A Neural Control Architecture for Joint-Drift-Free and Fault-Tolerant Redundant Robot Manipulators

Zhong, Nan; Li, Xuanzong; Yan, Ziyi; Zhang, Zhijun

doi:10.1109/access.2018.2878856

Cited by 6 publications

(17 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Li et al [22] designed and implemented a fault-tolerant motion planning scheme which can adaptively localize which joints run away from the normal state to be fault. A recurrent neural network (VP-RNN) with varying parameters was developed to resolve the fault-tolerant motion planning problem, which can make the remaining healthy joints to remedy the whole system which is effected by faulty joints and complete the expected end-effector path [23]. By taking both the robot kinematics and robot dynamics into account, a different-level simultaneous minimization scheme is proposed to solve fault-tolerant motion planning of redundant manipulator using a recurrent neural network [24].…”

Section: Related Workmentioning

confidence: 99%

A Discrete Model-Free Scheme for Fault-Tolerant Tracking Control of Redundant Manipulators

Tan

Zhong

et al. 2022

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

Fault tolerance is a critical requirement for robust motion control of redundant robotic manipulators. This task aims to endow the redundant manipulator with the capability to achieve the required path of end-effector in the condition that one or some of its joints' motion fail. Although many fault-tolerant control algorithms of redundant manipulator have been proposed in recent years. However, few of them are on the basis of the condition that the robotic model is unknown. The complexity of the calculation model limits the efficiency and portability of these algorithms. For the first time, we proposed a discrete model-free fault tolerant tracking control (DMFFTC) scheme of redundant manipulator, which takes into account the fault tolerance in the control system of redundant manipulator by formulating it into a quadratic programming (QP) framework. The core of the proposed scheme consists of a discrete kinematic estimator and a discrete QP solver, powered by which the fault-tolerant control problem is transformed into a unified computing problem relaxing the need of knowing the redundant manipulator's kinematic model. A discrete joint space observer is proposed for detection of the happening of faulty states. Extensive simulations and experiments based on a redundant manipulator are performed and analyzed to support the verification of the efficiency and effectiveness of the proposed scheme.

show abstract

Section: Related Workmentioning

confidence: 99%

A Discrete Model-Free Scheme for Fault-Tolerant Tracking Control of Redundant Manipulators

Tan

Zhong

et al. 2022

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

show abstract

“…The centroid of each joint of the multi-joint snake-like robot is located at the center of the joint x j , y j , and the coordinates of the links are x ∈ R N and y ∈ R N [29], [33]. The constraint conditions between links satisfy (1).…”

Section: Modeling Of a Multi-joint Snake-like Robot A Kinematicsmentioning

confidence: 99%

“…The robot has high flexibility, super convenience and redundancy. The robot can not only accomplish important tasks such as earthquake relief, fire extinguishing and war investigation in engineering, but provide experimental platform for people to study artificial intelligence, control theory and mechanical analysis in experiments [1], [2]. Therefore, the research of a multi-joint snake-like robot has important engineering application value and strategic significance [3], [4].…”

Section: Introductionmentioning

confidence: 99%

Motion Planning Algorithm of a Multi-Joint Snake-Like Robot Based on Improved Serpenoid Curve

Wang

Deng

et al. 2020

IEEE Access

View full text Add to dashboard Cite

In order to study the winding motion of a multi-joint snake-like robot with multi-degree of redundancy in plane, a motion planning algorithm of a multi-joint snake-like robot based on improved Serpenoid curve equation is proposed in this paper. Firstly, the kinematics and dynamics models of a multijoint snake-like robot are established, and the joint angle curve equation and the thrust expression of each joint of the robot relative to time are obtained. Next, the existing Serpenoid curve equation is improved to calculate the axial bending moment function with joint angle amplitude adjustment factor and turn angle adjustment factor. By analyzing the relationship between the forward thrust of the robot and the improved Serpenoid curve equation, a simple, efficient and reliable closed-loop control system was designed. Then, MATLAB and SimWise4D were used for simulation to obtain the motion trajectory of the robot based on the improved Serpenoid curve motion planning algorithm, and the influence of different parameters on the forward velocity of the multi-joint snake robot was analyzed. Finally, the validity of the motion planning algorithm of a multi-joint snake-like robot based on improved Serpenoid curve equation is verified by the actual experiment. INDEX TERMS Multi-joint snake-like robot, serpenoid curve, axial bending moment, closed-loop control.

show abstract

“…Theoretical analysis is undertaken to demonstrate the stability and convergence properties of the proposed scheme. Complexity analysis is also undertaken to demonstrate the computational efficiency of the proposed model as compared to leading alternative designs such as [14], [24]. Simulation and experimental studies are carried out with a KUKA LBR IIWA 14 R820 to show the efficacy of the proposed models for path tracking applications in redundant manipulators with bounds on the joint velocities.…”

Section: Introductionmentioning

confidence: 99%

“…The suitability of the proposed model for fault tolerant trajectory tracking is then demonstrated in simulation and experiments in the presence of multiple joint failures. Note that this approach differs from the previous approaches proposed for fault tolerance such as [24], in the sense that it incorporates limits on the state/input of the system. Further, the presence of prescribed performance constraints and the inclusion of formal guarantees for rigorous adhesion to bound constraint distinguishes it from the fault-tolerant approaches proposed in [25]- [27].…”

Section: Introductionmentioning

confidence: 99%

A Provably Constrained Neural Control Architecture With Prescribed Performance for Fault-Tolerant Redundant Manipulators

Singh

Keshavan

2022

IEEE Access

View full text Add to dashboard Cite

In this paper, a novel neural control architecture is proposed and investigated for resolving redundancy in trajectory tracking applications for manipulators with joint velocity constraints. First, a nonlinear invertible map is invoked to transform the constrained system state into a set of unconstrained variables, which allows the proposed framework to realize solutions that rigorously adhere to the specified bound constraints. Next, a quadratic program (QP) architecture is synthesized by incorporating suitably prescribed performance constraints to ensure that the resulting system error achieves exponential convergence to the ground truth while also ensuring that the system states evolve along trajectories with good transient and steady-state behavior. Thus, in contrast with previous approaches that do not rigorously guarantee the satisfaction of the bound constraint in the transient phase and/or steady-state, the proposed scheme ensures that these constraints are rigorously satisfied while achieving prescribed performance both during the transient phase and in the steady-state. The novelty of the proposed scheme lies in the fusion of prescribed performance constraints with the state and input constraints within the QP framework, which offers the important advantage of higher computational efficiency compared to leading alternative designs. A detailed theoretical analysis is undertaken to prove the global stability and convergence of the proposed scheme. Simulation and experimental results with the KUKA LBR IIWA 14 R820 manipulator are used to verify the efficacy of the proposed scheme in accomplishing trajectory tracking for the fault-free and faulttolerant cases with multiple joint failures. Finally, detailed performance comparison studies with leading alternative designs are further used to illustrate the advantages of the proposed scheme.

show abstract

A Neural Control Architecture for Joint-Drift-Free and Fault-Tolerant Redundant Robot Manipulators

Cited by 6 publications

References 26 publications

A Discrete Model-Free Scheme for Fault-Tolerant Tracking Control of Redundant Manipulators

A Discrete Model-Free Scheme for Fault-Tolerant Tracking Control of Redundant Manipulators

Motion Planning Algorithm of a Multi-Joint Snake-Like Robot Based on Improved Serpenoid Curve

A Provably Constrained Neural Control Architecture With Prescribed Performance for Fault-Tolerant Redundant Manipulators

Contact Info

Product

Resources

About