Robot learning from humans has been proposed and researched for several decades as a means to enable robots to learn new skills or adapt existing ones to new situations. Recent advances in AI, including learning approaches like reinforcement learning and architectures like transformers and foundation models, combined with access to massive datasets, have created attractive opportunities to apply those data-hungry techniques to this problem. We argue that the focus on massive amounts of pre-collected data, and the resulting learning paradigm, where humans demonstrate and robots learn in isolation, is overshadowing a specialized area of work we term Human-Interactive Robot Learning (HIRL). This paradigm, wherein robots and humans interact during the learning process , is at the intersection of multiple fields (AI, robotics, human–computer interaction, design and others) and holds unique promise. Using HIRL, robots can achieve greater sample efficiency (as humans can provide task knowledge through interaction), align with human preferences (as humans can guide the robot behavior toward their expectations), and explore more meaningfully and safely (as humans can utilize domain knowledge to guide learning and prevent catastrophic failures). This can result in robotic systems that can more quickly and easily adapt to new tasks in human environments. The objective of this article is to provide a broad and consistent overview of HIRL research and to guide researchers toward understanding the scope of HIRL, and current open or underexplored challenges related to four themes—namely, human, robot learning, interaction, and broader context. The article includes concrete use cases to illustrate the interaction between these challenges and inspire further research according to broad recommendations and a call for action for the growing HIRL community.

In an interdisciplinary and evolving research field like human-robot interaction, clear and precise results reporting is essential for study comparability and replicability. To address the lack of a standard for such reporting and, at the same time, provide guidance for novices in the field, we have developed a web-based reporting form to capture human-robot interaction studies, serving as a model for how conferences could adopt it into the submission pipeline. In this work, we present a formative evaluation of this form regarding its level of detail, format and clarity, and the perceived benefits for authors, reviewers, and the community as a whole. We report the expert review of nine researchers who highlight the substantial value of this tool. In addition, these experts also provide suggestions for improvements to its form and the addition of details surrounding qualitative reporting.

In social robots, visual attention expresses awareness of the scenario components and dynamics. As in humans, their attention should be driven by a combination of different attention mechanisms. In this article, we introduce multi-modal saliency maps, i.e., spatial representations of saliency that dynamically integrate multiple attention sources depending on the context. We provide the mathematical formulation of the model and an open source software implementation. Finally, we present an initial exploration of its potential in social interaction scenarios with humans and evaluate its implementation.

Abstract Socially assistive robots represent a promising tool in assistive contexts for improving people’s quality of life and well-being through social, emotional, cognitive, and physical support. However, the effectiveness of interactions heavily relies on the robots’ ability to adapt to the needs of the assisted individuals and to offer support proactively, before it is explicitly requested. Previous work has primarily focused on defining the actions the robot should perform, rather than considering when to act and how confident it should be in a given situation. To address this gap, this paper introduces a new data-driven framework that involves a learning pipeline, consisting of two phases, with the ultimate goal of training an algorithm based on Influence Diagrams. The proposed assistance scenario involves a sequential memory game, where the robot autonomously learns what assistance to provide when to intervene, and with what confidence to take control. The results from a user study showed that the proactive behaviour of the robot had a positive impact on the users’ game performance. Users obtained higher scores, made fewer mistakes, and requested less assistance from the robot. The study also highlighted the robot’s ability to provide assistance tailored to users’ specific needs and anticipate their requests.

While Automatic Speech Recognition (ASR) systems excel in controlled environments, challenges arise in robot-specific setups due to unique microphone requirements and added noise sources. In this paper, we create a dataset of initiating conversations with brief exchanges in 5 European languages, and we systematically evaluate current state-of-art ASR systems (Vosk, OpenWhisper, Google Speech and NVidia Riva). Besides standard metrics, we also look at two critical downstream tasks for human-robot verbal interaction: intent recognition rate and entity extraction, using the open-source Rasa chatbot. Overall, we found that open-source solutions as Vosk performs competitively with closed-source solutions while running on the edge, on a low compute budget (CPU only).

Frailty assessment plays a pivotal role in providing older adults care. However, the current process is time-consuming and only measures patients’ completion time for each test. This paper introduces a set of algorithms to be used in robots to autonomously perform frailty assessments. In doing so we aim at reducing therapists’ burden and provide additional frailty-related metrics that can enhance the effectiveness of diagnosis. We conducted a pilot study with 22 elderly participants and compared our system’s performance with that of medical professionals to assess its precision. The results demonstrate that our approach achieved performances close to that of its human counterpart. This research represents an important step forward in the integration of social robotics in healthcare, offering potential benefits for patient care and clinical decision-making.

As robots become more and more integrated in human spaces, it is increasingly important for them to be able to explain their decisions to the people they interact with. These explanations need to be generated automatically and in real-time in response to decisions taken in dynamic and often unstructured environments. However, most research in explainable human-robot interaction only considers explanations (often manually selected) presented in controlled environments. We present an explanation generation method based on counterfactuals and demonstrate its use in an "in-the-wild" experiment using automatically generated and selected explanations of autonomous interactions with real people to assess the effect of these explanations on participants’ ability to predict the robot’s behaviour in hypothetical scenarios. Our results suggest that explanations aid one’s ability to predict the robot’s behaviour, but also that the addition of counterfactual statements may add some burden and counteract this beneficial effect.

In the future, robots are expected to autonomously interact and/or collaborate with humans, who will increase the uncertainty during the execution of tasks, provoking online adaptations of robots' plans. Hence, trustworthy robots must be able to store, retrieve and narrate important knowledge about their collaborations and adaptations. In this article, it is proposed a sound methodology that integrates three main elements. First, an ontology for collaborative robotics and adaptation to model the domain knowledge. Second, an episodic memory for time-indexed knowledge storage and retrieval. Third, a novel algorithm to extract the relevant knowledge and generate textual explanatory narratives. The algorithm produces three different types of outputs, varying the specificity, for diverse uses and preferences. A pilot study was conducted to evaluate the usefulness of the narratives, obtaining promising results. Finally, we discuss how the methodology can be generalized to other ontologies and experiences. This work boosts robot explainability, especially in cases where robots need to narrate the details of their short and long-term past experiences.

Enabling a robot to perform new tasks is a complex endeavor, usually beyond the reach of non-technical users. For this reason, research efforts that aim at empowering end-users to teach robots new abilities using intuitive modes of interaction are valuable. In this article, we present INtuitive PROgramming 2 (INPRO2), a learning framework that allows inferring planning actions from demonstrations given by a human teacher. INPRO2 operates in an assistive scenario, in which the robot may learn from a healthcare professional (a therapist or caregiver) new cognitive exercises that can be later administered to patients with cognitive impairment. INPRO2 features significant improvements over previous work, namely: (1) exploitation of negative examples; (2) proactive interaction with the teacher to ask questions about the legality of certain movements; and (3) learning goals in addition to legal actions. Through simulations, we show the performance of different proactive strategies for gathering negative examples. Real-world experiments with human teachers and a TIAGo robot are also presented to qualitatively illustrate INPRO2.

The ability to impact the attitudes and behaviours of others is a key aspect of human-human interaction. The same capability is a desideratum in human-robot interaction when it can have an impact on healthy behaviours. The robot’s interaction style plays a significant role in achieving effective communication, leading to better outcomes, improved user experience, and overall enhanced robot performance. Nonetheless, little is known about how different robots’ communication styles impact users’ performance and decision-making. In this article, we build upon previous work, in which a robot was endowed with two personality behavioural patterns: one more antagonist and other-comparative and the other one more agreeable and self-comparative. We conducted a user study where N = 66 participants played a game with a robot displaying the two multimodal communication styles. Our results indicated that i) participants’ decision-making was not influenced by the designed robot’s communication styles, ii) participants who interacted with the agreeable robot performed better in the game, and iii) the more participants are knowledgeable about robots, the lower they performed in the game.

Abstract Socially assistive robots have the potential to augment and enhance therapist’s effectiveness in repetitive tasks such as cognitive therapies. However, their contribution has generally been limited as domain experts have not been fully involved in the entire pipeline of the design process as well as in the automatisation of the robots’ behaviour. In this article, we present aCtive leARning agEnt aSsiStive bEhaviouR (CARESSER), a novel framework that actively learns robotic assistive behaviour by leveraging the therapist’s expertise (knowledge-driven approach) and their demonstrations (data-driven approach). By exploiting that hybrid approach, the presented method enables in situ fast learning, in a fully autonomous fashion, of personalised patient-specific policies. With the purpose of evaluating our framework, we conducted two user studies in a daily care centre in which older adults affected by mild dementia and mild cognitive impairment ( N = 22) were requested to solve cognitive exercises with the support of a therapist and later on of a robot endowed with CARESSER. Results showed that: (i) the robot managed to keep the patients’ performance stable during the sessions even more so than the therapist; (ii) the assistance offered by the robot during the sessions eventually matched the therapist’s preferences. We conclude that CARESSER, with its stakeholder-centric design, can pave the way to new AI approaches that learn by leveraging human–human interactions along with human expertise, which has the benefits of speeding up the learning process, eliminating the need for the design of complex reward functions, and finally avoiding undesired states.

The aim of this workshop is to foster the exchange of insights on past and ongoing research towards effective and long-lasting collaborations between humans and robots. This workshop will provide a forum for representatives from academia and industry communities to analyse the different aspects of HRI that impact on its success. We particularly focus on AI techniques required to implement autonomous and proactive interactions, on the factors that enhance, undermine, or recover humans' acceptance and trust in robots, and on the potential ethical and legal concerns related to the deployment of such robots in human-centred environments. Website: https://sites.google.com/view/trains-hri-2022.

The success of human-robot interaction is strongly affected by the people’s ability to infer others’ intentions and behaviours, and the level of people’s trust that others will abide by their same principles and social conventions to achieve a common goal. The ability of understanding and reasoning about other agents’ mental states is known as Theory of Mind (ToM). ToM and trust, therefore, are key factors in the positive outcome of human-robot interaction. We believe that a robot endowed with a ToM is able to gain people’s trust, even when this may occasionally make errors.In this work, we present a user study in the field in which participants (N=123) interacted with a robot that may or may not have a ToM, and may or may not exhibit erroneous behaviour. Our findings indicate that a robot with ToM is perceived as more reliable, and they trusted it more than a robot without a ToM even when the robot made errors. Finally, ToM results to be a key driver for tuning people’s trust in the robot even when the initial condition of the interaction changed (i.e., loss and regain of trust in a longer relationship).

In this paper, we present a learning approach to facilitate the teaching of new board exercises to assistive robotic systems. We formulate the problem as the learning of action models using Boolean predicates, disjunctive preconditions, and existential quantifiers from demonstrations of successful exercise executions. To be able to cope with exercises whose rules depend on a set of features that are initialized at the beginning of each play-out, we introduce the concept of dynamic context. Furthermore, we show how the learnt knowledge can be represented intuitively in a graphical interface that helps the caregiver understand what the system has learnt. As validation, we conducted a user study in which we evaluated whether and to which extent different types of feedback can affect the subjects’ performance while teaching three types of exercises: (1) sorting numbers; (2) arranging letters; and (3) reproducing shapes sequences in reversed order. The results suggest that textual and graphical feedback are beneficial.

Robots are expected to become part of everyday life. However, while there have been important breakthroughs during the recent decades in terms of technological advances, the ability of robots to interact with humans intuitively and effectively is still an open challenge. In this paper, we aim to evaluate how humans interpret and leverage backchannel cues exhibited by a robot which interacts with them in an entertainment context. To do so, a conceptual model was designed to investigate the legibility and the effectiveness of a designed social cue, called SOCial ImmediAcy BackchanneL cuE (SOCIABLE), on participant's performance. In addition, user's attitude and cognitive capability were integrated into the model as an estimator of participants' motivation and ability to process the cue. In working toward such a goal, we conducted a two-day long user study (N=114) at an international event with untrained participants who were not aware of the social cue the robot was able to provide. The results showed that participants were able to perceive the social signal generated from SOCIABLE and thus, they benefited from it. Our findings provide some important insights for the design of effective and instantaneous backchannel cues and the methodology for evaluating them in social robots.

Collecting data in Human-Robot Interaction for training learning agents might be a hard task to accomplish. This is especially true when the target users are older adults with dementia since this usually requires hours of interactions and puts quite a lot of workload on the user. This paper addresses the problem of importing the Personas technique from HRI to create fictional patients' profiles. We propose a Persona-Behaviour Simulator tool that provides, with high-level abstraction, user's actions during an HRI task, and we apply it to cognitive training exercises for older adults with dementia. It consists of a Persona Definition that characterizes a patient along four dimensions and a Task Engine that provides information regarding the task complexity. We build a simulated environment where the high-level user's actions are provided by the simulator and the robot initial policy is learned using a Q-learning algorithm. The results show that the current simulator provides a reasonable initial policy for a defined Persona profile. Moreover, the learned robot assistance has proved to be robust to potential changes in the user's behaviour. In this way, we can speed up the fine-tuning of the rough policy during the real interactions to tailor the assistance to the given user. We believe the presented approach can be easily extended to account for other types of HRI tasks; for example, when input data is required to train a learning algorithm, but data collection is very expensive or unfeasible. We advocate that simulation is a convenient tool in these cases.