Search

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. [ABSTRACT FROM AUTHOR]

Grasping postures on a human hand are generated by an effective combination of spatial motions and contact forces on individual finger linkages. The rich kinematic redundancy within its anatomy, poses critical control challenges, while emulating natural prehensile actions. A simplified grasp‐formulation resolution is presented, by proposing a virtual‐object imagery to define generic grasp enaction sequences. The same are conceived and controlled by a set of contact points on the imagined grasp‐sphere, whose spatial conformation is guided by a serial‐haptic interface. The kinaesthetic cognitions along with visual feed to an operator ushers a reliable framework for grasp execution and transfer to a robot hardware without resorting to supplementary mapping mechanisms. Stable grasps on the anthropomorphic robot set‐up portrays a systematic procedure to transcribe human‐like postural attributes, aided with somesthetic and visual sensations that are anticipated to steer remote operator controls. [ABSTRACT FROM AUTHOR]