Abstract
Industrial and mobile robots demand reliable and safe navigation capabilities to operate in human populated environments such as advanced manufacturing industries and logistics warehouses. Currently mobile robot platforms can navigate through their environment avoiding coworkers in the shared workspace, considering them as static or dynamic obstacles. This strategy is efficient for safety, strictly speaking, but is not sufficient to provide humans integrity and comfortable working conditions. To this end, this paper proposes a human-aware navigation framework for comfortable, reliable and safely navigation designed to run in real-time on a mobile robot platform in logistics warehouses. This is accomplished by estimating human localization using RGB-D detector, then generating a virtual circular obstacle enclosing human pose. This virtual obstacle is then fused with the 2D laser range scan and used in ROS navigation stack local costmap for human-aware navigation. This strategy guarantees a different approach distance to obstacles depending on the human or non-human nature of the obstacle. Hence the mobile robot can approach closely to pallet to pick up objects while maintaining an integrity distance to humans. The reliability of the proposed framework is demonstrated in a workbench of experiments using simulated mobile robot navigation in logistics warehouses environment.