Superficial pain model using ANNs and its application to robot control

Abstract

In the coexistence circumstance with humans and robots, sensory and emotional feeling of human should be considered when the robots interact to human. A typical unpleasant feeling at interaction is "pain". It is difficult to separate the robots from human in the sense of time or place in coexisting environment unlike factory automation design. Thus a new concept of separation in the sense of safety is required. One approach is to design the controller based on the pain that is subjective of human. In this paper, artificial superficial pain model (ASPM) caused by impact is proposed. This ASPM model consists of mechanical pain model, skin model and gate control by artificial neural networks (ANNs). The proposed ASPM is applied to robot control and is evaluated