Visual behavior modelling for robotic theory of mind

HUMANISE: Human-Inspired Smart Management, towards a Healthy and Safe Industrial Collaborative Robotics

The workplace is evolving towards scenarios where humans are acquiring a more active and dynamic role alongside increasingly intelligent machines. Moreover, the active population is ageing and consequently emerging risks could appear due to health disorders of workers, which requires intelligent intervention both for production management and workers' support. In this sense, the innovative and smart systems oriented towards monitoring and regulating workers' well-being will become essential. This work presents HUMANISE, a novel proposal of an intelligent system for risk management, oriented to workers suffering from disease conditions. The developed support system is based on Computer Vision, Machine Learning and Intelligent Agents. Results: The system was applied to a two-arm Cobot scenario during a Learning from Demonstration task for collaborative parts transportation, where risk management is critical. In this environment with a worker suffering from a mental disorder, safety is successfully controlled by means of human/robot coordination, and risk levels are managed through the integration of human/robot behaviour models and worker's models based on the workplace model of the World Health Organization. The results show a promising real-time support tool to coordinate and monitoring these scenarios by integrating workers' health information towards a successful risk management strategy for safe industrial Cobot environments.

Joint Interaction and Mutual Understanding in Social Robotics

Social robotics aims at designing robots capable of joint interaction with humans. On a conceptual level, sufficient mutual understanding is usually said to be a necessary condition for joint interaction. Against this background, the following questions remain open: in which sense is it legitimate to speak of human-robot joint interaction? What exactly does it mean to speak of humans and robots sufficiently understanding each other to account for human-robot joint interaction? Is such joint interaction effectively possible by reference, e.g., to the mere ascription or simulation of understanding? To answer these questions, we first discuss technical approaches which aim at the implementation of certain aspects of human-human communication and interaction in social robots in order to make robots accessible and understandable to humans and, hence, human-robot joint interaction possible. Second, we examine the human tendency to anthropomorphize in this context, with a view to human understanding of and joint interaction with social robots. Third, we analyze the most prominent concepts of mutual understanding and their implications for human-robot joint interaction. We conclude that it is-at least for the time being-not legitimate to speak of human-robot joint interaction, which has relevant implications both morally and ethically.

A Brain-Inspired Theory of Mind Spiking Neural Network for Reducing Safety Risks of Other Agents

Artificial Intelligence (AI) systems are increasingly applied to complex tasks that involve interaction with multiple agents. Such interaction-based systems can lead to safety risks. Due to limited perception and prior knowledge, agents acting in the real world may unconsciously hold false beliefs and strategies about their environment, leading to safety risks in their future decisions. For humans, we can usually rely on the high-level theory of mind (ToM) capability to perceive the mental states of others, identify risk-inducing errors, and offer our timely help to keep others away from dangerous situations. Inspired by the biological information processing mechanism of ToM, we propose a brain-inspired theory of mind spiking neural network (ToM-SNN) model to enable agents to perceive such risk-inducing errors inside others' mental states and make decisions to help others when necessary. The ToM-SNN model incorporates the multiple brain areas coordination mechanisms and biologically realistic spiking neural networks (SNNs) trained with Reward-modulated Spike-Timing-Dependent Plasticity (R-STDP). To verify the effectiveness of the ToM-SNN model, we conducted various experiments in the gridworld environments with random agents' starting positions and random blocking walls. Experimental results demonstrate that the agent with the ToM-SNN model selects rescue behavior to help others avoid safety risks based on self-experience and prior knowledge. To the best of our knowledge, this study provides a new perspective to explore how agents help others avoid potential risks based on bio-inspired ToM mechanisms and may contribute more inspiration toward better research on safety risks.

Supporting Artificial Social Intelligence With Theory of Mind

In this paper, we discuss the development of artificial theory of mind as foundational to an agent's ability to collaborate with human team members. Agents imbued with artificial social intelligence will require various capabilities to gather the social data needed to inform an artificial theory of mind of their human counterparts. We draw from social signals theorizing and discuss a framework to guide consideration of core features of artificial social intelligence. We discuss how human social intelligence, and the development of theory of mind, can contribute to the development of artificial social intelligence by forming a foundation on which to help agents model, interpret and predict the behaviors and mental states of humans to support human-agent interaction. Artificial social intelligence will need the processing capabilities to perceive, interpret, and generate combinations of social cues to operate within a human-agent team. Artificial Theory of Mind affords a structure by which a socially intelligent agent could be imbued with the ability to model their human counterparts and engage in effective human-agent interaction. Further, modeling Artificial Theory of Mind can be used by an ASI to support transparent communication with humans, improving trust in agents, so that they may better predict future system behavior based on their understanding of and support trust in artificial socially intelligent agents.

Visual design intuition: predicting dynamic properties of beams from raw cross-section images

In this work we aim to mimic the human ability to acquire the intuition to estimate the performance of a design from visual inspection and experience alone. We study the ability of convolutional neural networks to predict static and dynamic properties of cantilever beams directly from their raw cross-section images. Using pixels as the only input, the resulting models learn to predict beam properties such as volume maximum deflection and eigenfrequencies with 4.54% and 1.43% mean average percentage error, respectively, compared with the finite-element analysis (FEA) approach. Training these models does not require prior knowledge of theory or relevant geometric properties, but rather relies solely on simulated or empirical data, thereby making predictions based on 'experience' as opposed to theoretical knowledge. Since this approach is over 1000 times faster than FEA, it can be adopted to create surrogate models that could speed up the preliminary optimization studies where numerous consecutive evaluations of similar geometries are required. We suggest that this modelling approach would aid in addressing challenging optimization problems involving complex structures and physical phenomena for which theoretical models are unavailable.

The Increasing Centrality of Robotic Technology in the Context of Nursing Care: Bioethical Implications Analyzed through a Scoping Review Approach

At the dawn of the fourth industrial revolution, the healthcare industry is experiencing a momentous shift in the direction of increasingly pervasive technologization of care. If, up until the 2000s, imagining healthcare provided by robots was a purely futuristic fantasy, today, such a scenario is in fact a concrete reality, especially in some countries, such as Japan, where nursing care is largely delivered by assistive and social robots in both public and private healthcare settings, as well as in home care. This revolution in the context of care, already underway in many countries and destined to take place soon on a global scale, raises obvious ethical issues, related primarily to the progressive dehumanization of healthcare, a process which, moreover, has undergone an important acceleration following the outbreak of the COVID-19 pandemic, which has made it necessary to devise new systems to deliver healthcare services while minimizing interhuman contact. According to leading industry experts, nurses will be the primary users of healthcare robots in the short term. The aim of this study is to provide a general overview, through a scoping review approach, of the most relevant ethical issues that have emerged in the nursing care field in relation to the increasingly decisive role that service robots play in the provision of care. Specifically, through the adoption of the population-concept-context framework, we formulated this broad question: what are the most relevant ethical issues directly impacting clinical practice that arise in nursing care delivered by assistive and social robots? We conducted the review according to the five-step methodology outlined by Arksey and O'Malley. The first two steps, formulating the main research question and carrying out the literature search, were performed based on the population-context-concept (PCC) framework suggested by the Joanna Briggs Institute. Starting from an initial quota of 2,328 scientific papers, we performed an initial screening through a computer system by eliminating duplicated and non-English language articles. The next step consisted of selection based on a reading of the titles and abstracts, adopting four precise exclusion criteria: articles related to a nonnursing environment, articles dealing with bioethical aspects in a marginal way, articles related to technological devices other than robots, and articles that did not treat the dynamics of human-robot relationships in depth. Of the 2,328 titles and abstracts screened, we included 14. The results of the 14 papers revealed the existence of nonnegligible difficulties in the integration of robotic systems within nursing, leading to a lively search for new theoretical ethical frameworks, in which robots can find a place; concurrent with this exploration are the frantic attempts to identify the best ethical design system applicable to robots who work alongside nurses in hospital wards. In the final part of the paper, we also proposed considerations about the Italian nursing context and the legal implications of nursing care provided by robots in light of the Italian legislative panorama. Regarding future perspectives, this paper offers insights regarding robot engagement strategies within nursing.