Give Pedestrian More Choice: Socially Aware Navigation Using Reinforcement Learning with Human Action Entropy Maximization

Robot navigation in a human-populated environment has spurred wide interest in recent years. While moving safely and efficiently are basic requirements for robot navigation, it is also important for robots to move in a socially acceptable way that obeys the social norms. However, since the social norms are subtle and diverse, most of the rule-based methods considered only situations of pairwise human-robot confrontation, and are difficult to generalize to crowded scenarios. In this paper, we propose a socially aware navigation method using reinforcement learning with human action entropy maximization, in which the diversity of human choices is considered as a reward to inform the robot of the socially acceptable interaction with a crowd. By learning to maximize this reward, the proposed method realizes social acceptability by giving pedestrians more choices to enlarge their chance to take their preferred action. The experiments demonstrate that the proposed method enables the robot to learn socially aware navigation that provides neighboring pedestrians with efficient and safe traffic, outperforming state-of-the-art methods.