For mobile robots to operate in compliance with human presence, interpreting the impact of human activities and responding constructively is a challenging goal. In this paper,weproposeagenerativeapproachforenhancingrobot mapping and mobility in the presence of humans through a joint, probabilistic treatment of static and dynamic characteristics of indoor environments. Human spatial activity is explicitly exploited for the purpose of passage detection andspaceoccupancy predictionwhileeffectivelydiscarding falsepositivehumandetectionsusingpriormapinformation. In turn, this allows the execution of plan trajectories within unexplored areas by using human presence for resolving the uncertainty or ambiguity that is due to dynamic events. A seriesofexperimentswithanindoorrobotnavigatinginclose human proximity within a multi-floor building demonstrate the effectiveness of our approach in realistic conditions.

EB00000003646K

Available

• Binding human spatial interactions with mapping for enhanced mobility in dynamic environments