Repetitive motion of redundant robots planned by three kinds of recurrent neural networks and illustrated with a four-link planar manipulator’s straight-line example

Zhang, Yunong; Tan, Zheng; Chen, Ke; Yang, Zhi; Lv, Xudong

doi:10.1016/j.robot.2009.01.002

Cited by 69 publications

(66 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To lay a basis for further discussion, some well-known essential equations for redundant robot arms can be given below directly [5] f (u) = r…”

Section: Aldf Inverse Kinematicsmentioning

confidence: 99%

“…The proof is thus completed. □ Based on the authors' previous work [5], the above ALDF scheme (5)-(7) of robot manipulators can be reformulated as the QP subject to an equality constraint as below minimise y T My/2 + s T y (9) subject to Cy = d…”

Section: Aldf Inverse Kinematicsmentioning

confidence: 99%

“…5 shows the joint-angle and joint-velocity profiles, which demonstrates that the final joint-angle and joint-velocity states of the robot manipulator that the manipulator's behaviour is hard to predict. In addition, it is less efficient to readjust the manipulator's configuration via self-motion [5].…”

Section: Simulation and Comparisonsmentioning

confidence: 99%

See 2 more Smart Citations

Design and experimentation of acceleration‐level drift‐free scheme aided by two recurrent neural networks

Zhang

2013

IET Control Theory & Applications

Self Cite

105

View full text Add to dashboard Cite

To solve the joint-angle and joint-velocity drift problems in cyclic motion of redundant robot manipulators, an acceleration-level drift-free (ALDF) scheme subject to a linear equality constraint is proposed, of which the effectiveness is analysed and proved via the theory of second-order system. The scheme is then reformulated into a quadratic program (QP). Furthermore, two recurrent neural networks (RNNs) are developed for solving the resultant QP problem. The first RNN solver is based on Zhang et al's neural-dynamic method and called Zhang neural network (ZNN), whereas the other is based on the gradient-descent method and called gradient neural network (GNN). Comparison results based on computer simulations between the ZNN and GNN solvers with a circular-path tracking task demonstrate that the ZNN solver has faster convergence and fewer errors. In addition, the hardware experiments of tracking a straight-line path and a rhombic path based on a six degrees of freedom manipulator validate the physical realisability and efficacy of the proposed ALDF scheme and the two RNN QP-solvers. Moreover, the position, velocity and acceleration error analyses indicate the accuracy of the proposed ALDF scheme and the corresponding RNN QP-solvers.

show abstract

“…To lay a basis for further discussion, some well-known essential equations for redundant robot arms can be given below directly [5] f (u) = r…”

Section: Aldf Inverse Kinematicsmentioning

confidence: 99%

Section: Aldf Inverse Kinematicsmentioning

confidence: 99%

See 1 more Smart Citation

Design and experimentation of acceleration‐level drift‐free scheme aided by two recurrent neural networks

Zhang

2013

IET Control Theory & Applications

Self Cite

105

View full text Add to dashboard Cite

show abstract

“…with x ∈ R m being the dual decision vector for equality constraint (16), and 0 being defined sufficiently large to replace +∞ for numerical implementation purposes. In addition, P (·) : R n+m → is a projection operator, with the ith element of P (y) defined as…”

Section: Plpe-based Numerical Algorithmmentioning

confidence: 99%

“…Inspired by successful application to fixed-platform redundant manipulators, 16, 18 a quadratic program (QP) method is presented and generalized for wheeled mobile redundant manipulators. Specifically, we propose and investigate a physical-limits-constrained (PLC) minimum velocity norm (MVN) coordinating scheme (termed as PLC-MVN-C scheme) to plan the motion trajectories of mobile redundant manipulators.…”

Section: Introductionmentioning

confidence: 99%

Physical-limits-constrained minimum velocity norm coordinating scheme for wheeled mobile redundant manipulators

Zhang

2014

Robotica

Self Cite

View full text Add to dashboard Cite

In order to resolve the redundancy of a wheeled mobile redundant manipulator comprising a twowheel-drive mobile platform and a 6-degree-of-freedom manipulator, a physical-limits-constrained (PLC) minimum velocity norm (MVN) coordinating scheme (termed as PLC-MVN-C scheme) is proposed and investigated. Such a scheme can not only coordinate the mobile platform and the manipulator to fulfill the end-effector task and to achieve the desired optimal index (i.e., minimizing the norm of the rotational velocities of the wheels and the joint velocities of the manipulator) but also consider the physical limits of the robot (i.e., the joint-angle limits and joint-velocity limits of the manipulator as well as the rotational velocity limits of the wheels). The scheme is then reformulated as a quadratic program (QP) subject to equality and bound constraints, and is solved by a discrete QP solver, i.e., a numerical algorithm based on piecewise-linear projection equations (PLPE). Simulation results substantiate the efficacy and accuracy of such a PLC-MVN-C scheme and the corresponding discrete PLPE-based QP solver.

show abstract

References

2017

Robot Manipulator Redundancy Resolution

View full text Add to dashboard Cite

Repetitive motion of redundant robots planned by three kinds of recurrent neural networks and illustrated with a four-link planar manipulator’s straight-line example

Cited by 69 publications

References 23 publications

Design and experimentation of acceleration‐level drift‐free scheme aided by two recurrent neural networks

Design and experimentation of acceleration‐level drift‐free scheme aided by two recurrent neural networks

Physical-limits-constrained minimum velocity norm coordinating scheme for wheeled mobile redundant manipulators

References

Contact Info

Product

Resources

About