Teacher, Teammate, Subordinate, Friend: Generating Norm Violation Responses Grounded in Role-based Relational Norms

Wen, Ruchen; Han, Zhao; Williams, Tom

doi:10.1109/hri53351.2022.9889594

Cited by 12 publications

(1 citation statement)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Robots are not only capable of influencing humans to comply with their requests and commands (Bartneck et al 2010;Cormier et al 2013;Rea, Geiskkovitch, and Young 2017), but can also exert moral influence over human moral norm systems Williams 2019, 2018;Williams, Jackson, and Lockshin 2018). It is thus important for robots to use their persuasive power in a way that is going to help regulate people's behavior and preserve a better moral ecosystem, by rejecting unethical commands (Briggs et al 2021;Wen, Han, and Williams 2022) and calling out norm-violating behavior (Winkle et al 2022(Winkle et al , 2021Jung, Martelaro, and Hinds 2015). For example, imagine a scenario where a robot and a team of humans are working together on a collaborative task, and one of the human Presented at the AI-HRI Symposium at AAAI Fall Symposium Series (FSS) 2022 teammate verbally abuses another team member who accidentally made a mistake.…”

Section: Introductionmentioning

confidence: 99%

Hidden Complexities in the Computational Modeling of Proportionality for Robotic Norm Violation Response

Wen¹,

Williams²

2022

Preprint

View full text Add to dashboard Cite

Language-capable robots hold unique persuasive power over humans, and thus can help regulate people's behavior and preserve a better moral ecosystem, by rejecting unethical commands and calling out norm violations. However, miscalibrated norm violation responses (when the harshness of a response does not match the actual norm violation severity) may not only decrease the effectiveness of human-robot communication, but may also damage the rapport between humans and robots. Therefore, when robots respond to norm violations, it is crucial that they consider both the moral value of their response (by considering how much positive moral influence their response could exert) and the social value (by considering how much face threat might be imposed by their utterance). In this paper, we present a simple (naive) mathematical model of proportionality which could explain how moral and social considerations should be balanced in multiagent norm violation response generation. But even more importantly, we use this model to start a discussion about the hidden complexity of modeling proportionality, and use this discussion to identify key research directions that must be explored in order to develop socially and morally competent language-capable robots.

show abstract