More Like this

1. Investigating Robot Moral Advice to Deter Cheating Behavior

   Kim, Boyoung ; Wen, Ruchen ; de Visser, Ewart J. ; Zhu, Qin ; Williams, Tom ; Phillips, Elizabeth ( January 2021 , TSAR Workshop at ROMAN 2021)

   null (Ed.)

   We examined whether a robot that proactively offers moral advice promoting the norm of honesty can discourage people from cheating. Participants were presented with an opportunity to cheat in a die-rolling game. Prior to playing the game, participants received from either a NAO robot or a human, a piece of moral advice grounded in either deontological, virtue, or Confucian role ethics, or did not receive any advice. We found that moral advice grounded in Confucian role ethics could reduce cheating when the advice was delivered by a human. No advice was effective when a robot delivered moral advice. These findings highlight challenges in building robots that can possibly guide people to follow moral norms. 

   more » « less
2. Comparing Norm-Based and Role-Based Strategies for Robot Communication of Role-Grounded Moral Norms

   https://doi.org/10.1145/3571719  

   Wen, Ruchen ; Kim, Boyoung ; Phillips, Elizabeth ; Zhu, Qin ; Williams, Tom ( September 2023 , ACM Transactions on Human-Robot Interaction)

   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. 

   more » « less
3. Comparing Strategies for Robot Communication of Role-Grounded Moral Norms

   https://doi.org/10.1145/3434074.3447185  

   Wen, Ruchen ; Kim, Boyoung ; Phillips, Elizabeth ; Zhu, Qin ; Williams, Tom ( March 2021 , ACM/IEEE International Conference on Human-Robot Interaction)

   null (Ed.)

   Because robots are perceived as moral agents, they hold significant persuasive power over humans. It is thus crucial for robots to behave in accordance with human systems of morality and to use effective strategies for human-robot moral communication. In this work, we evaluate two moral communication strategies: a norm-based strategy grounded in deontological ethics, and a role-based strategy grounded in role ethics, in order to test the effectiveness of these two strategies in encouraging compliance with norms grounded in role expectations. Our results suggest two major findings: (1) reflective exercises may increase the efficacy of role-based moral language and (2) opportunities for moral practice following robots’ use of moral language may facilitate role-centered moral cultivation. 

   more » « less
4. Kantian one day, Consequentialist the next: Moral emotions as mediators between ethical frameworks for robots

   Wagner, A. ; Borenstein, J. ; and Arkin, R. ( June 2019 , 2019 Conference of the International Association for Computing and Philosophy (IACAP 2019))

   The field of machine ethics in the process of designing and developing the computational underpinnings necessary for a robot to make ethical decisions in real-world environments. Yet a key issue faced by machine ethics researchers is the apparent lack of consensus as to the existence and nature of a correct moral theory. Our research seeks to grapple with, and perhaps sidestep, this age-old and ongoing philosophical problem by creating a robot architecture that does not strictly rely on one particular ethical theory. Rather, it would be informed by the insights gleaned from multiple ethical frameworks, perhaps including Kantianism, Utilitarianism, and Ross’s duty based ethical theory, and by moral emotions. Arguably, moral emotions are an integral part of a human’s ethical decision-making process and thus need to be accounted for if robots are to make decisions that roughly approximate how humans navigate through ethically complex circumstances. The aim of this presentation is to discuss the philosophical aspects of our approach. 

   more » « less
5. Kantian one day, Consequentialist the next: Moral emotions as mediators between ethical frameworks for robots

   Wagner, A. ; Borenstein, J. ; Arkin, R. ( June 2019 , 2019 Conference of the International Association for Computing and Philosophy (IACAP 2019))

   The field of machine ethics in the process of designing and developing the computational underpinnings necessary for a robot to make ethical decisions in real-world environments. Yet a key issue faced by machine ethics researchers is the apparent lack of consensus as to the existence and nature of a correct moral theory. Our research seeks to grapple with, and perhaps sidestep, this age-old and ongoing philosophical problem by creating a robot architecture that does not strictly rely on one particular ethical theory. Rather, it would be informed by the insights gleaned from multiple ethical frameworks, perhaps including Kantianism, Utilitarianism, and Ross’s duty-based ethical theory, and by moral emotions. Arguably, moral emotions are an integral part of a human’s ethical decision-making process and thus need to be accounted for if robots are to make decisions that roughly approximate how humans navigate through ethically complex circumstances. The aim of this presentation is to discuss the philosophical aspects of our approach. 

   more » « less