Expected perception: an anticipation-based perception-action scheme in robots

Abstract

The paper proposes an anticipation mechanism to improve the perception-action loop of robots interacting with real-world environments. According to recent neuroscientific findings, sensory anticipation can increase the effectiveness of perception-action loops and reduce the delays in obtaining the sensory information, especially in case of complex sensory modalities like vision, that affect pure feed-back structures. In the proposed scheme, perception crucially involves comparison processes between incoming stimuli and expected perceptions (EPs), built from previous perceptions, current motor commands, and internal models of the robot and the environment. 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 evaluate the conditions of applicability of the proposed strategy, and to validate the viability and effectiveness of the initial hypothesis.