Human Aspects in Collaborative Order Picking – Letting Robotic Agents Learn About Human Discomfort

Abstract

Human aspects in collaboration of humans and robots, as common in warehousing, are considered increasingly important objectives in operations management. This work aims to let robots learn about human discomfort in collaborative order picking of robotic mobile fulfillment systems. To this end, a multi-agent reinforcement (MARL) approach that considers human discomfort next to traditional performance objectives in the reward function of robotic agents is developed. As a first step, we assume a human-oriented assignment problem in which the robotic agents assign orders to human workers at order picking work stations. The results show that among the four evaluated assignment policies, only the proposed MARL policy effectively considers human discomfort. While the approach may need to be refined to obtain near-optimal solutions for the trade-off between humans aspects and efficiency objectives, it also shows a practicable pathway for related problems of human-robot collaboration, inside and outside of warehousing.