For parameter identifications of robot systems, most existing works have focused on the estimation veracity, but few literature are concerned with convergence speed. In this paper, we developed a control/identification scheme to identify unknown kinematic and dynamic parameters enhanced rate. Superior traditional methods, information error was properly integrated into proposed identification algorithm, such that performance achieved. Besides, Newton-Euler (NE) method used build model, where...

Robots with coordinated dual arms are able to perform more complicated tasks that a single manipulator could hardly achieve. However, rigorous motion precision is required guarantee effective cooperation between the arms, especially when they grasp common object. In this case, internal forces applied on object must also be considered in addition external forces. Therefore, prescribed tracking performance at both transient and steady states first specified, then, controller synthesized...

Mobile robots tracking a reference trajectory are constrained by the motion limits of their actuators, which impose requirement for high autonomy driving capabilities in robots. This paper presents model predictive control (MPC) scheme incorporating neural-dynamic optimization to achieve nonholonomic mobile (NMRs). By using derived tracking-error kinematics robots, proposed MPC approach is iteratively transformed as quadratic programming (QP) problem, and then primal-dual neural network used...

In this paper, a novel control scheme is developed for teleoperation system, combining the radial basis function (RBF) neural networks (NNs) and wave variable technique to simultaneously compensate effects caused by communication delays dynamics uncertainties. The system set up with TouchX joystick as master device simulated Baxter robot arm slave robot. haptic feedback provided human operator sense interaction force between environment when manipulating stylus of joystick. To utilize...

This paper proposes an enhanced robot skill learning system considering both motion generation and trajectory tracking. During demonstrations, dynamic movement primitives (DMPs) are used to model robotic motion. Each DMP consists of a set systems that enhances the stability generated toward goal. A Gaussian mixture regression integrated improve performance DMP, such more features can be extracted from multiple demonstrations. The learned scaled in space time. Besides, neural-network-based...

In this paper, automatic motion control is investigated for wheeled inverted pendulum (WIP) models, which have been widely applied modeling of a large range two modern vehicles. First, the underactuated WIP model decomposed into fully actuated second-order subsystem Σ <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">a</sub> consisting planar movement vehicle forward and yaw angular motions, passive (nonactuated) first-order...

This paper presents adaptive impedance control of an upper limb robotic exoskeleton using biological signals. First, we develop a reference musculoskeletal model the human and experimentally calibrate to match operator's motion behavior. Then, proposed novel algorithm transfers stiffness from operator through surface electromyography (sEMG) signals, being utilized design optimal model. Considering unknown deadzone effects in robot joints absence precise knowledge robot's dynamics, neural...

Due to strongly coupled nonlinearities of the grasped dual-arm robot and internal forces generated by objects, control with uncertain kinematics dynamics raises a challenging problem. In this paper, an adaptive fuzzy scheme is developed for robot, where approximate Jacobian matrix applied address kinematic control, while decentralized logic controller constructed compensate robotic arms manipulated object. Also, novel finite-time convergence parameter adaptation technique estimation...

Intelligent techniques foster the dissemination of new discoveries and novel technologies that advance ability robots to assist support humans. The human-centered intelligent robot has become an important research field spans all capabilities including navigation, control, pattern recognition human-robot interaction. This paper focuses on recent achievements presents a survey existing works robots. Furthermore, we provide comprehensive development discuss issues challenges in field.

In this paper, a physical human-robot interaction approach is presented for the developed robotic exoskeleton using admittance control to deal with human subject's intention as well unknown inertia masses and moments in dynamics. The represented by reference trajectory when complying external force. Online estimation of stiffness employed variable impedance property exoskeleton. Admittance first based on measured force order generate tasks. Then, adaptive proposed uncertain dynamics...

In this paper, we investigate fuzzy neural network (FNN) control using impedance learning for coordinated multiple constrained robots carrying a common object in the presence of unknown robotic dynamics and environment with which robot comes into contact. First, an FNN algorithm is developed to identify plant model. Second, introduced regulate input order improve environment-robot interaction, can track desired trajectory generated by learning. Third, light condition requiring move finite...

To perform power augmentation tasks of a robotic exoskeleton, this paper utilizes fuzzy approximation and designed disturbance observers to compensate for the torques caused by unknown input saturation, errors, viscous friction, gravity, payloads. The proposed adaptive control with updated parameters' mechanism additional torque inputs using are exerted into exoskeleton via feedforward loops counteract disturbances. Through such an approach, system does not need any requirement built-in...

In this article, an admittance-based controller for physical human-robot interaction (pHRI) is presented to perform the coordinated operation in constrained task space. An admittance model and a soft saturation function are employed generate differentiable reference trajectory ensure that end-effector motion of manipulator complies with human avoids collision surroundings. Then, adaptive neural network (NN) involving integral barrier Lyapunov (IBLF) designed deal tracking issues. Meanwhile,...

This paper describes a novel development of lower limber exoskeleton for physical assistance and rehabilitation. The developed is motorized leg device having total 4 DOF with hip, knee, ankle actuated in the sagittal plane. applies forces learns impedance parameters both robot human. An adaptive control scheme by incorporating learning approaches into system to help movement on desired periodic trajectory handle uncertainties known periods. proposed approach does not require muscle model can...

This article discusses the control design and experiment validation of a flexible two-link manipulator (FTLM) system represented by ordinary differential equations (ODEs). A reinforcement learning (RL) strategy is developed that based on actor–critic structure to enable vibration suppression while retaining trajectory tracking. Subsequently, closed-loop with proposed RL algorithm proved be semi-global uniform ultimate bounded (SGUUB) Lyapunov's direct method. In simulations, approach...

Although great progress has been made in generic object detection by advanced deep learning techniques, detecting small objects from images is still a difficult and challenging problem the field of computer vision due to limited size, less appearance, geometry cues, lack large-scale datasets targets. Improving performance wider significance many real-world applications, such as self-driving cars, unmanned aerial vehicles, robotics. In this article, first-ever survey recent studies...

This paper studies the optimal distribution of feet forces and control multilegged robots with uncertainties in both kinematics dynamics. First, a constrained dynamics for environment model are established by considering kinematic dynamic uncertainties. Under an external wrench robots, foot moments supporting legs can be formulated as quadratic programming problems subject to linear nonlinear constraints. The neurodynamics recurrent neural network is developed force optimization. For...

It has been established that the transfer of human adaptive impedance is great significance for physical human-robot interaction (pHRI). By processing electromyography (EMG) signals collected from muscles, limb could be extracted and transferred to robots. The existing interfaces rely only on visual feedback and, thus, may insufficient skill in a sophisticated environment. In this paper, haptic mechanism introduced result muscle activity would generate EMG natural manner, order achieve...

An adaptive neural control strategy for multiple input output nonlinear systems with various constraints is presented in this paper. To deal the nonsymmetric nonlinearity and constrained states, proposed combined backstepping method, radial basis function network, barrier Lyapunov (BLF), disturbance observer. By ensuring boundedness of BLF closed-loop system, it demonstrated that tracking achieved all states remaining constraint sets general assumption on nonsingularity unknown coefficient...

Touch-free guided hand gesture recognition for human-robot interactions plays an increasingly significant role in teleoperated surgical robot systems. Indeed, despite depth cameras provide more practical information accuracy enhancement, the instability and computational burden of data represent a tricky problem. In this letter, we propose novel multi-sensor system teleoperation. A fusion model is designed performing interference presence occlusions. multilayer Recurrent Neural Network (RNN)...

In this paper, two upper limbs of an exoskeleton robot are operated within a constrained region the operational space with unidentified intention human operator's motion as well uncertain dynamics including physical limits. The new human-cooperative strategies developed to detect subject's movement efforts in order make behavior flexible and adaptive. extracted from measurement muscular effort terms applied forces/torques can be represented derive reference trajectory his/her limb using...

One promising approach for robots efficiently learning skills is to learn manipulation from human tutors by demonstration and then generalize these learned complete new tasks. Traditional generalization methods, however, have not well considered impedance features, which makes the less humanlike restricted in physical human-robot interaction scenarios. In particular, stiffness has been considered. This paper develops a framework that enables robot both movement features tutor. To this end,...

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

In this paper, a novel high-order disturbance observer (HODO) for the mobile wheeled inverted pendulum (MWIP) system is first proposed. Based on choice method of optimal gain matrices, estimation accuracy HODO can be improved. Combining proposed and sliding mode control (SMC), new strategy designed balance speed MWIP system. The boundness error proved stability closed-loop achieved through appropriate selection surface coefficients. effectiveness all methods verified by experiments real

In this paper, an adaptive neural bounded control scheme is proposed for ${n}$ -link rigid robotic manipulator with unknown dynamics. With the combination of approximation and backstepping technique, network policy developed to guarantee tracking performance robot. Different from existing results, bounds designed controller are known a priori, they determined by gains, making them applicable within actuator limitations. Furthermore, also able compensate effect Via Lyapunov stability theory,...