SARL: Deep Reinforcement Learning based Human-Aware Navigation for Mobile Robot in Indoor Environments

Abstract

In a human-robot coexisting environment, reaching the goal position safely and efficiently is essential for a mobile service robot. In this paper, we present an advanced version of the Socially Attentive Reinforcement Learning (SARL) algorithm, namely SARL*, to achieve human-aware navigation in indoor environments. Recently, deep reinforcement learning has achieved great success in generating human-aware navigation policies. However, there exist some limitations in the real-world implementations: the learned navigation policies are limited to certain distances associated with the training process, and the simplification of the environment neglects obstacles other than humans. In this work, we improve the state-of-the-art SARL algorithm by introducing a dynamic local goal setting mechanism and a map-based safe action space to tackle the above problems. Real-world experimental results demonstrate that the proposed algorithm outperforms the original SARL algorithm in both time cost and path length in the human-aware navigation tasks in the indoor environment.