Deflection compensation of a flexible hydraulic manipulator utilizing neural networks

Deflection compensation of flexible boom structures in robot positioning is usually done using tables with inverse kinematics solutions. The number of table values increases greatly if the working area of the boom is large and the required accuracy is high. On the other hand, inverse kinematics problems are very nonlinear, and if the structure is redundant, in some cases it cannot be solved in closed form. If the flexibility of the structure is taken into account, the problem is almost impossible to solve using analytical methods. Neural networks offer a possibility to approximate any linear or nonlinear function. Four different methods of using neural networks in the static deflection compensation of a flexible hydraulically driven manipulator are presented. Training information required for training neural networks is obtained by employing a simulation model that includes elasticity characteristics. The functionality of the presented methods is tested based on simulated results of positioning accuracy. The positioning accuracy is tested in 25 separate coordinate points. For each point, positioning is tested with five different mass loads. The mean positioning error of a manipulator decreases from 48 to 5.8 mm in the test points. This accuracy enables the use of flexible manipulators in the positioning of larger objects. (C) 1997 Elsevier Science Ltd.