Solving an end-effector positioning problem by Hopfield neural network
The paper proposes application of a Hopfield network to optimization of the movement of a 3R planar robot. More specifically, the network is used to solve a typically complex problem from the computational point of view — determination of the positions of the robot along a certain trajectory — in such a way as to minimize the final end-effector positioning error. The paper illustrates the methodology followed to solve this problem and discusses the results that can be obtained by using the neural solution proposed.
Unable to display preview. Download preview PDF.
- P.D.Wasserman, “Neural Computing — Theory and Practice”. Van Nostrand Reinhold Editor, pp.106–109.Google Scholar
- R.P.Lippmann, “An Introduction to Computing with Neural Nets”. IEEE ASSP Magazine, April 1987, pp.2–22.Google Scholar
- J.J.Hopfield, “Neurons with Graded Response Have Collective Computational Properties Like those of two-state Neurons”, Proceedings National Academy of Sciences 81:3088–3092, May 1984.Google Scholar
- J.J.Hopfield, “Neural Networks and Physical Systems with Emergent Collective Computational Abilities”, Proceedings National Academy of Sciences 79:2554–2558, April 1982.Google Scholar
- S.Cavalieri, M.Martini, F.Petrone, R.Sinatra, “A Neural Network Approach for Position Error Minimization Problem in Redundant Robot”, Ninth World Congress on the Theory of Machines and Mechanisms, Politecnic of Milan, Italy, August 30–September 2, 1995.Google Scholar
- V.Marchis, F.Petrone, R.Sinatra, “Analisi dello Spazio di Lavoro di Robot Ridondanti”, XI National Congress AIMETA, 28 September–2 October, 1992, Trento, Italy.Google Scholar
- Anza Plus User's Guide and Neurosoftware Documents Release 2.2 15 May, 1989.Google Scholar