Language-enabled robots with moral reasoning capabilities will inevitably face situations in which they have to respond to human commands that might violate normative principles and could cause harm to humans. We believe that it is critical for robots to be able to reject such commands. We thus address the two key challenges of when and how to reject norm-violating directives. First, we present research in both engineering language-enabled robots that can engage in rudimentary rejection dialogues, as well as related HRI research into the effectiveness of robot protest. Second, we argue that how rejections are phrased is important and review the factors that should guide natural language formulations of command rejections. Finally, we conclude by identifying relevant open questions that will further inform the design of future language-capable and morally competent robots.

具有道德推理能力的支持语言的机器人将不可避免地面临这样的情况，即他们必须应对可能违反规范原则并可能对人类造成伤害的人类命令。我们认为，对于机器人来说，拒绝此类命令至关重要。因此，我们应对何时以及如何拒绝违反规范的指令的两个关键挑战。首先，我们介绍了可以进行基本拒绝对话的支持工程语言的机器人的研究，以及有关机器人抗议有效性的相关HRI研究。其次，我们认为如何拒绝的措辞很重要，并回顾应指导命令拒绝的自然语言表述的因素。最后，我们通过确定相关的开放性问题作为结束语，这些问题将进一步为未来具有语言能力和道德能力的机器人的设计提供信息。