To Örebro University

The concept of Theory of Mind (ToM) is central to many social robotic studies. It may be invoked during the design of social robots as a way to improve collaboration or create a form of "social intelligence". It is also considered as an established fact and never put in question. However, many scholars have analysed the concept of ToM from a critical perspective and argued that it is, in fact, a theory with significant shortcomings, that rests on neuronormative and neuroprivileged grounds. In this paper, we explore these arguments and what this change of perspective means for the field of Social Robotics. We argue that the field should abandon the concept of ToM and move forward to more appropriate and inclusive models and research questions, and propose some directions to do so.

Unlocking the full societal potential of artificial intelligence demands a fundamental shift towards responsible and reproducible research. Understanding that PhD students are pivotal in conducting and reproducing experiments, we investigated the challenges of 28 AI PhD candidates from 13 European countries. We identify three critical areas where current practices fall short: (1) the findability and quality of AI resources such as datasets, models, and experiments; (2) the difficulties in replicating the experiments in AI papers; (3) and the lack of trustworthiness and interdisciplinarity. After uncovering some of the underlying reasons behind the challenges, we propose a combination of social and technical recommendations to overcome the identified challenges and foster a more transparent and reliable AI research ecosystem. Socially, we recommend the general adoption of reproducibility initiatives in AI conferences and journals, as well as improved interdisciplinary scientific collaboration, especially in data governance practices. On the technical front, we call for enhanced tools to better support versioning control of datasets and code, and a computing infrastructure that facilitates the sharing and discovery of AI resources, as well as the sharing, execution, and verification of experiments.

In this short paper, we consider scenarios in human-robot collaboration where the robot relies on deliberation to activate communicative actions. We claim that reasoning about the perception of these actions is a key, but often disregarded ingredient for successful communication, and propose a pre-theoretical model that accounts for this. We also discuss the problems that may arise if perception is neglected when reasoning about communication.

Tackling many of humanity's contemporary challenges requires individuals to cooperate in so-called collective risk dilemmas, i.e. scenarios where cooperation is costly yet required to reach collective targets and prevent catastrophic outcomes. It remains a scientific challenge to understand which external incentives enable cooperation and whether that can be facilitated through socially interactive agents. In this paper, we evaluate human cooperation in the presence of an artificial virtual agent. We developed a game called The Pest Control, in which five players attempt to maximize their earnings while avoiding being infested by a spreading pest. Controlling the pest requires costly public good contributions, yet free-riding on the efforts of others leads to maximum individual payoffs. We conducted an online experiment and analyzed the data of 265 participants, where we manipulated the feedback strategy of the virtual agent in a between-subject design. Our results suggest that feedback highlighting salient elements of the game increases participants' cooperation, while feedback regarding the consequences of actions slightly promotes selfish behaviors. Our study provides insight into how future artificial agents and AI systems could be designed to promote cooperation in complex social dilemmas by leveraging different strategies.

As Artificially Intelligent systems are becoming more and more present in our surroundings, our ways of interacting with them are also changing. From commercial chatbots to home assistants and robot companions, machines are progressively taking up the role of “communicators”, provided with their own agency, and able to interact with their human counterparts in new ways. This workshop aimed at gathering experts in fields relevant to the study of AI systems as communicators, including but not limited to Human-Computer Interaction, Artificial Intelligence, Human-Robot and Human-AI Interaction. It was organized in order to discuss new challenges brought by this recent shift, compare methods and perspectives between different fields, and foster long-term collaborations.

In this position paper, we argue for the need for deliberation in communication for artificial agents that perform tasks together with humans. Existing works use a set of terms and concepts with different meanings, resulting in ambiguity which does not allow for a general framework. As an initial step towards such a framework, we propose the notion of deliberative communication, clarify the necessary concepts and terminology, highlight the capabilities required in using deliberation for agents that communicate with human users, and discuss the main challenges.

In many robotic applications, especially those involving humans and the environment, linguistic and visual information must be processed jointly and bound together. Existing works either encode the image or the language into a subsymbolic space, like the CLIP model, or create a symbolic space of extracted information, like the object detection models. In this paper, we propose to describe images by nouns and modifiers and introduce a new embedded binding space where the linguistic and visual cues can effectively be bound. We investigate how state-of-the-art models perform in recognizing nouns and modifiers from images, and propose our method by introducing a dataset and CLIP-like recognition techniques based on transfer learning and metric learning. We show real-world experiments that demonstrate the practical applicability of our approach to robotics applications. Our results indicate that our method can surpass the state-of-the-art in recognizing nouns and modifiers from images. Interestingly, our method exhibits a language characteristic related to context sensitivity.

Dynamics in Human-AI interaction should lead to more satisfying and engaging collaboration. Key open questions are how to design such interactions and the role personal goals and expectations play. We developed three AI partners of varying initiative (leader, follower, shifting) in a collaborative game called Geometry Friends. We conducted a within-subjects experiment with 60 participants to assess personal AI partner preference and performance satisfaction as well as perceived warmth and competence of AI partners. Results show that AI partners following human initiative are perceived as warmer and more collaborative. However, some participants preferred AI leaders for their independence and speed, despite being seen as less friendly. This suggests that assigning a leadership role to the AI partner may be suitable for time-sensitive scenarios. We identify design factors for developing collaborative AI agents with varying levels of initiative to create more efective human-AI teams that consider context and individual preference.

In traditional decision-theoretic planning, information gathering is a means to a goal. The agent receives information about its environment (state or observation) and uses it as a way to optimize a state-based reward function. Recent works, however, have focused on application domains in which information gathering is not only the mean but the goal itself. The agent must optimize its knowledge of the environment. However, traditional Markov-based decision-theoretic models cannot account for rewarding the agent based on its knowledge, which leads to the development of many approaches to overcome this limitation. We survey recent approaches for using decision-theoretic models in information-gathering scenarios, highlighting common practices and existing generic models, and show that existing methods can be categorized into three classes: reactive sensing, single-agent active sensing, and multi-agent active sensing. Finally, we highlight potential research gaps and suggest directions for future research.

The integration of Ambient Assisted Living (AAL) frameworks with Socially Assistive Robots (SARs) has proven useful for monitoring and assisting older adults in their own home. However, the difficulties associated with long-term deployments in real-world complex environments are still highly under-explored. In this work, we first present the MoveCare system, an unobtrusive platform that, through the integration of a SAR into an AAL framework, aimed to monitor, assist and provide social, cognitive, and physical stimulation in the own houses of elders living alone and at risk of falling into frailty. We then focus on the evaluation and analysis of a long-term pilot campaign of more than 300 weeks of usages. We evaluated the system's acceptability and feasibility through various questionnaires and empirically assessed the impact of the presence of an assistive robot by deploying the system with and without it. Our results provide strong empirical evidence that Socially Assistive Robots integrated with monitoring and stimulation platforms can be successfully used for long-term support to older adults. We describe how the robot's presence significantly incentivised the use of the system, but slightly lowered the system's overall acceptability. Finally, we emphasise that real-world long-term deployment of SARs introduces a significant technical, organisational, and logistical overhead that should not be neglected nor underestimated in the pursuit of long-term robust systems. We hope that the findings and lessons learned from our work can bring value towards future long-term real-world and widespread use of SARs.