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.

To support positive, ethical human-robot interactions, robots need to be able to respond to unexpected situations in which societal norms are violated, including rejecting unethical commands. Implementing robust communication for robots is inherently difficult due to the variability of context in real-world settings and the risks of unintended influence during robots’ communication. HRI researchers have begun exploring the potential use of LLMs as a solution for language-based communication, which will require an in-depth understanding and evaluation of LLM applications in different contexts. In this work, we explore how an existing LLM responds to and reasons about a set of norm-violating requests in HRI contexts. We ask human participants to assess the performance of a hypothetical GPT-4-based robot on moral reasoning and explanatory language selection as it compares to human intuitions. Our findings suggest that while GPT-4 performs well at identifying norm violation requests and suggesting non-compliant responses, its flaws in not matching the linguistic preferences and context sensitivity of humans prevent it from being a comprehensive solution for moral communication between humans and robots. Based on our results, we provide a four-point recommendation for the community in incorporating LLMs into HRI systems.

Due to their unique persuasive power, language-capable robots must be able to both adhere to and communicate human moral norms. These requirements are complicated by the possibility that people may blame humans and robots differently for violating those norms. These complications raise particular challenges for robots giving moral advice to decision makers, as advisors and deciders may be blamed differently for endorsing the same moral action. In this work, we thus explore how people morally evaluate human and robot advisors to human and robot deciders. In Experiment 1 (n = 555), we examine human blame judgments of robot and human moral advisors and find clear evidence for an advice as decision hypothesis: advisors are blamed similarly to how they would be blamed for making the decisions they advised. In Experiment 2 (n = 1326), we examine blame judgments of a robot or human decider following the advice of a robot or human moral advisor. We replicate the results from Experiment 1 and also find clear evidence for a differential dismissal hypothesis: moral deciders are penalized for ignoring moral advice, especially when a robot ignores human advice. Our results raise novel questions about people's perception of moral advice, especially when it involves robots, and present challenges for the design of morally competent robots.

In this work, we present Robots for Social Justice (R4SJ): a framework for an equitable engineering practice of Human-Robot Interaction, grounded in the Engineering for Social Justice (E4SJ) framework for Engineering Education and intended to complement existing frameworks for guiding equitable HRI research. To understand the new insights this framework could provide to the field of HRI, we analyze the past decade of papers published at the ACM/IEEE International Conference on Human-Robot Interaction, and examine how well current HRI research aligns with the principles espoused in the E4SJ framework. Based on the gaps identified through this analysis, we make five concrete recommendations, and highlight key questions that can guide the introspection for engineers, designers, and researchers. We believe these considerations are a necessary step not only to ensure that our engineering education efforts encourage students to engage in equitable and societally beneficial engineering practices (the purpose of E4SJ), but also to ensure that the technical advances we present at conferences like HRI promise true advances to society, and not just to fellow researchers and engineers.

Deployed social robots are increasingly relying on wakeword-based interaction, where interactions are human-initiated by a wakeword like "Hey Jibo". While wakewords help to increase speech recognition accuracy and ensure privacy, there is concern that wakeword-driven interaction could encourage impolite behavior because wakeword-driven speech is typically phrased as commands. To address these concerns, companies have sought to use wakeword design to encourage interactant politeness, through wakewords like "Name?, please". But while this solution is intended to encourage people to use more "polite words", researchers have found that these wakeword designs actually decrease interactant politeness in text-based communication, and that other wakeword designs could better encourage politeness by priming users to use Indirect Speech Acts. Yet there has been no previous research to directly compare these wakewords designs in in-person, voice-based human-robot interaction experiments, and previous in-person HRI studies could not effectively study carryover of wakeword-driven politeness and impoliteness into human-human interactions. In this work, we conceptually reproduced these previous studies (n=69) to assess how the wakewords "Hey "Name"", "Excuse me "Name?", and "Name?, please" impact robot-directed and human-directed politeness. Our results demonstrate the ways that different types of linguistic priming interact in nuanced ways to induce different types of robot-directed and human-directed politeness.

The current work explored to what extent a robot could persuade people to participate in charitable giving by offering moral advice grounded in different ethical theories. In a laboratory, participants, who are students at a university, first performed a task to acquire lottery tickets and then received from a robot information about a charity event organized for students at their university. The robot also offered them moral advice of which the underlying framework was grounded in either deontological or Confucian role ethics to encourage donating their lottery tickets to the event. We found advice grounded in Confucian role ethics to be more effective in inducing donations than advice grounded in deontological ethics. We also found that the more strongly participants felt close to other students at their university, the less donations they would make after receiving advice grounded in deontological ethics. These findings suggest the benefits of framing moral messages of robots based upon theories of Confucian role ethics in promoting prosocial behavior. We discuss potential explanations for the negative relationship between participants’ sense of closeness with other students and their donation behavior when the robot’s advice focuses on theories of deontological ethics.

Because robots are perceived as moral agents, they must behave in accordance with human systems of morality. This responsibility is especially acute for language-capable robots because moral communication is a method for building moral ecosystems. Language capable robots must not only make sure that what they say adheres to moral norms; they must also actively engage in moral communication to regulate and encourage human compliance with those norms. In this work, we describe four experiments (total N =316) across which we systematically evaluate two different moral communication strategies that robots could use to influence human behavior: a norm-based strategy grounded in deontological ethics, and a role-based strategy grounded in role ethics. Specifically, we assess the effectiveness of robots that use these two strategies to encourage human compliance with norms grounded in expectations of behavior associated with certain social roles. Our results suggest two major findings, demonstrating the importance of moral reflection and moral practice for effective moral communication: First, opportunities for reflection on ethical principles may increase the efficacy of robots’ role-based moral language; and second, following robots’ moral language with opportunities for moral practice may facilitate role-based moral cultivation.

Language-capable robots require moral competence, including representations and algorithms for moral reasoning and moral communication. We argue for an ethical pluralist approach to moral competence that leverages and combines disparate ethical frameworks, and specifically argue for an approach to moral competence that is grounded not only in Deontological norms (as is typical in the HRI literature) but also in Confucian relational roles. To this end, we introduce the first computational approach that centers relational roles in moral reasoning and communication, and demonstrate the ability of this approach to generate both context-oriented and role-oriented explanations for robots' rejections of norm-violating commands, which we justify through our pluralist lens. Moreover, we provide the first investigation of how computationally generated role-based expla-nations are perceived by humans, and empirically demonstrate (N=120) that the effectiveness (in terms of of trust, understanding confidence, and perceived intelligence) of explanations grounded in different moral frameworks is dependent on nuanced mental modeling of human interlocutors.

For enhanced performance and privacy, companies deploying voice-activated technologies such as virtual assistants and robots are increasingly tending toward designs in which technologies only begin attending to speech once a specified wakeword is heard. Due to concerns that interactions with such technologies could lead users, especially children, to develop impolite habits, some companies have begun to develop use modes in which interactants are required to use ostensibly polite wakewords such as “ Please”. In this paper, we argue that these “please-centering” wakewords are likely to backfire and actually discourage polite interactions due to the particular types of lexical and syntactic priming induced by those wakewords. We then present the results of a human-subject experiment (n=90) that validates those claims.

For robots to successfully operate as members of human-robot teams, it is crucial for robots to correctly understand the intentions of their human teammates. This task is particularly difficult due to human sociocultural norms: for reasons of social courtesy (e.g., politeness), people rarely express their intentions directly, instead typically employing polite utterance forms such as Indirect Speech Acts (ISAs). It is thus critical for robots to be capable of inferring the intentions behind their teammates' utterances based on both their interaction context (including, e.g., social roles) and their knowledge of the sociocultural norms that are applicable within that context. This work builds off of previous research on understanding and generation of ISAs using Dempster-Shafer Theoretic Uncertain Logic, by showing how other recent work in Dempster-Shafer Theoretic rule learning can be used to learn appropriate uncertainty intervals for robots' representations of sociocultural politeness norms.

There is a significant body of research seeking to enable moral decision making and ensure moral conduct in robots. One aspect of moral conduct is rejecting immoral human commands. For social robots, which are expected to follow and maintain human moral and sociocultural norms, it is especially important not only to engage in moral decision making, but also to properly communicate moral reasoning. We thus argue that it is critical for robots to carefully phrase command rejections. Specifically, the degree of politeness-theoretic face threat in a command rejection should be proportional to the severity of the norm violation motivating that rejection. We present a human subjects experiment showing some of the consequences of miscalibrated responses, including perceptions of the robot as inappropriately polite, direct, or harsh, and reduced robot likeability. This experiment intends to motivate and inform the design of algorithms to tactfully tune pragmatic aspects of command rejections autonomously.