Parallel manipulators have attracted the attention of researchers from different areas such as: high-precision robotics, machine-tools, simulators and haptic devices. The choice of a particular structural configuration and its dimen-sioning is a central issue to the performance of these manipulators. A solution to the dimensioning problem, normally involves the definition of performance crite-ria as part of an optimization process. In this paper the kinematic design of a 6-dof parallel robotic manipulator for maximum dexterity is analyzed. The condition number of the inverse kinematic jacobian is defined as the measure of dexterity and solutions that minimize this criterion are found through a genetic algorithm formulation. Subsequently a neuro-genetic formulation is developed and tested. It is shown that the neuro-genetic algorithm can find close to optimal solutions for maximum dexterity, significantly reducing the computational load.
展开▼