Trust is a critical factor in human-robot interaction. This study investigates how using human data to train reinforcement learning (RL) agents affects perceived performance and trust. We conducted two experiments: an online study using the video game Seaquest, and a physical robot study involving a wire loop task. In both, RL agents were trained using demonstrations from human users with varying skill levels, as well as without human data. Participants then rated the agents’ performance and how much they trusted them. Our results for the online study indicate that RL agents trained with expert human data received significantly higher trust ratings than other agents, and that trust was higher in replay and long training conditions compared to short and no training. Videos showing beginner players were also trusted, despite lower performance, although these differences did not always reach statistical significance. This highlights that trust is influenced by factors beyond mere performance, suggesting a role for cues such as perceived human involvement. In the physical robot study, our findings indicate that trust was significantly influenced by the type of training data, with data from an experienced human having a positive effect under certain training conditions. Performance ratings were influenced primarily by the training approach, with replay receiving higher ratings than short training. Although trust was notably higher under certain conditions, performance ratings did not always align with trust, indicating a partial dissociation between the two measures. Together, these results suggest that training with high-quality human data can enhance the trustworthiness of RL agents under appropriate training conditions. However, trust depends not only on performance, but also on how human-like an agent's behavior appears. Designing agents for trust-sensitive applications may therefore benefit from aligning behavior with user expectations, rather than optimizing performance alone.

This paper presents a human-centred design study examining how low-fidelity and embodied prototyping methods can elicit design-relevant knowledge for robotic-assisted surgery. Focusing on femoral cement removal in revision total hip arthroplasty (rTHA), we conducted a design-led workshop involving a senior orthopaedic surgeon with expertise in complex revision cases, a surgical assistant, a robotics engineer from an industry partner developing orthopaedic surgical robots, and a team of design researchers. Through scenario-based roleplay, task enactment, and spatial configuration activities, we surfaced tacit, embodied, and situated insights into anatomical factors, instrument design, surgeon–robot ergonomics, shared control models, and operating theatre layout. These findings highlight challenges and opportunities for integrating robotic systems into complex surgical procedures and demonstrate how collaborative exploratory prototyping can support early-stage reflection and interdisciplinary knowledge exchange. Rather than validating a specific solution, the study contributes both a transferable methodological approach for eliciting design insights in high-risk, highly constrained environments, and formative insights into the design of robotic-assisted surgical systems for rTHA.

Eye-tracking-driven controls for assistive robotic arms provide people with severe physical disabilities with intuitive interaction opportunities.In this context, shared control can improve acceptance of the robot by partially automating task execution. Based on recent literature, we present a Wizard of Oz design for shared control driven by eye-tracking. This approach allows for the rapid exploration of user expectations to inform future design iterations. Two studies were conducted to assess user experience, identify design challenges, and determine ways to improve usability and accessibility. The first study involved people with severe motor disabilities (PSMD) and consisted of an online survey. The second study aimed to gain technical insights through direct robot interaction to provide a comprehensive overview of the findings.

The comparatively recent advent of Large Language Models (LLMs) has resulted in a wide array of new capabilities and components relevant to Human–Robot Interaction (HRI) researchers. LLMs are being applied to vision, manipulation, planning, reasoning, learning, and HRI problems, frequently as “Scarecrows,” in which LLMs serve as black box modules integrated into robot architectures for the purpose of quickly enabling full-pipeline solutions. However, despite this explosion of applications, general questions remain about the best ways to incorporate LLMs into robot architectures, appropriate safety and guardrail considerations, and, critically, how to report properly on HRI research that involves LLMs. In this article, we explore the question of reporting guidelines for HRI researchers who utilize Scarecrows in robot architectures. We identify five key stakeholder groups in the HRI research process, discuss what information each group needs from HRI researchers, and identify appropriate mechanisms for conveying that information from HRI researchers to stakeholders either directly or indirectly. We contribute a set of suggested guidelines regarding what information should be included when researchers disseminate information about HRI research that uses LLMs.

Scales are commonly employed in Human–Robot Interaction (HRI) research, yet due to its multidisciplinary nature, many in this community lack direct training in psychometrics. This poses challenges for appropriate scale selection, accurate assessments of reliability and validity, and use. We provide a tutorial to empower researchers without scale development expertise to assess scale quality efficiently. We detail a guideline that provides high-level questions and examples to help the reader make confident evaluations of existing scales in HRI. The guideline is then used to evaluate the Godspeed and Robotic Social Attributes Scale (RoSAS). RoSAS is found to be adequately validated, whereas Godspeed warrants further investigation before it should be used in HRI contexts. The article concludes by offering advice on the use of custom scales and provides references for further enhancing expertise in this domain.

How do robot designers anthropomorphize their own creations? Because robot designers have the ability to alter the robot, identify as its creator, and understand their robot’s internal makeup, their process of anthropomorphism and its outcomes may be different from that of the typical robot user. We investigate this research question in the domain of combat robots, where anthropomorphism is critical to decision-making, communication, and trust in high-stakes, high-emotion combat situations faced by robot-soldier teams. We conducted an in-depth case study of a university’s student-led combat robotics design team over the design, construction, testing, and competition phases for their competitive combat robot. Based on inductive computational and human coding of extensive field notes, supplemented with interviews and surveys, we found that these robot designers anthropomorphize for three purposes. First, they anthropomorphize the bot to manage impressions of it within their team and to outsiders like competitors, spectators, and sponsors, specifically presenting it as a warrior. Second, they anthropomorphize it like a child, a pet, or simply treat it as a non-anthropomorphic mechanical set of parts as a way to calibrate their relationship and attach with or detach from their own creation. Third, they anthropomorphize the bots to assign blame either blaming it, its parts, or others based on their expectations of whether it is performing based on how they designed it. We conclude with implications for anthropomorphism by robot designers and application to military robot design.

Autism Spectrum Disorder (ASD) is a neurodevelopmental condition characterized by differences in social communication and interaction, highlighting the importance of early and supportive engagement. Robot-Assisted Autism Therapy (RAAT) has emerged as a promising approach that utilizes repetitive, interactive sessions to facilitate engagement and learning experiences. This systematic review, conducted following PRISMA guidelines, evaluates advancements in RAAT from 2013 to 2023, addressing three key questions: the benefits and limitations, the metrics used to assess success, and the technological advancements aimed at overcoming challenges. After screening 2,396 papers from IEEE Xplore and ACM Digital Library, 46 studies were included. These studies met the following inclusion criteria: English-language, peer-reviewed journal articles and conference proceedings focusing on RAAT advancements for children, specifically addressing human–robot interaction (HRI) and user experience (UX). The studies were categorized by demographics, methods, robot types, targeted behaviors, HRI modes, UX, and ethical considerations. Our findings highlight a preference for humanoid robots, particularly in sessions supporting imitation and joint attention development. The review also emphasizes the need for user-friendly therapist interfaces and addresses challenges related to robot autonomy. Future research should focus on integrating artificial intelligence and developing comprehensive datasets to fill current gaps in RAAT systems. Overall, this review identifies emerging trends, limitations, and provides guidance for advancing robot-assisted support for autistic children through accessible, engaging, and ethical interaction design.

The integration of human-robot teams is increasingly essential in dynamic task environments, particularly in sectors like warehouse management, assembly lines, search and rescue operations, material handling, and autonomous driving. This trend leverages the complementary strengths of humans and robots to enhance efficiency and tackle complex objectives. However, significant challenges arise due to differences in task execution, communication modes, empathy, mental model understanding, and adaptability between humans and robots. This survey paper examines the complexities of human-robot collaboration (HRC), focusing on the “3 Cs” of teamwork: collaboration, communication, and cognition. It introduces a novel 3Cs rating system to evaluate HRC systems, offering a comprehensive analysis of current research trends and identifying key challenges. The findings highlight a prevalent lack of robot adaptation based on human states and performance, underscoring the need for improved communication metrics and consistent definitions of collaborative frameworks. Key contributions include the development of the 3Cs rating system, an in-depth analysis of HRC research trends, and the identification of critical areas requiring further investigation to realize the full potential of human-robot teams. This paper aims to guide future research and development, promoting more effective human-robot collaborations.

In cooperative training, humans within a team coordinate on complex tasks, building mental models of their teammates and learning to adapt to teammates’ actions in real-time. To reduce the often prohibitive scheduling constraints associated with cooperative training, this article introduces a paradigm for cooperative asynchronous training of human teams in which trainees practice coordination with autonomous teammates rather than humans. We introduce a novel experimental design for evaluating autonomous teammates for use as training partners in cooperative training. We apply this design to a human-subjects experiment where humans are trained with either another human or an autonomous teammate and are evaluated with a new human subject in a new, partially observable, cooperative game developed for this study. Importantly, we employ an unsupervised sequential clustering methodology to partition teammate trajectories from demonstrations performed in the experiment to form a smaller number of training conditions. This results in a simpler experiment design, enabling us to conduct a complex cooperative training human-subjects study in a reasonable amount of time. Through a demonstration of the proposed experimental design, we provide takeaways and design recommendations for future research in the development of cooperative asynchronous training systems utilizing robot surrogates for human teammates.

Developments in the assistive capabilities of robots have allowed them to be more prevalent across domains from manufacturing to healthcare to education. To achieve more efficient and fluent collaborations between robots and humans, it has become necessary to explore how humans trust robot partners during collaborations. Current measurements of human trust in a robot partner typically rely on reflective, subjective survey measures, which are difficult to incorporate and update in the robot’s decision-making models for real-time deployment. To address this challenge, we aim to identify potential objective measures of trust, which can be incorporated into the robot’s decision-making process. We examine physiological data (Electrodermal Activity (EDA), Skin Temperature (TEMP), and Blood Volume Pulse (BVP)) and facial expression in an in-person ( \(n=30\) ) human–robot collaboration study and report the effect of trust on these objective measures. The results indicate that the participants who distrusted the robot partner experienced higher EDA, higher TEMP, and lower BVP variations than participants who trusted the robot. For facial expression, participants who distrusted the robot had more intense facial expressions than participants who trusted the robot. Ultimately, these findings can be used to further research on developing a real-time model of human trust in robots.