How to model a human-to-robot romantic relationship? Just a few elements will do: artificial emotional hormones, intelligent affective system and probabilistic parameters of love between humans and the robot…
Subsequent generations of robots developed fast. Industrial robots are employed nowadays in all industrial factories. Service robots offer their assistance on a large scale in points of sales, as well as virtual assistants guide users on numerous websites. Social robots, sociable agents and conversational agents ensure social interaction in various multimedia centers.
New generation of robots - loving robots called lovotics - have the ability to feel, love and be loved by humans. They employ artificial hormones to exhibit feelings, emotions and behaviors. Their design is inspired by the psychology and biology of humans in love.
The artificial intelligence system of Lovotics is proposed by Hooman Samani, artificial intelligence researcher in Keio-NUS CUTE Center, which is a collaborative lab between National University of Singapore and Keio University of Japan. Lovotics includes Artificial Endocrine System, Probabilistic Love Assembly and Affective State Transition modules. They are based on physiology of love, psychology of love and emotional models respectively.
Probabilistic Love Assembly calculates probabilistic parameters of love between humans and the robot. Into consideration there are taken various parameters: proximity, similarity, desirability, attachment, reciprocal liking, satisfaction, and attraction.
Artificial Endocrine System produces artificial hormones such as Dopamine, Oxytocin, Serotonin and Endorphin, imitating the human endocrine system.
Affective State Transition controls various affective parameters of love, for example facial expressions, voice, gesture. They allow Lovotics robot to reason about other person’s emotions and state of mind.
The Lovotics robot actively participates in the communication process. It adjusts its internal hormonal levels and affective states depending on inputs and feedback from the human. It is modeled as closely to the human being as possible in order to be an emotionally engaging system and to exhibit suitable states and behaviors in real-time.
