Investigating the ability to read others’ intentions using humanoid robots

Abstract

The ability to interact with other people hinges crucially on the possibility to anticipate how their actions would unfold. Recent evidence suggests that a similar skill may be grounded on the fact that we perform an action differently if different intentions lead it. Human observers can detect these differences and use them to predict the purpose leading the action. Although intention reading from movement observation is receiving a growing interest in research, the currently applied experimental paradigms have important limitations. Here, we describe a new approach to study intention understanding that takes advantage of robots, and especially of humanoid robots. We posit that this choice may overcome the drawbacks of previous methods, by guaranteeing the ideal trade-off between controllability and naturalness of the interactive scenario. Robots indeed can establish an interaction in a controlled manner, while sharing the same action space and exhibiting contingent behaviors. To conclude, we discuss the advantages of this research strategy and the aspects to be taken in consideration when attempting to define which human (and robot) motion features allow for intention reading during social interactive tasks.

Sociomotor action control

“…A useful test bed to study the interaction of bottom-up and topdown factors are robots, who can look and move in a more-or-less humanoid manner, while prior knowledge can suggest, more or less, that such robots behave in an either intentional or preprogrammed manner (Sciutti, Ansuini, Becchio, & Sandini, 2015). While there is some research regarding the impact of these factors to imitate and corepresent robot actions (e.g., Klapper, Ramsey, Wigboldus, & Cross, 2014), little is known about how these factors shape the way people manipulate robots' behavior, which is the focus of the sociomotor approach.…”

The Importance of Mutual Gaze in Human-Robot Interaction

“…They can induce both low-level social cognition mechanisms (perceptual and motor processes) [6-8] and higher-order mechanisms, such as mentalizing [9]. In terms of experimental control, precise behavioral parameters of the robot can be manipulated, and subsequently, influence of these parameters on the social cognition mechanisms of humans can be examined [10]. Although lowlevel social processes are typically evoked when robots are used as interaction partners [6][7][8], they can be modulated by human-likeness of the robot, as people are sensitive to subtle human-like features in robot's behavior [11][12].…”

Examining joint attention with the use of humanoid robots-A new approach to study fundamental mechanisms of social cognition

“…In the case of using humanoid robots in interactive scenarios, one can maintain experimental control while also embedding the setup in natural 3-D joint environment. Importantly for the purposes of studying joint attention, humanoids offer excellent experimental control-they can repeat same specific behaviors over many trials, and they allow for "modularity of control" (Sciutti, Ansuini, Becchio, & Sandini, 2015); that is, their movements can be decomposed into specific elements, an impossible endeavor for a human. For instance, in the context of joint attention research, the trajectory time of the movement of the eyes can be controlled and can follow predefined parameters over many repetitions.…”

“…One crucial theoretical question that is not yet fully understood in joint attention research relates to how different nonverbal cues such as eyes, head, body posture or pointing are integrated in order to summon human's attention. This question could be easily addressed with full-body humanoid robots that consist of mechanical eyes since the robot's movements can be decomposed into individual components but also in selected combinations of them, as described in (Sciutti et al, 2015) by the term "modularity of the control." The importance of this topic is also relevant for clinical studies.…”