In order to operate successfully, robots need to collect and represent information about their environment and be able to reason about their own goals and the effects of their actions. If the environment contains also other agents, the robot should be able to reason about their goals and the information they have. If the environment is something as complex as the human social world, , the robot may need to be able to reason about the functions, and purposes of the groups, rules, norms, conventions, and other institutional structures. Will it be enough to stay within the conceptual paradigm of intentional agency and do with the conceptual primitives of beliefs, desires, and intentions (BDI)? Or will it be necessary to add new primitive concepts, e.g. normative concepts like obligations or commitments, or group-based concepts, like collective beliefs or we-intentions? Or are there viable alternatives to the intentional agency paradigm that would enable robots to operate in complex social environments without recourse to attribution of intentional states altogether? These are some of the questions that the workshop aims to tackle. 

In brief, embodied cognition emerges within the perception-action loop and unfolds in physical space. Cognitive processes that are distributed across agents and environment are accessible and actionable. Cognition cooperates with the surroundings to upgrade basic skills within ongoing collaboration; to illustrate, you can consult the task environment to modulate performance, and use external props to prolong interaction. Bodily co-presence allows for physically and mentally moving into another’s perspective. When humans and robots collaborate, they share the task environment and function as resources for each other, learning from one another. Humans tend to spontaneously organize themselves in spatial patterns that permit the continuous coordination of all participants’ behaviour and attention, creating full transparency among them. Finally, recurring activities form routines that increase predictability. Routines materialize as trajectories through space, built around artefact use with locations and transitions as cues to action. These trajectories are accessible for everybody and in principle others can join in

Social robots are coming to appear in our daily lives. Yet, it is not as easy as one might imagine. We developed a human-like social robot, Robovie, and studied the way to make it serve for people in public space, such as a shopping mall. On the technical side, we developed a human-tracking sensor network, which enables us to robustly identify locations of pedestrians. Given that the robot was able to understand pedestrian behaviors, we studied various human-robot interaction in the real-world. We faced with many of difficulties. For instance, the robot failed to initiate interaction with a person, and it 
failed to coordinate with environments, like causing a congestion around it. Toward these problems, we have modeled various human interaction. Such models enabled the robot to better serve for individuals, and also enabled it to understand people’s crowd behavior, like congestion around the robot; however, it invited another new problem, robot abuse. I plan to talk about a couple of studies in this direction, hoping to provide an insight about near-future applications, research problems, and ethical issues about the social robots in public space in a near future. 

In this talk, I review findings about social practices in social institutions and their consequences for robot deployment in these institutions from the perspective of whether and how these findings can be addressed from the perspective of a paradigm that rests on representations of beliefs, desires and intentions (BDI). Specifically, previous work has revealed many social factors that influence and constrain whether and how robots can play a valid role in these institutions. Many of these issues concern tacit, implicit knowledge and social norms and practices, rather than rules and explicit knowledge. Using a case study in which we attempted to deploy a robot in an elderly care facility as a starting point, I illustrate what underlies social practice in such a social institution and provide input to the joint discussion, to what extent these types of knowledge can be addressed from a BDI perspective.