A Lagrangian network for kinematic control of redundant robot manipulators

Wang, Jun; Hu, Qingni; Jiang, Danchi

doi:10.1109/72.788651

Cited by 91 publications

(4 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The developed robot arm has a 7 DOF redundant structure. In this study, a Lagrangian network (Wang et al, 1999) was utilized to solve the inverse kinematics problem of this redundant arm with a modified weighting matrix, in which elements were adjusted based on the performance criteria for preventing joint limits and collision avoidance with robotic body. Figure 10 shows stills from a stroke motion video when a ball was served by a pitching machine.…”

Section: Resultsmentioning

confidence: 99%

Stroke Motion Learning for a Humanoid Robotic Ping-Pong Player Using a Novel Motion Capture System

Lai¹,

Tsay²

2010

Journal of Computer Science

View full text Add to dashboard Cite

Problem statement: Human ping-pong players determine the stroke trajectory according to their experience before the ball enters their court. However, to enable a humanoid robot to select the appropriate stroke motion based on skills learned from 3D motion, important patterns must be generated to simplify the complex 3D motion. Approach: This study developed an effective strategy for teaching ping-pong skills to a humanoid robot. An optical/inertial motion-capture system that retrieves the stroke motion was constructed, along with the retrieved stroke motion trajectories analyzed to obtain the desired stroke patterns of the robot. Results: A motion capture system was implemented mainly to orient the robot on the stroke motion trajectory. This system was applied directly to a ping-pong game between a human player and a pitching machine to enable the robot to learn backhand strokes through human demonstration. The ball was continuously struck to the opponent so that it hit the anticipated region on the opposite side of the court while the pitching machine served the ball. The data were then classified using the proposed stopping detector and then processed by Principal Components Analysis (PCA) to generate the stroke patterns after collecting 50 datasets for stroke trajectories. Conclusion: The right arm of the humanoid robot was successfully instructed to perform the actual ping-pong stroke using the generated trajectory.

show abstract

Section: Resultsmentioning

confidence: 99%

Stroke Motion Learning for a Humanoid Robotic Ping-Pong Player Using a Novel Motion Capture System

Lai¹,

Tsay²

2010

Journal of Computer Science

View full text Add to dashboard Cite

show abstract

“…Many special classes and branches of RNNs have been introduced and investigated for the robot kinematic as well as dynamic autonomy, e.g., the Lagrangian neural networks and the PDNNs. [151] In particular, Zhang et al [68] proposed a dual neural network (i.e., a special case of PDNNs) for the bi-criteria kinematics issue of robot manipulators. In order to eliminate discontinuity of minimum infinity-norm solutions, the kinematics control issue was reformulated as the bi-criteria of infinity and Euclidean norms in.…”

Section: Pdnn In Robot Autonomymentioning

confidence: 99%

A Review on Neural Dynamics for Robot Autonomy

Chen

2018

IJRC

View full text Add to dashboard Cite

Exploiting neural networks to solve control problems of robots is becoming commonly and effectively in academia and engineering. Due to the remarkable features like distributed storage, parallelism, easy implementation by hardware, adaptive self-learning capability, and free of off-line training, the solutions of neural networks break the bottlenecks of serial-processing strategies and methods, and serve as significant alternatives for robotic engineers and researchers. Especially, various types and branches of recurrent neural networks (RNNs) have been sequentially developed since the seminal works by Hopfield and Tank. Successively, many classes and branches of RNNs such as primal-dual neural networks (PDNNs), zeroing neural networks (ZNNs) and gradient neural networks (GNNs) are proposed, investigated, developed and applied to the robot autonomy. The objective of this paper is to present a comprehensive review of the research on neural networks (especially RNNs) for control problems solving of different kinds of robots. Specifically, the state-of-the-art research of RNNs, PDNNs, ZNNs and GNNs in different robot control problems solving are detailedly revisited and reported. The readers can readily find many effective and valuable solutions on the basis of neural networks for the robot autonomy in this paper.

show abstract

“…With the existence of at least one optimal solution x * ∈R n+1 , the QP problem (8)-(11) could be converted to the LVI problem (12).…”

Section: Theoremmentioning

confidence: 99%

“…The research of recent ten years shows that redundancy-resolution problems might be solved in a more favorable manner via online optimization techniques [4,7,8]. In addition, people resolve the redundancy problem mainly at the level of joint velocities by optimizing various performance criteria [6,[8][9][10][11][12][13][14][15][16][17][18][19]. The optimal control schemes at joint-velocity level could include infinity-norm velocity minimization (INVM) scheme [9-11, 13, 14], minimum velocity norm (MVN) scheme [12,18], minimum kinetic energy (MKE) scheme [7,20,21], bi-criteria velocity minimization scheme [4,10,16], repetitive motion planning scheme [4,8,17], and so on.…”

Section: Introductionmentioning

confidence: 99%

Bi‐criteria optimal control of redundant robot manipulators using LVI‐based primal‐dual neural network

Cai¹,

Zhang²

2009

Optim Control Appl Methods

View full text Add to dashboard Cite

In this paper, a bi-criteria weighting scheme is proposed for the optimal motion control of redundant robot manipulators. To diminish the discontinuity phenomenon of pure infinity-norm velocity minimization (INVM) scheme, the proposed bi-criteria redundancy-resolution scheme combines the minimum kinetic energy scheme and the INVM scheme via a weighting factor. Joint physical limits such as joint limits and joint-velocity limits could also be incorporated simultaneously into the scheme formulation. The optimal kinematic control scheme can be reformulated finally as a quadratic programming (QP) problem. As the real-time QP solver, a primal-dual neural network (PDNN) based on linear variational inequalities (LVI) is developed as well with a simple piecewise-linear structure and global exponential convergence to optimal solutions. Since the LVI-based PDNN is matrix-inversion free, it has higher computational efficiency in comparison with dual neural networks. Computer simulations performed based on the PUMA560 manipulator illustrate the validity and advantages of such a bi-criteria neural optimal motion-control scheme for redundant robots.

show abstract

A Lagrangian network for kinematic control of redundant robot manipulators

Cited by 91 publications

References 50 publications

Stroke Motion Learning for a Humanoid Robotic Ping-Pong Player Using a Novel Motion Capture System

Stroke Motion Learning for a Humanoid Robotic Ping-Pong Player Using a Novel Motion Capture System

A Review on Neural Dynamics for Robot Autonomy

Bi‐criteria optimal control of redundant robot manipulators using LVI‐based primal‐dual neural network

Contact Info

Product

Resources

About