Will i bother here?: a robot anticipating its influence on pedestrian walking comfort

Abstract

A robot working among pedestrians can attract crowds of people around it, and consequentially become a bothersome entity causing congestion in narrow spaces. To address this problem, our idea is to endow the robot with capability to understand humans' crowding phenomena. The proposed mechanism consists of three underlying models: a model of pedestrian flow, a model of pedestrian interaction, and a model of walking comfort. Combining these models a robot is able to simulate hypothetical situations where it navigates between pedestrians, and anticipate the degree to which this would affect the pedestrians' walking comfort. This idea is implemented in a friendly-patrolling scenario. During planning, the robot simulates the interaction with pedestrian crowd and determines the best path to roam. The result of a field experiment demonstrated that with the proposed method the pedestrians around the robot perceived better walking comfort than pedestrians around the robot that only maximized its exposure.