Ostensive Human Robot Interaction – OSTENSIVE

When humans demonstrate a task, the demonstrations are directed not just towards the objects that are manipulated, but they are also accompanied by ostensive communicative cues such as gaze and/or modulations of the demonstrations in the space–time dimensions. These behaviors, such as pause, repetition and exaggeration, might appear to be sub-optimal, but they are provided by humans to communicate. Cognitive Science addresses this challenge of communication in action by drawing inspiration from language (literal meaning-pragmatic inference). Most of the approaches of Human-Robot Interaction assume literal interpretation of behaviours resulting in a strong limitation of interpretation of actions and intentions of the other. There is a need of forward and inverse models being able to generate relevant content to the other (human/robot) and to adequately interpret the actions of the other. The aim of OSTENSIVE is to develop such computational forward and inverse models using machine learning based approaches conditioned by reasoning mechanisms about humans (WP3). Based on Cognitive Science based approaches, we will investigate situations, indicators and metrics allowing to determine conditions under which humans engage and take benefit from such models by new approaches of on-line evaluation of second-person perspective taking. OSTENSIVE will develop new models able to synthesize ostensive and interactive robot motions and probabilistic representations of ostensive actions learned from human demonstrations. We aim to adapt and extend experimental protocols used to study social cognition. We will address manipulation of objects and social navigation and integrate ostensive action into different robotics platforms (and whole body control). After ethical approval, we will conduct extensive experiments to validate the ostensive communication skills of the robots with naive participants that should maximally benefit of such skills to accomplish a task with the robot.