics. Currently, artificial intelligence (AI) has endowed micro/nanorobots (MNRs) with unprecedented benefits, such as material synthesis, optimal design, fabrication, and swarm behavior. Using advanced AI algorithms, the motion control, environment perception, and swarm intelligence of MNRs in microfluidics are significantly enhanced. This emerging interdisciplinary research trend holds great potential to propel biomedical research to the forefront and make valuable contributions to human health. Herein, we initially introduce the AI algorithms integral to the development of MNRs. We briefly revisit the components, designs, and fabrication techniques adopted by robots in microfluidics with an emphasis on the application of AI. Then, we review the latest research pertinent to AI-enhanced MNRs, focusing on their motion control, sensing abilities, and intricate collective behavior in microfluidics. Furthermore, we spotlight biomedical domains that are already witnessing or will undergo game-changing evolution based on AI-enhanced MNRs. Finally, we identify the current challenges that hinder the practical use of the pioneering interdisciplinary technology.

A Wearable Upper Limb Exoskeleton System and Intelligent Control Strategy

Heavy lifting operations frequently lead to upper limb muscle fatigue and injury. In order to reduce muscle fatigue, auxiliary force for upper limbs can be provided. This paper presents the development and evaluation of a wearable upper limb exoskeleton (ULE) robot system. A flexible cable transmits auxiliary torque and is connected to the upper limb by bypassing the shoulder. Based on the K-nearest neighbors (KNN) algorithm and integrated fuzzy PID control strategy, the ULE identifies the handling posture and provides accurate active auxiliary force automatically. Overall, it has the quality of being light and easy to wear. In unassisted mode, the wearer's upper limbs minimally affect the range of movement. The KNN algorithm uses multi-dimensional motion information collected by the sensor, and the test accuracy is 94.59%. Brachioradialis muscle (BM), triceps brachii (TB), and biceps brachii (BB) electromyogram (EMG) signals were evaluated by 5 kg, 10 kg, and 15 kg weight conditions for five subjects, respectively, during lifting, holding, and squatting. Compared with the ULE without assistance and with assistance, the average peak values of EMG signals of BM, TB, and BB were reduced by 19-30% during the whole handling process, which verified that the developed ULE could provide practical assistance under different load conditions.

Double-Modal Locomotion of a Hydrogel Ultra-Soft Magnetic Miniature Robot with Switchable Forms

Flexible miniature robots are expected to enter difficult-to-reach areas in vivo to carry out targeted operations, attracting widespread attention. However, it is challenging for the existing soft miniature robots to substantially alter their stable shape once the structure is designed. This limitation leads to a fixed motion mode, which subsequently restricts their operating environment. In this study, we designed a biocompatible flexible miniature robot with a variable stable form that is capable of adapting to complex terrain environments through multiple movement modes. Inspired by the reversible stretching reaction of alginate saline gel stimulated by changes in environmental ion concentration, we manufactured a morphologically changeable super-soft hydrogel miniature robot body. According to the stretch and contraction shapes of the flexible hydrogel miniature robot, we designed magnetic fields for swing and rolling motion modes to realize multi-shape movement. The experimental results demonstrate that the deflection angle of the designed flexible miniature robot is reversible and can reach a maximum of 180°. The flexible miniature robot can complete forward swinging in the bar stretch state and tumbling motion in the spherical state. We anticipate that flexible hydrogel miniature robots with multiple morphologies and multimodal motion have great potential for biomedical applications in complex, unstructured, and enclosed living environments.

Micro/nanorobots for remediation of water resources and aquatic life

Nowadays, global water scarcity is becoming a pressing issue, and the discharge of various pollutants leads to the biological pollution of water bodies, which further leads to the poisoning of living organisms. Consequently, traditional water treatment methods are proving inadequate in addressing the growing demands of various industries. As an effective and eco-friendly water treatment method, micro/nanorobots is making significant advancements. Based on researches conducted between 2019 and 2023 in the field of water pollution using micro/nanorobots, this paper comprehensively reviews the development of micro/nanorobots in water pollution control from multiple perspectives, including propulsion methods, decontamination mechanisms, experimental techniques, and water monitoring. Furthermore, this paper highlights current challenges and provides insights into the future development of the industry, providing guidance on biological water pollution control.

A Robot Motion Learning Method Using Broad Learning System Verified by Small-Scale Fish-Like Robot

The widespread application of learning-based methods in robotics has allowed significant simplifications to controller design and parameter adjustment. In this article, robot motion is controlled with learning-based methods. A control policy using a broad learning system (BLS) for robot point-reaching motion is developed. A sample application based on a magnetic small-scale robotic system is designed without detailed mathematical modeling of the dynamic systems. The parameter constraints of the nodes in the BLS-based controller are derived based on Lyapunov theory. The design and control training processes for a small-scale magnetic fish motion are presented. Finally, the effectiveness of the proposed method is demonstrated by convergence of the artificial magnetic fish motion to the targeted area with the BLS trajectory, successfully avoiding obstacles.

A review on microrobots driven by optical and magnetic fields

Due to their small sizes, microrobots are advantageous for accessing hard-to-reach spaces for delivery and measurement. However, their small sizes also bring challenges in on-board powering, thus usually requiring actuation by external energy. Microrobots actuated by external energy have been applied to the fields of physics, biology, medical science, and engineering. Among these actuation sources, light and magnetic fields show advantages in high precision and high biocompatibility. This paper reviews the recent advances in the design, actuation, and applications of microrobots driven by light and magnetic fields. For light-driven microrobots, we summarized the uses of optical tweezers, optoelectronic tweezers, and heat-mediated optical manipulation techniques. For magnetically driven microrobots, we summarized the uses of torque-driven microrobots, force-driven microrobots, and shape-deformable microrobots. Then, we compared the two types of field-driven microrobots and reviewed their advantages and disadvantages. The paper concludes with an outlook for the joint use of optical and magnetic field actuation in microrobots.

Dynamic morphological transformations in soft architected materials via buckling instability encoded heterogeneous magnetization

The geometric reconfigurations in three-dimensional morphable structures have a wide range of applications in flexible electronic devices and smart systems with unusual mechanical, acoustic, and thermal properties. However, achieving the highly controllable anisotropic transformation and dynamic regulation of architected materials crossing different scales remains challenging. Herein, we develop a magnetic regulation approach that provides an enabling technology to achieve the controllable transformation of morphable structures and unveil their dynamic modulation mechanism as well as potential applications. With buckling instability encoded heterogeneous magnetization profiles inside soft architected materials, spatially and temporally programmed magnetic inputs drive the formation of a variety of anisotropic morphological transformations and dynamic geometric reconfiguration. The introduction of magnetic stimulation could help to predetermine the buckling states of soft architected materials, and enable the formation of definite and controllable buckling states without prolonged magnetic stimulation input. The dynamic modulations can be exploited to build systems with switchable fluidic properties and are demonstrated to achieve capabilities of fluidic manipulation, selective particle trapping, sensitivity-enhanced biomedical analysis, and soft robotics. The work provides new insights to harness the programmable and dynamic morphological transformation of soft architected materials and promises benefits in microfluidics, programmable metamaterials, and biomedical applications.

POMDP-Based Real-Time Path Planning for Manipulation of Multiple Microparticles via Optoelectronic Tweezers

With high throughput and high flexibility, optoelectronic tweezers (OETs) hold huge potential for massively parallel micromanipulation. However, the trajectory of the virtual electrode has been planned in advance in most synchronous manipulations for multiple targets based on an optically induced dielectrophoresis (ODEP) mechanism, which is insufficient to ensure the stability and efficiency in an environment with potential collision risk. In this paper, a synchronously discretized manipulation method based on a centralized and decoupled path planner is proposed for transporting microparticles of different types with an OET platform. An approach based on the Kuhn-Munkres algorithm is utilized to achieve the goal assignment between target microparticles and goal positions. With the assistance of a visual feedback module, a path planning approach based on the POMDP algorithm dynamically determines the motion strategies of the particle movement to avoid potential collisions. The geometrical parameters of the virtual electrodes are optimized for different types of particles with the goal of maximum transport speed. The experiments of micropatterning with different morphologies and transporting multiple microparticles (e.g., polystyrene microspheres and 3T3 cells) to goal positions are performed. These results demonstrate that the proposed manipulation method based on optoelectronic tweezers is effective for multicell transport and promises to be used in biomedical manipulation tasks with high flexibility and efficiency.

Hydrodynamic Modeling and Parameter Identification of a Bionic Underwater Vehicle: RobDact

In this paper, the hydrodynamic modeling and parameter identification of the RobDact, a bionic underwater vehicle inspired by Dactylopteridae, are carried out based on computational fluid dynamics (CFD) and force measurement experiment. Firstly, the paper briefly describes the RobDact, then establishes the kinematics model and rigid body dynamics model of the RobDact according to the hydrodynamic force and moment equations. Through CFD simulations, the hydrodynamic force of the RobDact at different speeds is obtained, and then, the hydrodynamic model parameters are identified. Furthermore, the measurement platform is developed to obtain the relationship between the thrust generated by the RobDact and the input fluctuation parameters. Finally, by combining the rigid body dynamics model and the fin thrust mapping model, the hydrodynamic model of the RobDact at different motion states is constructed.

Learning Human Strategies for Tuning Cavity Filters with Continuous Reinforcement Learning

Learning to master human intentions and behave more humanlike is an ultimate goal for autonomous agents. To achieve that, higher requirements for intelligence are imposed. In this work, we make an effort to study the autonomous learning mechanism to solve complicated human tasks. The tuning task of cavity filters is studied, which is a common task in the communication industry. It is not only time-consuming, but also depends on the knowledge of tuning technicians. We propose an automatic tuning framework for cavity filters based on Deep Deterministic Policy Gradient and design appropriate reward functions to accelerate training. Simulation experiments are carried out to verify the applicability of the algorithm. This method can not only automatically tune the detuned filter from random starting position to meet the design requirements under certain circumstances, but also realize the transfer of learning skills to new situations, to a certain extent.

A Review of Deep Learning in Multiscale Agricultural Sensing

Population growth, climate change, and the worldwide COVID-19 pandemic are imposing increasing pressure on global agricultural production. The challenge of increasing crop yield while ensuring sustainable development of environmentally friendly agriculture is a common issue throughout the world. Autonomous systems, sensing technologies, and artificial intelligence offer great opportunities to tackle this issue. In precision agriculture (PA), non-destructive and non-invasive remote and proximal sensing methods have been widely used to observe crops in visible and invisible spectra. Nowadays, the integration of high-performance imagery sensors (e.g., RGB, multispectral, hyperspectral, thermal, and SAR) and unmanned mobile platforms (e.g., satellites, UAVs, and terrestrial agricultural robots) are yielding a huge number of high-resolution farmland images, in which rich crop information is compressed. However, this has been accompanied by challenges, i.e., ways to swiftly and efficiently making full use of these images, and then, to perform fine crop management based on information-supported decision making. In the past few years, deep learning (DL) has shown great potential to reshape many industries because of its powerful capabilities of feature learning from massive datasets, and the agriculture industry is no exception. More and more agricultural scientists are paying attention to applications of deep learning in image-based farmland observations, such as land mapping, crop classification, biotic/abiotic stress monitoring, and yield prediction. To provide an update on these studies, we conducted a comprehensive investigation with a special emphasis on deep learning in multiscale agricultural remote and proximal sensing. Specifically, the applications of convolutional neural network-based supervised learning (CNN-SL), transfer learning (TL), and few-shot learning (FSL) in crop sensing at land, field, canopy, and leaf scales are the focus of this review. We hope that this work can act as a reference for the global agricultural community regarding DL in PA and can inspire deeper and broader research to promote the evolution of modern agriculture.