Multi-hierarchy interaction control of a redundant robot using impedance learning

Jiang, Yiming; Yang, Chenguang; Wang, Yaonan; Ju, Zhaojie; Li, Yanan; Su, Chun‐Yi

doi:10.1016/j.mechatronics.2020.102348

Cited by 21 publications

(6 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When the execution environment or robot model changes significantly, the resulting mapping function will be difficult to apply and will need to learn again [ 79 ]. Whereas the method of IRL is more task-related, the appropriate strategy can be obtained based on the previous reward function after receiving new information from the environment and the model [ 80 ]. Inverse reinforcement learning can be classified according to the algorithms it depends on.…”

Section: Imitation Learningmentioning

confidence: 99%

Learning for a Robot: Deep Reinforcement Learning, Imitation Learning, Transfer Learning

Jiang

Zeng

et al. 2021

Sensors

Self Cite

133

View full text Add to dashboard Cite

Dexterous manipulation of the robot is an important part of realizing intelligence, but manipulators can only perform simple tasks such as sorting and packing in a structured environment. In view of the existing problem, this paper presents a state-of-the-art survey on an intelligent robot with the capability of autonomous deciding and learning. The paper first reviews the main achievements and research of the robot, which were mainly based on the breakthrough of automatic control and hardware in mechanics. With the evolution of artificial intelligence, many pieces of research have made further progresses in adaptive and robust control. The survey reveals that the latest research in deep learning and reinforcement learning has paved the way for highly complex tasks to be performed by robots. Furthermore, deep reinforcement learning, imitation learning, and transfer learning in robot control are discussed in detail. Finally, major achievements based on these methods are summarized and analyzed thoroughly, and future research challenges are proposed.

show abstract

Section: Imitation Learningmentioning

confidence: 99%

Learning for a Robot: Deep Reinforcement Learning, Imitation Learning, Transfer Learning

Jiang

Zeng

et al. 2021

Sensors

Self Cite

133

View full text Add to dashboard Cite

show abstract

“…The identification results were as follows: Second, using the transfer functions (18) and (19), the parameters of the PID controllers were determined based on the approach presented in section 3. where (1) p K , (1) i K , and (1) d K are the parameters of the PID controller that controls the first link, and…”

Section: Numerical Simulationsmentioning

confidence: 99%

“…Then, the system was run to obtain the system outputs and to compare them to the desired inputs. During the simulation, the parameters of the simulations were set as follows: the sampling period was 0.01s, the network communication mode was CSMA/CD (Ethernet), the transmission rate was 80Kbit/s, the induced-network time delays were (1) 0.45s τ = and (2) 0.75s τ =…”

Section: Numerical Simulationsmentioning

confidence: 99%

“…The last one should be carefully pre-designed to ensure that the robot performs the required tasks with high degrees of precision, accuracy, and reliability. The problems inherent to the design of a good controller for a robot or part of it have beenand still are-the subject of active research (see [1][2][3][4][5][6][7][8][9][10][11][12] and references therein). A considerable volume of the research in the literature that relates to the control of robots or their parts is focused on the control of robot arms(see [13][14][15][16][17][18][19][20] and references therein).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Modeling and Networked Control of Two-rigid link Robot Arm

vall

2020

Wseas Transactions on Systems and Control

View full text Add to dashboard Cite

A networked control system (NCS) is one in which controller(s), actuator(s),and sensor(s)exchange command signals and data through a limited-bandwidth communication network that may be used by other applications, devices, and control systems. Compared to classical wired controlled systems, NCSs possess many advantages. In this paper, we propose the modeling and networked control of two-rigid link robot arm. To deal with the time delays that may occur during communication between the components of the system through the network, a model of the system was first determined, and second, PID controllers were designed based on the obtained model and using the stability region boundary locus technique. To demonstrate the validity of the proposed approach, numerical simulations were conducted using TrueTime, Simscape, SimMechanics, and Simulink with the MATLAB environment

show abstract

“…A lot of meaningful work on compliant control has been carried out, and two mainstream methods are hybrid position/force control and impedance control. (6)(7)(8)(9) Without considering the dynamic coupling between environment and robot, the accuracy of hybrid position/force control cannot be guaranteed. In contrast, impedance control aims to adjust the mechanical impedance to the target impedance, which has better robustness and safety.…”

Section: Introductionmentioning

confidence: 99%

Surface Electromyography (sEMG)-based Intention Recognition and Control Design for Human–Robot Interaction in Uncertain Environment

Gan¹,

Wang²,

Zuo³

2021

Sensors and Materials

View full text Add to dashboard Cite

An important direction of human-robot interaction (HRI) is making robots respond to complex and dexterous tasks intelligently. To achieve this, biological signals based on surface electromyography (sEMG) have widely been used to identify human intentions rapidly and effectively. We propose an algorithm that can recognize human intentions conveyed by different hand gestures through analyzing sEMG data. This will facilitate the selection of the most appropriate interaction mode and level during HRI for the robot. We also propose an admittance control framework combining a tan-type barrier Lyapunov function (BLF) and a radial basis function neural network (RBFNN) to ensure the interaction and tracking performance and to guarantee the stability of the system in uncertain environments. Experiments performed on a Baxter robot verify the effectiveness of the proposed framework.

show abstract

Multi-hierarchy interaction control of a redundant robot using impedance learning

Cited by 21 publications

References 47 publications

Learning for a Robot: Deep Reinforcement Learning, Imitation Learning, Transfer Learning

Learning for a Robot: Deep Reinforcement Learning, Imitation Learning, Transfer Learning

Modeling and Networked Control of Two-rigid link Robot Arm

Surface Electromyography (sEMG)-based Intention Recognition and Control Design for Human–Robot Interaction in Uncertain Environment

Contact Info

Product

Resources

About