Developmental changes in children understanding robotic actions: The case of lifting

Abstract

Humans develop already from the first years of life the ability to understand the actions and intentions of others and naturally use this skill to help others [1]. It would be important for the future of human-robot collaboration if children could easily generalize this understanding to robotic agents. In this paper we have investigated whether this is possible, at least in the context of inferring object weight from the observation of a humanoid action. Our results show that children of different ages need a different degree of human-likeness in robot motion to be able to infer which weight is being lifted. Indeed, from 10 years of age on, even non-humanlike trajectories can communicate the lifted load, if the lifting speed is appropriately varied as a function of weight. Conversely, younger children are significantly better at judging weight only in presence of a human-like trajectory. Hence, robots should adapt even the basic properties of their motion to their users, taking into account that children perception progressively changes with age.