Getting the shot: Socially-aware viewpoints for autonomously observing tasks

摘要: In this work, we present an algorithm for autonomously determining the appropriate location from which to observe a human or robot agent (actor) while it completes task in dynamic environments. We develop theory selecting such using forward physical simulation of randomly-selected candidate viewpoints. The simulated points provide obstacle avoidance, and by incorporating modified version Social Force Model, viewpoints adjust themselves so that they do not encroach on actor's personal space and/or safety region. best observer position is chosen these candidates most complete view volume, taking into account occlusion caused actor itself. show our works under variety volume configurations, types (human robot), environmental constraints. Finally, paper shows results hardware deployment two-robot system — one observer, actor. concludes examining social impacts deploying autonomous observation algorithms real-world systems.