Reshaping Human Intentions by Autonomous Sociable Robot Moves Through Intention Transients Generated by Elastic Networks Considering Human Emotions


This thesis focuses on reshaping a previously detected human intention into a desired one, using contextual motions of mobile robots, which are in our applications, autonomous mobile 2-steps and a chair. Our system first estimates the current intention based on human trajectory depicted as location and detects body-mood of the person based on proxemics behaviors. Our previous reshaping applications have shown that the current human intention has to be deviated towards the new desired one in phases according to the readiness changes induced in the human. In our novel approach, Elastic network plans way points (intention transients) by searching trajectories in the feature space of previously learned motion trajectories each labeled with an intention. Our methodology aims at planning an “intention trajectory” (sequences of intention transients) towards the final goal. The initial way points possess destabilizing effects on the obstinance of the person intention making “the robot gain the curiosity of the person” and induces positive mood to the person making “the robot gain the trust of the person”. Each way point found by the elastic network is executed by moves of an adequate robot (here mobile 2-steps or chair) in adequate directions (towards coffee table, PC, library). After each robot moves, the resulting human intention is estimated and compared to the desired goal in the intention space. Intention trajectories are planned in two modes: the “confident mode” and the “suspicious mode”. This thesis work introduces our novel approach of planning trajectories based on elastic networks following these two modes. Keywords: Human-Robot Interactions, Sociable Robots, Intention Reshaping, Elastic Networks, Emotional Body-Mood Detection, Path Planning, Intention Estimation

Master Thesis