From Human Perception and Action Recognition to Causal Understanding of Human-Robot Interaction in Industrial Environments

Human-robot collaboration is migrating from lightweight robots in laboratory environments to industrial applications, where heavy tasks and powerful robots are more common. In this scenario, a reliable perception of the humans involved in the process and related intentions and behaviors is fundamental. This paper presents two projects investigating the use of robots in relevant industrial scenarios, providing an overview of how industrial human-robot collaborative tasks can be successfully addressed.