ABSTRACT
This chapter introduces sensor networks consisting of various sensors and discusses how they support both robots and humans. Sensing system is the fundamental components in most of robotic systems. Humans live in the world with ubiquitous sensors, and access to the Internet via smart phones and computers to refer to information in distant locations. In similar metaphor, as robots are networked, large part of sensing can be done with ubiquitous sensors in network robot system. Robots designed to interact socially with people require reliable estimates of human position and motion. Additional pose data such as body orientation may enable a robot to interact more effectively by providing a basis for inferring contextual social information such as people’s intentions and relationships. The proposed method was found to be efficient with the classification of real human–robot interactions, and was able to be implemented as distributed in-network processing.
