Anthropomorphic grasp generation through probabilistic modelling in an optimised eigen-space

Artificial cognitive systems are increasingly drawn towards ‘human-like’ gestural exhibits while performing various manipulative acts. Representing such actions in a natural settings requires temporal extractions of their grasp progressions. A novel optimisation-based hidden Markov framework is offered, to generate natural hand prehensions through maximisation of a composite grasp function built of individual finger trajectory likelihoods. In order to produce the desired motion in an intuitive framework, the final grasp frame (represented in terms of standard discriminants z ∈ ℜ2 in a condensed grasp eigen-space) is extended in a temporal sequence by equi-spaced increments of z, over their conventional joint-space representations.