Robot navigation in a dynamic environment needs to consider the comfort of the surrounding pedestrians under the premise of ensuring the safety of human, which is a challenging task.

This paper proposes the concept of social stress index based on tension space of robot and human, which is an important part of Human-Robot interaction. Especially, the proposed approach develops crowd-comfort navigation by combining social stress index with a deep reinforcement learning framework and the value network.

A set of typical simulation experiments show that our method effectively improves the comfort of surrounding pedestrians during the process of robot navigation.

Simulation Experiment 1 : Simple mode

Simulation Experiment 2 : Difficult mode