Toward socially aware trajectory planning system for autonomous mobile robots in complex environments

Abstract

This paper proposes a socio-spatio-temporal human characteristics-based socially aware navigation framework that enables mobile service robots to both approach and avoid humans in dynamic social environments. The proposed framework consists of two major stages. In the first stage, the robots estimate the approaching poses of the robot to the human or human group. In the second stage, the proposed framework will estimate an optimal robot's trajectory using the online trajectory planning technique. The control command extracted from the optimal trajectory is then utilized to drive the mobile robot to approach the individual humans or human groups, while avoiding regular obstacles, humans and human groups during the robot's navigation. The proposed framework is verified in the Gazebo-based simulation environment. The simulation results illustrate that, the mobile robots equipped with our proposed framework are able to safely and socially approach and avoid individual humans and human groups, providing socially acceptable behavior for the robots.