Neural Network Control of Space Manipulator Based on Dynamic Model and Disturbance Observer

He, Jiajia; Hu, Qi; Li, Yanhui; Wang, Kai; Zhu, Ming; Xu, Zhenbang

doi:10.1109/access.2019.2937908

Cited by 12 publications

(9 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The definitions of and are given in the sentence below (22). According to (30) and (31), It is clear that * . Therefore, the sliding variable * is outside the vicinity * , which means the set is not empty with 1 because * ∈…”

Section: B Stability Analysismentioning

confidence: 99%

“…Many algorithms have been proposed to cope with external disturbances and unmodelled nonlinearities, including neural networks (NN) [16][17][18][19][20][21][22][23], fuzzy logic approximators (FLA) [7,[24][25][26][27] and adaptive disturbance observers (ADO) [28][29][30][31][32]. Such algorithms have a stronger capability for motion control of FSRMs over control schemes [13][14][15] that can only handle parameter uncertainties.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A New Reinforcement Learning Based Adaptive Sliding Mode Control Scheme for Free-Floating Space Robotic Manipulator

Xie¹,

Sun²,

Kwan³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

This paper presents a new adaptive small chattering sliding mode control (SCSMC) scheme that uses reinforcement learning (RL) and time-delay estimation (TDE) for the motion control of free-floating space robotic manipulators (FSRM) subject to model uncertainty and external disturbance. The proposed sliding mode control scheme can achieve small chattering effects and improve the tracking accuracy by using a new adaptive law for the switching gain and a RL-based robust term to handle the control inputs. In SCSMC, the complicated multiple-input-multiple-output (MIMO) uncertain system of FSRM is transformed into multiple single-input-single-output (SISO) known subsystems with bounded estimation errors by the TDE technique and state feedback compensation. Subsequently, once the sliding variable is inside the designed manifold, the derivative of the switching gain for each subsystem becomes a negative hyperbolic tangent function of the associated sliding variable, which offers the ability to reduce chattering by decreasing the switching gain. Moreover, the RL based robust term for each subsystem is designed to avoid the loss of tracking accuracy caused by the aforementioned switching gain drop. The tracking errors are proven to be uniformly-ultimately-bounded (UUB) with an arbitrarily small bound by using the Lyapunov theory. The effectiveness of the proposed control scheme is verified by numerical simulations.

show abstract

Section: B Stability Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A New Reinforcement Learning Based Adaptive Sliding Mode Control Scheme for Free-Floating Space Robotic Manipulator

Xie¹,

Sun²,

Kwan³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…where y k denote the prediction of the missing observation vector, O k denote the prediction of state vector. According to (16), there is the covariance of an observation noise sequence R k between the observation and real value at k instant. Y k is not the real observation noise sequence, but it is the compensation noise, which approximates the real observation vector by introducing the covariance R k .…”

Section: B Computation Of the Forgetting Factormentioning

confidence: 99%

“…Such as in [15], for the tracking problem of the flexible joint manipulator, a composite observer is designed to estimate the fault and disturbance, and the sliding mode controller is designed for the fault-tolerant control. And as in [16], for the vibration of space manipulators for on-orbit service, neural network controller and disturbance are designed to suppress the influence of friction and dynamic coupling on joint control performance.…”

Section: Introductionmentioning

confidence: 99%

Dynamic Visual Tracking for Robot Manipulator Using Adaptive Fading Kalman Filter

Zhang

Tang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

This paper focuses on the problem of visual tracking of a moving target with the temporary occlusion of image feature, a dynamic visual tracking control system for robot manipulator is developed by using adaptive fading Kalman filter (AFKF). The estimation of the residual covariance is used to compute the forgetting factor to automatically adjust the weight of the image observation data for improving the visual state estimation accuracy. When the target features are occluded, the prediction of missing observation sequence are generated by using the predicted compensation noise and preorder observation sequence to determine the forgetting factor for estimating the missing visual states. Then, a parameter adaptive law with projection error compensation is designed to realize the visual tracking with uncertain camera parameters. Finally, the trajectory tracking experiments based on a real robot platform is carried out to verify the performance of the proposed state estimator and tracking controller. The results show that the proposed method can accurately realize the visual tracking with the occluded trajectory and inaccurate camera parameters, which improves the flexibility of dynamic visual tracking of robot manipulator. INDEX TERMS Visual tracking, robot manipulation, Kalman filter, occlusion.

show abstract

“…Besides, a hierarchical controller [15], [16] was utilized to do quadrupedal locomotion in Anymal [17] and MIT Cheetah [18], [19]. Neural Network-based method was also investigated to control robots and manipulators [20].…”

Section: Introductionmentioning

confidence: 99%

Virtual Model Control for Quadruped Robots

et al. 2020

View full text Add to dashboard Cite

Virtual model control is a motion control framework that uses virtual components to create virtual forces/torques, which are actually generated by joint actuators when the virtual components interact with robot systems. Firstly, this paper employs virtual model control to do a dynamic balance control of whole body of quadruped robots' trot gait in a bottom controller. In each leg, there exists a designed swing phase virtual model control and a stance phase counterparts. In the whole body, virtual model control is utilized to achieve a attitude control containing roll, pitch and yaw. In the attitude control, a forces/torques distribution method between two stance legs is pre-investigated. In a high-level implemented controller, an intuitive velocity control approach proposed by Raibert is applied for the locomotion of quadruped robots. Secondly, an anti-disturbance control, which contains compensating gravity, adjusting step length, adjusting swing trajectory, adjusting attitude, and adjusting virtual forces/torques, is investigated to improve the robustness, terrain adaptability, and dynamic balance performance of quadrupedal locomotion. Thirdly, a trajectory tracking control method based on an intuitive velocity control is addressed through considering four factors: terrain complexity index, curvature radius of given trajectory, distance to terminal, and maximum velocity of quadruped robots. Finally, simulations validate the effectiveness of proposed controllers.

show abstract

Neural Network Control of Space Manipulator Based on Dynamic Model and Disturbance Observer

Cited by 12 publications

References 51 publications

A New Reinforcement Learning Based Adaptive Sliding Mode Control Scheme for Free-Floating Space Robotic Manipulator

A New Reinforcement Learning Based Adaptive Sliding Mode Control Scheme for Free-Floating Space Robotic Manipulator

Dynamic Visual Tracking for Robot Manipulator Using Adaptive Fading Kalman Filter

Virtual Model Control for Quadruped Robots

Contact Info

Product

Resources

About