Towards Intention Recognition for Human-Interacting Agricultural Robots

Abstract

—Robots sharing a common working space with humans and interacting with them to accomplish some task should not only optimise task efficiency, but also consider the safety and comfort of their human collaborators. This requires the recognition of human intentions in order for the robot to anticipate behaviour and act accordingly. In this paper we propose a robot behavioural controller that incorporates both human behaviour and environment information as the basis of reasoning over the appropriate responses. Applied to Human-Robot Interaction in an agricultural context, we demonstrate in a series of simulations how this proposed method leads to the production of appropriate robot behaviour in a range of interaction scenarios. This work lays the foundation for the wider consideration of contextual intention recognition for the generation of interactive robot behaviour.