Transferring Adaptive Theory of Mind to Social Robots: Insights from Developmental Psychology to Robotics

Abstract

Despite the recent advancement in the social robotic field, important limitations restrain its progress and delay the application of robots in everyday scenarios. In the present paper, we propose to develop computational models inspired by our knowledge of human infants' social adaptive abilities. We believe this may provide solutions at an architectural level to overcome the limits of current systems. Specifically, we present the functional advantages that adaptive Theory of Mind (ToM) systems would support in robotics (i.e., mentalizing for belief understanding, proactivity and preparation, active perception and learning) and contextualize them in practical applications. We review current computational models mainly based on the simulation and teleological theories, and robotic implementations to identify the limitations of ToM functions in current robotic architectures and suggest a possible future developmental pathway. Finally, we propose future studies to create innovative computational models integrating the properties of the simulation and teleological approaches for an improved adaptive ToM ability in robots with the aim of enhancing human-robot interactions and permitting the application of robots in unexplored environments, such as disasters and construction sites. To achieve this goal, we suggest directing future research towards the modern cross-talk between the fields of robotics and developmental psychology.

What Makes a Robot Social? A Review of Social Robots from Science Fiction to a Home or Hospital Near You

“…[34][35][36][37]), theory of mind (e.g. [38][39][40][41]), mind perception (e.g. [42][43][44][45]), intention attribution (e.g.…”

From Psychological Intention Recognition Theories to Adaptive Theory of Mind for Robots

“…Although several studies provided computational models of ToM based on the accounts above described [19,20], we previously debated that such computational processes do not fully explain the way in which we are also able to infer abstract mental states (ToM components), such as intentions, desires and beliefs (see [7,8] for more details on current robotic architectures for ToM). Similarly, we suggest that humans are able to access more complex concepts than those described by the previous accounts, which cannot be inferred through action observation.…”

“…In fact, building robots as social agents, thus able to autonomously infer humans' intentions and beliefs and to adapt their behaviour both in various environments and when interacting with different people, remains one of the biggest challenges in robotics [6]. Previously [7,8], we highlighted the need for a cross-talk between robotics and developmental psychology as a means to advance robots' social skills and improve HRI. Specifically, we suggested the integration of a human-inspired adaptive Theory of Mind (ToM) in the architectures for social robots to do so.…”

“…In addition, four main functional advantages of equipping robots with an adaptive ToM with respect to current robotic architectures were identified, namely belief understanding and tracking, proactivity, active perception and learning (see [7] for further details). However, human ToM is characterised differently in the literature and it is yet to be fully defined [8]. To advance this debate, we thus identified a few important questions to be answered which would aid the integration of an adaptive ToM model in social robot architectures.…”

What Makes a Robot Social? A Review of Social Robots from Fiction to a Home or Hospital Near You

“…When cognitive neuroscience theory and methods are applied to HRI research, they allow us to probe how the human brain processes and reacts to robots, and these insights, in turn, can help facilitate further development of social robots [33]. Previous research in cognitive neuroscience has used social robots to address questions regarding attention (e.g., [34,35,36,37]), theory of mind (e.g., [38,39,40,41]), mind perception (e.g., [42,43,44,45]), intention attribution (e.g., [40,46,47]) and decision making (e.g., [48,49]).…”