Dynamic social zone for human safety in human-robot shared workspaces

In this paper, we present an efficient human safety framework of robotic systems that guaranties human safety in human-robot shared workspace. The general framework is composed of three stages: 1) human detection and tracking algorithms are used to detect and track the human in unknown dynamic environments; 2) human social signals is estimated; 3) human states and their social signals are integrated in a estimation model, so-called dynamic social zone (DSZ). The dynamic social zone is embedded into the navigation control guiding the mobile robots to move safely in human populated environments. The experimental results indicate that the proposed framework is able to ensure human safety in human-robot shared workspaces.