Abstract
The paper presents an original application of the Hopfield-type neural network to a robotics optimisation problem. The robot considered features an arm composed of three revolute joints, the last of which is the end-effector. The robot is planar as the movement of the end-effector is limited to one plane. The mechanical characteristics of the actuators in the joints, the accuracy of the angle position sensors, and dimensional errors in the mechanical elements which make up the end-effector all contribute towards an end-effector positioning error along an assigned trajectory. The computational complexity of the algorithmic solution to the minimisation of this error is at times incompatible with certain particularly critical industrial applications. To reduce the calculation time, the author presents a neural approach based on a Hopfield-type model. A detailed definition of the neural approach is given, its capacity for solving the problem is demonstrated, and the computational complexity is analysed. This analysis shows the drastic computational reduction provided by the neural approach as compared with an algorithmic solution to the problem of end-effector position optimisation.
Similar content being viewed by others
References
Wasserman PD. Neural Computing — Theory and Practice, Van Nostrand Reinhold, 106–109
Lippmann RP. An introduction to computing with neural nets. IEEE ASSP Magazine April, 1987; 2–22
Brück J. On the convergence properties of the Hopfield model. Proc IEEE 1990; 78 (10): 1579–1585
Florèen P. Worst case convergence times for Hopfield memories. IEEE Trans Neural Networks 1991; 2: 533–535
Fogelman F, Goles E, Weisbuch G. Transient length in sequential iterations of threshold functions. Discrete Applied Mathematics 1983; 6: 95–98
Goles E, Martinez S. Neural and Automata Networks: Dynamics Behaviour and Applications, Kluwer, Dordrecht, 1990
Marchis V, Petrone F, Sinatra R. A correlation between the state-space and the task-oriented path in the presence of obstacles for mechanical manipulators. J Robotics Systems 1994; 11 (5): 441–448
Cavalieri S, Martini M. Solving an end-effector positioning problem by Hopfield neural network. Proc Int Workshop on Artificial Neural Networks, IWANN, Malaga-Costa del Sol, Spain, June 7–9 1995
Cavalieri S, Martini M, Petrone F, Sinatra R. A neural network approach for position error minimisation problem in redundant robot. Proc Ninth World Congress on the Theory of Machines and Mechanisms, Milan, Italy, August 30–September 2 1995
Hopfield J-J. Neural networks and physical systems with emergent collective computational abilities. Proc Nat Academy of Sciences 1982; 79: 2554–2558
Hopfield JJ, Tank DW. Neural computations of decisions in optimzation problems. Biol Cybern 1985; 52: 1–25
Tank DW, Hopfield JJ. Simple ‘neural’ optimization networks: an A/D converter, signal decision circuit, and a linear programming circuit. IEEE Trans Circuits Syst 1986; 33 (5): 533–541
Cohen MA, Grossberg SG. Absolute stability of global pattern formation and parallel memory storage by competitive neural networks. IEEE Trans Systems, Man and Cybernetics 1983; 13: 915–826.
Hecht-Nielsen R. Neurocomputing, Addison-Wesley, Reading, MA, 1990
Hopfield J-J. Neurons with graded response have collective computational properties like those of two-state neurons. Proc Nat Academy of Sciences 1984; 81: 3088–3092.
Mehmet Ali MK, Famoun F. Neural networks for shortest path computation and routing in computer networks. IEEE Trans Neural Networks 1993; 4 (6): 941–954
Takeda M, Goodman JW. Neural networks for computation: number representations and programming complexity. Appl Opt 1986; 25 (18): 3033–3046
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Cavalieri, S. A solution to the end-effector position optimisation problem in robotics using neural networks. Neural Comput & Applic 5, 45–57 (1997). https://doi.org/10.1007/BF01414102
Issue Date:
DOI: https://doi.org/10.1007/BF01414102