Social Robot Navigation with Adaptive Proxemics Based on Emotions

The primary aim of this paper is to investigate the integration of emotionsinto the social navigation framework to analyse its effect on both navigationand human physiological safety and comfort. The proposed framework uses legdetection to find the whereabouts of people and computes adaptive proxemiczones based on their emotional state. We designed several case studies in asimulated environment and examined 3 different emotions; positive (happy),neutral and negative (angry). A survey study was conducted with 70 participantsto explore their impressions about the navigation of the robot and compare thehuman safety and comfort measurements results. Both survey and simulationresults showed that integrating emotions into proxemic zones has a significanteffect on the physical safety of a human. The results revealed that when aperson is angry, the robot is expected to navigate further than the standarddistance to support his/her physiological comfort and safety. The results alsoshowed that reducing the navigation distance is not preferred when a person ishappy.