Expected perception in robots: a biologically driven perception-action scheme

The paper presents a biologically-inspired perception-action scheme for robots interacting with real-world environments, grounded in the broad hypothesis that, like in humans, perception and action are improved in speed and accuracy by expectation mechanisms: perception crucially involves comparison processes between incoming stimuli and expected perceptions (EPs). In the proposed approach, EPs are built on the basis of previous perceptions, current motor commands, proprioception, and internal models of the robot and the environment. In contrast to pure reactive approaches, background knowledge plays here a helpful role, as it reduces the computational burden of perception and motor coordination tasks, in partially structured environments. In the work presented here, an EP mechanism has been applied in the visuo-motor coordination of an anthropomorphic 8 d.o.f. robotic manipulator equipped with a vision system, in order to validate the viability and effectiveness of the initial hypothesis.