The human wrist, a complex articulation of skeletal muscles and two-carpal rows, substantially contributes to improvements in maneuverability by agilely performing three-degree-of-freedom (3-DOF) orienting tasks and regulating stiffness according to variations in interaction forces. However, few soft robotic wrists simultaneously demonstrate dexterous 3-DOF motion and variable stiffness; in addition, they do not fully consider a soft-rigid hybrid structure of integrated muscles and two carpal rows. In this study, we developed a soft-rigid hybrid structure to design a biomimetic soft robotic wrist (BSRW) that is capable of rotating in the x and y directions, twisting around the z -axis, and possessing stiffness-tunable capacity. To actuate the BSRW, a lightweight soft-ring-reinforced bellows-type pneumatic actuator (SRBPA) with large axial, linear deformation ( η lcmax =70.6%, η lemax =54.3%) and small radial expansion ( η demax =3.7%) is designed to mimic the motion of skeletal muscles. To represent the function of two-carpal rows, a compact particle-jamming joint (PJJ) that combines particles with a membrane-covered ball-socket mechanism is developed to achieve various 3-DOF motions and high axial load-carrying capacity (>60 N). By varying the jamming pressure, the stiffness of the PJJ can be adjusted. Finally, a centrally positioned PJJ and six independently actuated SRBPAs, which are in an inclined and antagonistic arrangement, are sandwiched between two rigid plates to form a flexible, stable, and compact BSRW. Such a structure enables the BSRW to have a dexterous 3-DOF motion, high load-carrying ability, and stiffness tunability. Experimental analysis verify 3-DOF motion of BSRW, producing force of 29.6 N and 36 N and torque of 2.2 Nm in corresponding rotations. Moreover, the range of rotational angle and stiffness-tuning properties of BSRW are studied by applying jamming pressure to the PJJ. Finally, a system combining a BSRW and a soft enclosing gripper is proposed to demonstrate outstanding manipulation capability in potential applications.

In this paper, a continuously variable stiffness control strategy for shaft-hole assembly with a compliant wrist is proposed. The compliant wrist adjusts stiffness by changing the cantilever length of a super-elastic Ni-Ti wire. Its core idea is that when the contact force of the robot exceeds a particular value, the wrist adjusts the stiffness and can deform in a specific direction that guarantees assembly, allows a relatively significant misalignment, and produces a small force. The advantage of the proposed strategy is that the shaft-hole assembly status is supervised by calculating the deformation of compliant wrist based on contact force information, this significantly decrease the requirements of shaft-hole alignment accuracy. On this basis, the kinetostatic coupling kinematic and static force model is built and the fuzzy PD stiffness control strategy is designed to realize the desired stiffness of the wrist in various directions. Finally, the shaft-hole assembly experiments under different misalignment error demonstrates the reliability of the wrist, indicating the efficacy of the control method.

This paper presents a novel fuzzy-learning adaptive control approach for uncertain robotic systems with input dead zone and output saturation constraints. To address the input dead zone and output saturation and improve the control stability of the robot, an internal model compensation method was proposed, which utilizes online identification of an arctanh function to approximate the output saturation of actuators. The paper also introduces an adaptive learning control system based on a rules-reduced fuzzy neural network (RRFNN) algorithm, which considers the dead zone and output saturation function to enhance control performance, and an adaptive law driven by approximation mistakes is employed to handle multiple constraints. Furthermore, the controller utilizes the integral Lyapunov stability theorem and RRFNN to design the fuzzy-learning adaptive control law, ensuring global convergence and stability of the control system. Extensive simulations and experiments on a robotic manipulator are conducted to verify the feasibility of the proposed control method. Without the proposed method, the robot's joint tracking error exceeds 0.5 rad, while with the proposed controller, it is less than 0.05 rad and does not violate output saturation constraints. Thus, the proposed method can realize the desired performance and overcome multiple constraints.

An effective battery thermal management (BTM) strategy is very important for electric vehicles (EVs). In this paper, a robust predictive BTM strategy based on thermoelectric cooler (TEC) is proposed to adjust the battery temperature within an appropriate range and reduce energy consumption. Firstly, a modeling method of TEC based on thermal resistance is presented, which considers the influence of heat sink and fan on modeling effect. Next, a distributed battery thermal model is developed by using the difference method, which takes the tab thermal model as the first kind of boundary condition of the cell core. Then, a thermal management model is developed by combining the TEC model and distributed battery thermal model, and a neural network (NN) observer is proposed to compensate the model uncertainty. Finally, a nonlinear model predictive control (NMPC) method is proposed to optimize the cooling process. Genetic algorithm (GA) optimization is used to solve the nonlinear programming problem in NMPC method. Additional stability analysis shows the convergence of the proposed observer. Experiments and verifications suggest that the proposed method can accurately control the battery working near the target temperatures under four different cycles, and the errors are less than 0.5 degrees C.

The instability of the polishing force in the robot polishing process causes vibration of the polishing tool and degrades surface quality. Controlling vibration is essential for enhancing machining quality during high-precision polishing. This paper presents a magnetorheological (MR)-based polishing tool and vibration control method for improving the stability and reducing the vibration during machining. Firstly, a polishing end-effector with MR-based damper and magnetic spring mechanism is designed, the damping and stiffness model are built, the vibration dynamic model is established, and the vibration characteristics are theoretically analyzed. Multi-objective optimization is carried out to minimize the maximum frequency response value of polishing system. Then, a disturbance observer is designed to estimate the nonlinear cutting force and the stability is proved. To maintain normal contact force and reduce polishing tool vibration, a vibration controller based on polishing force with gravity compensation is proposed. The measured vibration amplitude and estimated cutting force are used as feedback in the controller to maintain the desired contact force. Finally, the polishing experiments are carried out to verify the feasibility of proposed strategy. The results show that the proposed method suppress the fluctuation of the polishing force and reduce vibration, the maximum vibration amplitude is reduced by 45% and the surface roughness is improved up 57.9%.

For a good soft gripper, it is desirable to have many grasping modes, variable stiffness and high load capacity in order to adapt to all sort of target objects. However, most of the existing soft grippers only have one grasping mode and are difficult to simultaneously possess variable stiffness and high load capacity. Here, a novel enclosing soft robotic gripper is designed to have two grasping modes, stiffness-tunable and high load capacity. This design includes two integrated closed annular structures, a contraction actuator in outside inner and a particle jamming package in inside inner. This contraction actuator is divided into four driving chambers and each chamber is inflated by an air compressor to produce gripping force. The particle jamming package is deflated by a vacuum pump to produce variable stiffness. In the contraction-based grasping mode, it can adapt to all sort of target objects (arbitrary shapes and rigidities) with a wide range of payloads (spanning from 2 g of a single-use plastic cup to 36.5 kg of weights). By designing a seal structure to produces the suction-based grasping mode under vacuum pressure, it enables the gripper to adsorb objects with flat surface and various weights (up to 16 kg).

Inchworm‐like robots have been increasingly investigated in recent years. However, most studies have focused on one or several locomotion modes, lacking in terms of inverted climbing, movement with a heavy load, and climbing a vertical plane. Herein, an inchworm‐like soft robot is actuated with multimodal locomotion using an acrylic stick‐constrained dielectric elastomer actuator (ASCDEA). By assembling the ASCDEA with a flexible support frame, a soft saddle‐like shape body is designed to provide the shape deformation ability for the robot. This design enables the robot to move under a heavy load. Two electroadhesion actuators are designed to implement the anchoring action. Additionally, a coordination control strategy is developed to synchronize the shape deformation and electroadhesion for multimodal locomotion. Experimental results confirm that the designed robot can move at a maximum velocity of 39.55 mm s −1 (0.53 body length s −1 ) on an inverted plane. Moreover, the robot is capable of multimodal locomotion, including inverted climbing, vertical climbing, horizontal crawling, turning locomotion, and rapid movement with a heavy load. The developed soft robot can navigate through a confined horizontal tunnel while carrying a payload, cross a gap, circumvent obstacles, and is particularly robust owing to its compliance.

This paper presents a fuzzy-learning adaptive control approach for robotic systems with uncertain dynamics and multiple constraints of actuators, including input dead zone and output saturation. To solve for dead-zone, an internal model compensation method is given, and online identification of an arctanh function is used to approximate output saturation. Using an adaptive learning system based on integral barrier Lyapunov function (IBLF) and rules-reduced fuzzy neural network (RRFNN) approaches, control performance is enhanced. We employ RRFNN to handle uncertainty and propose an adaptive law driven by approximation mistakes to correct for input dead zone and output saturation. In addition, the integral Lyapunov stability theorem and RRFNN are utilized to build the fuzzy-learning adaptive control approach, which is employed to compensate for the unknown dynamics and ensure global convergence and stability of the control system. According to the Lyapunov stability theory, it is demonstrated that all tracking errors converge to near-zero compact sets in a limited amount of time. Using a robot platform, the efficacy of the proposed controller is simulated and assessed; the results show that the output constraints are not violated and that the controller is capable of delivering high-precision tracking performance.

Controlling the manipulator is a big challenge due to its hysteresis, deadzone, saturation, and the disturbances of actuators. This study proposes a hybrid state/disturbance observer-based multiple-constraint control mechanism to address this difficulty. It first proposes a hybrid state/disturbance observer to simultaneously estimate the unmeasurable states and external disturbances. Based on this, a barrier Lyapunov function is proposed and implemented to handle output saturation constraints, and a back-stepping control method is developed to provide sufficient control performance under multiple constraints. Furthermore, the stability of the proposed controller is analyzed and proved. Finally, simulations and experiments are carried out on a 2-DOF and 6-DOF robot, respectively. The results show that the proposed control method can effectively achieve the desired control performance. Compared with several commonly used control methods and intelligent control methods, the proposed method shows superiority. Experiments on a 6-DOF robot verify that the proposed method has good tracking performance for all joints and does not violate constraints.

Here, a soft saddle-shaped dielectric elastomer actuator (SSDEA) is designed and a model-based tracking control approach is developed to achieve its desirable dynamics. In this actuator, a bent polyethylene terephthalate (PET) frame is connected with the dielectric elastomer (DE) driving mechanism. The DE driving mechanism induces PET frame elongation or shortening, which causes the movement of the SSDEA. With the benefit from its modular design, simple structure, and robust mechanical assembly, the SSDEA has the stable and linear driving capability. In order to describe the dynamic behaviors of this actuator, a hybrid modeling method that integrates a data-driven model with a physical model is presented, and a three-step identification method is proposed to obtain the model's parameters. Moreover, a model-based tracking control approach is further developed to achieve satisfactory control performance. Using experiments, the dynamics and control performance of the actuator are demonstrated effectively.

Accurate state-of-health (SOH) diagnosis and remaining useful life (RUL) prediction of lithium-ion batteries (LIBs) play an extremely important role in ensuring safe and reliable operation of electric and hybrid vehicles. However, due to the complex electrochemical properties, it is difficult to achieve the goal of accurate diagnosis and prediction. Here, we propose a novel data-model fusion method to perform accurate SOH estimation and RUL prediction for LIBs, which considers nonlinear dynamics of not only discharging process but also charging process. A long short-term memory (LSTM) network is first employed to model battery SOH dynamics. A neural network (NN) model is then developed to describe battery capacity degradation mechanism according to the prior knowledge extracted from the charging process. Finally, an unscented Kalman filter (UKF) algorithm is incorporated with the LSTM network and NN model to filter out the noises and further reduce the estimation errors. Different from the traditional model fusion approaches, this proposed method uses full information from all sensors, and with no need for any physical model. Experiments and verification demonstrate both the effectiveness of this proposed method and its superior modeling performance as compared with several commonly used methods.

The annelid, which consists of several identical segments, exploits its soft structures to move effectively in complex natural environments. Elongation and shortening of different segments produce a reverse peristaltic wave while retractable setae generate a variable friction, enabling bidirectional crawling locomotion. Although several designs have applied soft technologies towards the construction of annelid-like robots, these robots do not exhibit the homonymous segmentation, reverse peristaltic wave and variable friction. This paper reports the development of an annelid-like soft robot based on an improved dielectric elastomer (DE) minimum energy structure actuator to have these annelidan features. Each biomimetic segment of the robot is supported by a polyethylene terephthalate (PET) frame adhered to the DE actuator. The DE actuator induces segment elongation or shortening, which causes silica gel pads attached to the PET frame to contact or separate from the ground, producing a variable friction. The designed robot, whose identical segments conform to the homonymous segmentation, achieves forward or backward movement via the cooperative efforts of all the biomimetic segments. This cooperative movement, which produces the reverse peristaltic wave, strongly resembles that of natural annelidan locomotion. In addition, the kinematic analysis of the robot is investigated. Experimental results confirm that the designed robot is capable of bidirectional and rapid locomotion. The robot can achieve a maximum velocity of 11.5 mm s-1 and a maximum velocity/mass ratio of 86.25 mm (min-1 g-1). Compared to other existing annelid-like soft robots, this designed robot exhibits a superior average velocity, velocity/length ratio, body length/cycle, and velocity/mass ratio, and its performance affords the best approximation to that of the natural annelid.

The least squares support vector machine (LS-SVM) is often employed to model data with a nonlinear distribution using a divide-and-conquer strategy. However, when nonlinear data are contaminated by either noise or outliers, LS-SVM is often an ineffective approach due to a lack of robustness. In this paper, a collaborative learning-based clustered LS-SVM method is proposed for modeling of nonlinear processes that are subject to noise or outliers. First, a large-scale dataset is divided into several subsets and the data distribution of each subset is estimated. A robust LS-SVM is then developed to represent each subset using this distributional information. A global model is further constructed through integration of all submodels, whose continuity and smoothness are ensured by the development of the collaborative learning technique. As a result, the proposed method considers both the nonlinear distribution of data and the robustness of each submodel, and ensures the continuity and smoothness of the global model. Thus, it can effectively model nonlinear data that is subject to either noise or outliers. As further validation of this approach, both artificial and real cases demonstrated its effectiveness.

Dielectric elastomer actuators (DEA) have attracted increasing attention in the field of soft robotics for use in generating soft and compliant motions. However, owing to their strong viscoelasticity, nonlinearity, and uncertainty, it is often difficult to gain high-precision tracking control. Here, a physic-based and control-oriented modeling based robust control is proposed to alleviate this difficulty in tracking. First, a conical DEA is designed, along with a physics-based and control-oriented model used to describe its dynamic behaviors. After this, a two-step identification method is proposed to obtain the model’s parameters. Using the model, a robust control approach is then developed to achieve satisfactory control performance—even when tracking multi-frequency and wide-range reference trajectory under uncertain conditions. Its stability is then analyzed and proofed. Finally, we conduct experiments to demonstrate and test the effectiveness of the actuator.

Fuzzy modeling has been widely used to model lumped parameter systems. However, it cannot be used to model complex distributed parameter systems (DPS) due to its inability to handle spatial dynamics. In this paper, we propose a novel spatiotemporal fuzzy method for the modeling of complex nonlinear DPSs. A spatial fuzzy model is first constructed to represent the nonlinear spatial dynamics. This process ensures that the space information is inherently considered in the spatiotemporal fuzzy model. A fuzzy model is then used to represent the nonlinear temporal dynamics. These two fuzzy models are further integrated to construct a spatiotemporal fuzzy model, which allows for the reconstruction of the DPS. Additionally, it can improve the modeling robustness even in the presence of noise due to the robust ability of fuzzy modeling. Performance analyses and experimental validations further show that the proposed method can effectively model complex nonlinear DPSs and has the better modeling ability than several commonly used methods.

Real datasets are often distributed nonlinearly. Although many least squares support vector machine (LS-SVM) methods have successfully modeled this kind of data using a divide-and-conquer strategy, they are often ineffective when nonlinear data are subject to noise due to a lack of robustness within each sub-model. In this paper, a robust clustered LS-SVM is proposed to model this type of data. First, the clustering method is used to divide the sample data into several sub-datasets. A local robust LS-SVM model is then developed to capture the local dynamics of the corresponding sub-dataset and to be robust to noise. Subsequently, a global regularization is constructed to intelligently coordinate all local models. These new features ensure that the global model is smooth and continuous and has a good generalization and robustness. Through the use of both artificial and real cases, the effectiveness of the proposed robust clustered LS-SVM is demonstrated.