Intelligent controller for hybrid force and position control of robot manipulators using RBF neural network

Rani, Komal; Kumar, Naveen

doi:10.1007/s40435-018-0487-y

Cited by 20 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The algorithm of traditional RBF neural network can be expressed by the following formula (Rani and Kumar, 2019)…”

Section: Design Of the Mrbf Controllermentioning

confidence: 99%

“…This will bring great difficulties to the design of its controller (Ajwad et al, 2018; Han et al, 2021; He et al, 2015; Hong et al, 2020; Liu et al, 2019). It has been noted (Baumann et al, 2018) that the radial basis function (RBF) neural network has good generalization ability, and can effectively improve the performance of the controller when the system has a large uncertainty (Baumann et al, 2018; Cheng and Liu, 2020; Gambuzza et al, 2017; Gao et al, 2018; Jin et al, 2021; Kvatinsky et al, 2012; Rani and Kumar, 2019; Wang et al, 2019). However, with the continuous advancement of technology, the robotic manipulator control is required to become more and more intelligent.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Design of the MVT RBF neural network robotic manipulator control system based on model block approximation

Xiaoliang

Liu

2022

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

Due to the uncertain dynamic characteristics, the requirements for robotic manipulator control are increasingly complex. The traditional radial basis function (RBF) neural network has a good generalization ability, but its redundant and tedious training process cannot meet the “Intelligent” control requirement of robotic manipulator. This study designs a new valve-regulated memristive RBF neural network, which adopts the model block approximation control strategy to estimate the three coefficient matrices of the robotic manipulator and uses the memristor with voltage threshold (MVT) as an electronic synapse to provide connections between neurons for the neural network and store information. This study adopts the design idea of software hardening and replaces the updated neural network weight with the change of the memristance value in the MVT network (crossed array), which can effectively improve the control performance of the traditional RBF neural network and can also provide analytical data for the fault detection of the subsequent control system. A simulation analysis is conducted with a single-joint robotic manipulator as the control object, and the results verify the rationality and feasibility of the proposed control algorithm.

show abstract

“…The algorithm of traditional RBF neural network can be expressed by the following formula (Rani and Kumar, 2019)…”

Section: Design Of the Mrbf Controllermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Design of the MVT RBF neural network robotic manipulator control system based on model block approximation

Xiaoliang

Liu

2022

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

show abstract

“…Industrial robots have the characteristics of weak stiffness, complex stress and strong coupling, it is difficult to control contact force. Therefore, compliance control technology of robot machining has always been a focus in this field [11][12][13].…”

Section: Introductionmentioning

confidence: 99%

Study on robot automatic rounding for blade tip based on elastic grinding

Tian,

Qi,

Zhang

et al. 2024

Int J Adv Manuf Technol

View full text Add to dashboard Cite

In order to achieve automatic rounding for blade tip, the study was conducted on small radius rounding based on elastic grinding, and a method of robot automatic grinding for small radius fillets of blade tip was proposed.The elastic grinding wheel with polyester ammonia fiber as substrate material is utilized the characteristics of elastic envelope deformation contact to grind sharp angles of blade tip to small radius fillets. Based on elastic contact theory and Preston equation, theoretical contact model and material removal model between grinding wheel and blade tip were established. Abaqus software was used to simulate and analyze the contact stress distribution and grinding removal amount. Simulation result demonstrates that the adaptive elastic contact deformation between grinding wheel and sharp angle of blade tip forms small surface envelope contact pattern and variable grinding removal amount, which can realize small radius fillet machining. Robot automatic rounding experiments for blade tip were conducted to verify feasibility and controllability of the machining method. The research results indicate that the elastic deformation of grinding wheel causes an arc-shaped contact stress distribution in the contact area of blade tip and abrasive coated on the substrate can achieve small radius fillet grinding. The combination of passive compliance formed by elastic grinding deformation and active force control is feasible to realize robot automatic rounding for small radius fillets, and the fillet radius can be controlled by changing grinding process parameters. Robot automatic rounding for blade tip is feasible, and machining process and accuracy are controllable and stable, which breaks through the traditional manual sandpaper grinding method and provides a new small radius fillet processing method.

show abstract

“…Since there is only one hidden layer, it has good global approximation ability, strong robustness, high memory ability, superior nonlinear mapping ability and self-learning ability. Therefore, it has attracted the attention of many scholars [13][14][15][16][17][18]. In order to achieve accurate force/posture control for on-orbit insertion and extraction of space robots, an adaptive RBFNN impedance control strategy is proposed by combining RBFNN and impedance control principles.…”

Section: Introductionmentioning

confidence: 99%

Space Robot On-Orbit Operation of Insertion and Extraction Impedance Control Based on Adaptive Neural Network

Liu

Chen

2023

Aerospace

View full text Add to dashboard Cite

The on-orbit operation of insertion and extraction of space robots is a technology essential to the assembly and maintenance in orbit, satellite fuel filling, failed satellite recovery, especially modular in-orbit assembly of micro-spacecraft. Therefore, the force/posture impedance control for the on-orbit operation of insertion and extraction is studied. Firstly, the dynamic model of space robots’ system in the form of uncontrolled carrier position and controlled attitude is derived by using the momentum conservation principle. Through the kinematic constraints of the replacement component plug, the Jacobi relationship of the plug motion in the base coordinate system is established. Secondly, to achieve the output force control of the plug during the on-orbit operation of insertion and extraction, a second-order linear impedance model is established based on the dynamic relationship between the plug posture and its output force and the impedance control principle. Then, in order to improve the stability, robustness, and adaptability of the controller, an adaptive Radial Basis Function Neural Network (RBFNN) is used to approximate the uncertainties in the dynamic model for the force/posture control of the plug. Finally, the stability of the system is verified by the Lyapunov principle. The simulation results show that the designed neural network impedance control strategy can achieve a control accuracy of less than 10−3 rad for the plug’s attitude tracking error, less than 10−3 m for its position tracking error, and less than 0.5 N for its output force tracking error.

show abstract

Intelligent controller for hybrid force and position control of robot manipulators using RBF neural network

Cited by 20 publications

References 19 publications

Design of the MVT RBF neural network robotic manipulator control system based on model block approximation

Design of the MVT RBF neural network robotic manipulator control system based on model block approximation

Study on robot automatic rounding for blade tip based on elastic grinding

Space Robot On-Orbit Operation of Insertion and Extraction Impedance Control Based on Adaptive Neural Network

Contact Info

Product

Resources

About