Toward Error-Tolerant Robot Navigation: Sequential Inducement Based on Intent Conveyance from Robot to Human and Its Achievement

Abstract Human symbiotic mobile robots are required to smoothly reach destinations while avoiding humans. Human-intent information, e.g., a moving direction, must be carefully estimated since its lack leads the hesitation and repetitious avoidance. Conventional studies address human intent estimation conveyance but do not consider cases of failing communication as systematic framework, even though is essentially difficult for humans estimate due interiority. In response this problem, we propose framework error-tolerant navigation (ETN) with process actively by iterative interaction from robot. As preliminary study, focus on ‘the robot human’ ‘its achievement’ core information. The ETN estimates interference possibility determine need inducement, awareness (HA) select an inducement method, achievement (IA) judge action again. If interference, provides inducements according HA, route indication when HA high or voice/physical low. Each corresponds expected behavior change in human. IA calculated difference between actual changes. observes no within specified time after it executes stronger conveyance. When none strongest action, selects another route. This error-collection loop could prevent fatal mistake recognizing small recovering it. static dynamic experimental results indicated that achieve smoother movement reduce psychological burden correcting behaviors, compared conventional system, which can contribute constructing practical framework.