Examples of Planar Multilink Manipulators
In Chaps. 2 and 3, we have theoretically demonstrated the effectiveness of such a physically constrained RMP scheme (and its solvers) on solving the joint-angle drift problem. In this chapter, a dual neural network (introduced in Chap. 4) and an LVI-based primal–dual neural network (introduced in Chap. 5) are presented for online repetitive motion planning (RMP) of redundant robot manipulators (with multilink planar manipulators as examples). As real-time QP solvers, the aforementioned two kinds of neural networks both have piecewise-linear dynamics and can globally exponentially converge to the optimal solution of strictly-convex quadratic programs. Furthermore, the neural-network-based physically constrained RMP scheme is simulated based on the multilink planar robot manipulators. Computer-simulation results substantiate the theoretical analysis and also show the effective remedy of the joint-angle drift problem of robot manipulators.
- 1.Zhang Y, Li X, Zhu H, Tan N (2009) Joint-angle-drift remedy of three-link planar robot arm performing different types of end-effector trajectories. In: Proceedings of IEEE international conference on intelligent computing and intelligent systems, pp 581–585 Google Scholar
- 2.Chen K, Zhang L, Zhang Y (2008) Cyclic motion generation of multi-link planar robot performing square end-effector trajectory analyzed via gradient-descent and Zhang et al’s neural-dynamic methods. In: Proceedings of the 2nd international symposium on systems and control in aerospace and astronautics, pp 1–6 Google Scholar
- 4.Zhang Y, Tan Z, Yang Z, Lv X (2008) A dual neural network applied to joint angle drift-free resolution of five-link planar robot arm. In: Proceedings of IEEE international conference on information and automation, pp 1274–1279 Google Scholar