This article presents a cross-cultural replication of recent work on productively violating gender norms; specifically demonstrating that breaking norms can boost robot credibility while avoiding harmful stereotypes. In this work we demonstrate via a 3 (country) x 3 (robot behaviour) between-subject experiment that these findings replicate cross-culturally across the US, Sweden, and Japan, finding evidence that breaking gender norms boosts robot credibility regardless of gender or cultural context, and regardless of pretest gender biases. Our findings further motivate a call for feminist robots that subvert the existing gender norms of robot design.

The design of current natural language-oriented robot architectures enables certain architectural components to circumvent moral reasoning capabilities. One example of this is reflexive generation of clarification requests as soon as referential ambiguity is detected in a human utterance. As shown in previous research, this can lead robots to (1) miscommunicate their moral dispositions and (2) weaken human perception or application of moral norms within their current context. We present a solution to these problems by performing moral reasoning on each potential disambiguation of an ambiguous human utterance and responding accordingly, rather than immediately and naively requesting clarification. We implement our solution in the Distributed Integrated Cognition Affect and Reflection robot architecture, which, to our knowledge, is the only current robot architecture with both moral reasoning and clarification request generation capabilities. We then evaluate our method with a human subjects experiment, the results of which indicate that our approach successfully ameliorates the two identified concerns.

Acceptance of social robots in human-robot collaborative environments depends on the robots’ sensitivity to human moral and social norms. Robot behavior that violates norms may decrease trust and lead human interactants to blame the robot and view it negatively. Hence, for long-term acceptance, social robots need to detect possible norm violations in their action plans and refuse to perform such plans. This paper integrates the Distributed, Integrated, Affect, Reflection, Cognition (DIARC) robot architecture (implemented in the Agent Development Environment (ADE)) with a novel place recognition module and a norm-aware task planner to achieve context-sensitive moral reasoning. This will allow the robot to reject inappropriate commands and comply with context-sensitive norms. In a validation scenario, our results show that the robot would not comply with a human command to violate a privacy norm in a private context.

A key capability of morally competent robots is to reject or question potentially immoral human commands. However, robot rejections of inappropriate commands must be phrased with great care and tact. Previous research has shown that failure to calibrate the "face threat" in a robot's command rejection to the severity of the norm violation in the command can lead humans to perceive the robot as inappropriately harsh and can needlessly decrease robot likeability. However, it is well-established that gender plays a significant role in determining linguistic politeness norms and that people have a powerful natural tendency to gender robots. Yet, the effect of robotic gender presentation on these noncompliance interactions is not well understood. We present an experiment that explores the effects of robot and human gender on perceptions of robots in noncompliance interactions, and find evidence of a complicated interplay between these gendered factors. Our results suggest that (1) it may be more favorable for a male robot to reject commands than for a female robot to do so, (2) it may be more favorable to reject commands given by a male human than by a female human, and (3) that robots may be perceived more favorably when their gender matches that of human interactants and observers.

This paper describes early work at the intersection of robot ethics and natural language generation investigating two overarching questions: (1) how might current language generation algorithms generate utterances with unintended implications or otherwise accidentally alter the ecosystem of human norms, and (2) how can we design future language systems such that they purposefully influence the human normative ecosystem as productively as possible.

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.

As robots become more capable, they will become increasingly useful in a widening variety of contexts and applications. Non-roboticists in these diverse contexts will need to interact with their new robotic colleagues to facilitate productive human-robot teaming and comfortable coexistence in social environments. Natural language provides a medium for these interactions that will allow direct and fluid communication between robots and nearly all humans, without requiring specialized protocols or hardware. Indeed, many researchers have been actively investigating the problems of natural language understanding and generation in robots for some time [1]-[3].

Previous research in moral psychology and human-robot interaction has shown that technology shapes human morality, and research in human-robot interaction has shown that humans naturally perceive robots as moral agents. Accordingly, we propose that language-capable autonomous robots are uniquely positioned among technologies to significantly impact human morality. We therefore argue that it is imperative that language-capable robots behave according to human moral norms and communicate in such a way that their intention to adhere to those norms is clear. Unfortunately, the design of current natural language oriented robot architectures enables certain architectural components to circumvent or preempt those architectures' moral reasoning capabilities. In this paper, we show how this may occur, using clarification request generation in current dialog systems as a motivating example. Furthermore, we present experimental evidence that the types of behavior exhibited by current approaches to clarification request generation can cause robots to (1) miscommunicate their moral intentions and (2) weaken humans' perceptions of moral norms within the current context. This work strengthens previous preliminary findings, and does so within an experimental paradigm that provides increased external and ecological validity over earlier approaches.

As smart speakers like the Amazon Echo become more popular, they have given rise to rampant concerns regarding user privacy. This work investigates machine learning techniques to extract ostensibly private information from the TCP traffic moving between an Echo device and Amazon's servers, despite the fact that all such traffic is encrypted. Specifically, we investigate a supervised classification problem using six machine learning algorithms and three feature vectors. Our "request type classification" problem seeks to determine what type of user request is being answered by the Echo (again, even though the requests are encrypted). With six classes, we achieve 97% accuracy in this task using random forests.