Anticipating human presence for safer worker - robot shared workspaces

Abstract

The co-existence for human and mobile robots in modern industrial environments is increasingly common. Safety primitive behaviours are typically built-in mobile robots, to ensure safety. However, when fleets of multiple robots are operating in such environments, robot path planning becomes complicated and is often left sub-optimal to avoid compromising human, equipment, or process safety. Enhanced performance can be achieved if path planning takes into account not just current human presence, but projected human movement trajectories. While this problem has received extensive attention in outdoor environments in autonomous driving contexts, its indoors workspace equivalent has received less attention. This paper presents an approach for human movement prediction in industrial work environments, based on past and current heatmap occupancy grids and convolutional neural networks. The adopted heatmap format is appropriate for dealing with privacy concerns so as to avoid individual person identification. Obtained results from a range of simulation data are presented, following by a discussion on limitations, and challenges to be handled by further work.