How to Formally Model Human in Collaborative Robotics
This paper addresses the critical problem of ensuring human safety in collaborative robotics by surveying suitable formal models for human behavior.
This paper explores existing formal modeling techniques for human behavior in Human-Robot Collaboration (HRC) to identify those suitable for safety analysis. The goal is to enable comprehensive and realistic HRC system models that account for human uncertainty to prevent injuries.
Human-robot collaboration (HRC) is an emerging trend of robotics that promotes the co-presence and cooperation of humans and robots in common workspaces. Physical vicinity and interaction between humans and robots, combined with the uncertainty of human behaviour, could lead to undesired situations where humans are injured. Thus, safety is a priority for HRC applications. Safety analysis via formal modelling and verification techniques could considerably avoid dangerous consequences, but only if the models of HRC systems are comprehensive and realistic, which requires reasonably realistic models of human behaviour. This paper explores state-of-the-art solutions for modelling human and discusses which ones are suitable for HRC scenarios.