Cooperative Game-Based Approximate Optimal Control of Modular Robot Manipulators for Human-Robot Collaboration.

This article attempts to review papers on power assist rehabilitation robots, human motion intention, control laws, and estimation of power assist rehabilitation robots based on human motion intention in recent years. This paper presents the various ways in which human motion intention in rehabilitation can be estimated. This paper also elaborates on the control laws for the estimation of motion intention of the power assist rehabilitation robot. From the review, it has been found that the motion intention estimation method includes: Artificial Intelligence-based motion intention and Model-based motion intention estimation. The controllers include hybrid force/position control, EMG control, and adaptive control. Furthermore, Artificial Intelligence based motion intention estimation can be subdivided into Electromyography (EMG), Surface Electromyography (SEMG), Extreme Learning Machine (ELM), and Electromyography-based Admittance Control (EAC). Also, Model-based motion intention estimation can be subdivided into Impedance and Admittance control interaction. Having reviewed several papers, EAC and ELM are proposed for efficient motion intention estimation under artificial-based motion intention. In future works, Impedance and Admittance control methods are suggested under model-based motion intention for efficient estimation of motion intention of power assist rehabilitation robot. In addition, hybrid force/position control and adaptive control are suggested for the selection of control laws. The findings of this review paper can be used for developing an efficient power assist rehabilitation robot with motion intention to aid people with lower or upper limb impairment.

This paper presents a nonzero-sum strategy-based neuro-optimal control method for modular robot manipulators (MRMs). Based on joint torque feedback (JTF) technique, the dynamic model of the manipulator systems is described as an integration of joint subsystems. A local dynamic information-based robust compensator is designed to engage the model uncertainty compensation, and then, the optimal tracking control problem of an MRM system is transformed into an n-player nonzero-sum game issue of multiple joint subsystems. By taking advantage of the adaptive dynamic programming (ADP) algorithm, a cost function approximator is developed for solving the Hamilton- Jacobi (HJ) equation, thus facilitating the feasible derivation of the neuro-optimal control policy. Finally, experiment results illustrated the effectiveness of the developed control method.

Estimation of human impedance and motion intention for constrained human–robot interaction

In this paper, a finite-horizon ε-optimal control for a class of nonlinear systems with state delay is proposed by Adaptive Dynamic Programming (ADP) algorithm. First of all, the performance index function is defined and the Hamilton-Jacobi-Bellman (HJB) equation is obtained for the problem, the convergence of the iterative algorithm is also presented. Then, ADP algorithm for finite-horizon optimal control is introduced with an ε-error bound so as to get the ε-optimal control, and BP neural network is used to implement ADP algorithm. At last, an example is given to demonstrate the effectiveness of the proposed algorithm.

An electromyography signals-based human-robot collaboration system for human motion intention recognition and realization

In this paper, an on-line adaptive dynamic programming (ADP) algorithm is presented to solve the optimal control problem for continuous-time nonlinear systems with control constraints. First, a suitable non-quadratic performance function is introduced to confront control constraints, and then we present an on-line ADP algorithm in which dynamic programming techniques and neural networks are used to solve the optimal control problem for nonlinear systems with control constraints, which is completely different with the traditional ADP algorithm using off-line training, and the corresponding convergence proof is given. Finally, a simulation examples is given to demonstrate the convergence and feasibility of the proposed algorithm.

Optimal control of Markovian jump systems via a neural network-based ADP iterative algorithm

This paper studies the problem of optimal parallel tracking control for continuous-time general nonlinear systems. Unlike existing optimal state feedback control, the control input of the optimal parallel control is introduced into the feedback system. However, due to the introduction of control input into the feedback system, the optimal state feedback control methods can not be applied directly. To address this problem, an augmented system and an augmented performance index function are proposed firstly. Thus, the general nonlinear system is transformed into an affine nonlinear system. The difference between the optimal parallel control and the optimal state feedback control is analyzed theoretically. It is proven that the optimal parallel control with the augmented performance index function can be seen as the suboptimal state feedback control with the traditional performance index function. Moreover, an adaptive dynamic programming ( ADP ) technique is utilized to implement the optimal parallel tracking control using a critic neural network ( NN ) to approximate the value function online. The stability analysis of the closed-loop system is performed using the Lyapunov theory, and the tracking error and NN weights errors are uniformly ultimately bounded ( UUB ) . Also, the optimal parallel controller guarantees the continuity of the control input under the circumstance that there are finite jump discontinuities in the reference signals. Finally, the effectiveness of the developed optimal parallel control method is verified in two cases.

This paper studies the problem of event-triggered optimal control (ETOC) for continuous-time nonlinear systems and proposes a novel event-triggering condition that enables designing ETOC methods directly based on the solution of the Hamilton-Jacobi-Bellman (HJB) equation. We provide formal performance guarantees by proving a predetermined upper bound. Moreover, we also prove the existence of a lower bound for interexecution time. For implementation purposes, an adaptive dynamic programming (ADP) method is developed to realize the ETOC using a critic neural network (NN) to approximate the value function of the HJB equation. Subsequently, we prove that semiglobal uniform ultimate boundedness can be guaranteed for states and NN weight errors with the ADP-based ETOC. Simulation results demonstrate the effectiveness of the developed ADP-based ETOC method.

This paper investigates a novel fault tolerant control (FTC) scheme for reconfigurable manipulators with actuator failures based on adaptive dynamic programming (ADP) with an improved performance index function. With the help of fault observer, the estimated actuator failure is utilized to construct the performance index function that reflects the failure, regulation and control simultaneously. The fault tolerant controller consists of the desired controller and the approximated optimal feedback one. The desired controller is obtained by the system model directly. By establishing a critic neural network, the policy iteration (PI) algorithm is utilized to solve the Hamilton-Jacobi-Bellman (HJB) equation, and then the approximated optimal feedback controller can be derived directly. It is proven that the closed-loop system is uniformly ultimately bounded (UUB) based on Lyapunov stability theorem. Finally, the simulation study is given to show the effectiveness of the proposed FTC scheme.

In human–robot collaboration (HRC) scenarios with direct physical contact, accurately estimating human intentions and adjusting robot behaviors based on multimodal information is the core factors that restrict the efficiency and precision of current HRC tasks. To enhance the performance of human–robot collaboration under physical contact conditions, we propose a joint network model named ACT_force_cooperative (AFC). This model leverages force sensing information as a representation of human intent to achieve human intent prediction during physical interaction, while simultaneously capturing visual information and robot state data, thereby enabling more efficient execution of human–robot collaborative tasks with multimodal information processing. Existing HRC methods often ignore humans’ collaborative experience in the environment and fail to recognize the uniqueness of interactive force in expressing human intentions. Focusing on the special role of interactive force among various types of data in physical interaction environments, the proposed model predicts humans’ future behavioral intentions and adopts a Transformer model to realize the fusion and representation of multimodal information, thus accomplishing more accurate and effective HRC tasks. Experimental results demonstrate that, through the processing of force sensing information and fusion of multimodal data, the proposed model reduces the motion error by 44.9% and increases the effective collaborative time ratio by 20.2% compared with the baseline Action Chunk Transformer (ACT) model. This not only improves the motion accuracy of the robot in collaborative tasks but also enhances the collaborative experience of human operators.

In this paper, an optimal tracking control approach based on adaptive dynamic programming (ADP) algorithm is proposed to solve the linear quadratic regulation (LQR) problems for unknown discrete-time systems in an online fashion. First, we convert the optimal tracking problem into designing infinite-horizon optimal regulator for the tracking error dynamics based on the system transformation. Then we expand the error state equation by the history data of control and state. The iterative ADP algorithm of policy iteration (PI) and value iteration (VI) are introduced to solve the value function of the controlled system. It is shown that the proposed ADP algorithm solves the LQR without requiring any knowledge of the system dynamics. The simulation results show the convergence and effectiveness of the proposed control scheme.

In this paper, machine learning methods are proposed for human intention estimation based on the change of force distribution on the interaction surface during human-robot collaboration (HRC). The force distribution under different human intentions are examined when the human and robot are jointly carrying the same piece of object. A pair of Robotiq tactile sensors is applied to monitor the change of force distribution on the interaction surface. Three machine learning algorithms are tested on recognition of human intentions based on the force distribution patterns on the contact surface of grippers for the manipulator. The K-nearest Neighbor model is selected to build a real-time framework, which includes human intention estimation and cooperative motion planning for the robot manipulator. A real-time experiment is conducted to validate the method, which suggests the human intention estimation approach can help enhance the efficiency of HRC.

This paper presents a decentralized robust control of modular robot manipulators (MRMs) with harmonic drive transmission using redundant adaptive robust extended Kalman filter (RARKF)-based joint torque estimation. The dynamic model of MRMs is formulated via RARKF-based joint torque estimation method. A decentralized robust control is developed to guarantee the trajectory tracking error is uniform ultimate bounded (UUB). The closed-loop robotic system is asymptotic stability on the basis of Lyapunov verification. The experiments are performed to clarify the effectiveness of the proposed method.

In this paper, an event-triggered adaptive dynamic programming (ADP) algorithm is developed to solve the two-player zero-sum game problem of continuous-time nonlinear systems. First, a critic neural network is employed to approximate the optimal value function. Then, an event-triggered ADP method is proposed, which guarantees the stability of the closed-loop system. The developed method can save the amount of computation as the control law and disturbance law that update only when the pre-designed triggering condition is violated. Finally, its effectiveness is verified through simulation results.