A wearable affective robot

Abstract

With the speed of economic development and the accelerating pace of people's lives, new pressures associated with our social lives have had a significant impact on the psychology of individuals. The preservation of mental health has become an urgent requirement for people. Combining various technologies, such as robotics, flexible wearables, and emotion perception, we are proposing a wearable, emotional robot named Fitbot. As well as satisfying fashion tastes, Fitbot can better achieve affective social interaction by collecting multimodal, physiological information without influence and performing emotional reasoning. This chapter focuses on innovative research relating to brain wearables, including hardware circuit design, electro-encephalography data collection and analysis, user-behavior perception, algorithm deployment, and realizes user-behavior recognition based on electro-encephalography. The accompanying data can be obtained with a human-machine collaboration system of deep integration. Using these data, with both depth and breadth, we can conduct long-term modeling and an intention analysis of users, and then analyze the behavioral motivation behind the emotions. Our long-life-cycle learning algorithm designed for Fitbit can give users a more emotional interactive experience. Finally, combined with application service scenarios, open research challenges are proposed.