The ability to provide useful and intuitive explanations remains one of the major hurdles to creating robotic systems capable of working effectively with everyday users. In this paper, we consider a popular explanation generation framework for robot task plans, namely model reconciliation, and try to address one of its main drawbacks, namely its inability to generate actionable explanations. The current methods for generating model reconciliation focus on generating information that explains why the robot chose a certain behavior over one that was expected by the human. However, the user might also want to understand how they can influence the robot's behavior so it follows the one that was expected from it. Explanations that provide such information are called actionable, and we extend traditional model reconciliation explanations to be actionable by combining them with the existing notion of excuses. We will refer to the resulting explanations as Actionable Reconciliation Explanations (ARE), which explains the robot's decision-making process and suggests how its model might be modified for improved alignment with human expectations. However, as we will see, the generation of ARE requires methods that are distinct from existing model reconciliation and excuse generation methods, and ARE also exhibits properties that are distinct from these earlier methods. We assess our method through computational experiments and user studies and, in the process, also compare it against traditional forms of excuses and model reconciliation explanations.

For future human-autonomous vehicle (AV) interactions to be effective and smooth, human-aware systems that analyze and align human needs with automation decisions are essential. Achieving this requires systems that account for human cognitive states. We present a novel computational model in the form of a Dynamic Bayesian Network (DBN) that infers the cognitive states of both AV users and other road users, integrating this information into the AV's decision-making process. Specifically, our model captures the ``well-being'' of both an AV user and an interacting road user as cognitive states alongside trust. Our DBN models infer beliefs over the AV user’s evolving well-being, trust, and intention states, as well as the possible well-being of other road users, based on observed interaction experiences. Using data collected from an interaction study, we refine the model parameters and empirically assess its performance. Finally, we extend our model into a causal inference model (CIM) framework for AV decision-making, enabling the AV to enhance user well-being and trust while balancing these factors with its own operational costs and the well-being of interacting road users. Our evaluation demonstrates the model’s effectiveness in accurately predicting user's states and guiding informed, human-centered AV decisions.

In scenarios involving robots generating and executing plans, conflicts can arise between cost-effective robot execution and meeting human expectations for safe behavior. When humans supervise robots, their accountability increases, especially when robot behavior deviates from expectations. To address this, robots may choose a highly constrained plan when monitored and a more optimal one when unobserved. While this behavior is not driven by human-like motives, it stems from robots accommodating diverse supervisors. To optimize monitoring costs while ensuring safety, we model this interaction in a trust-based game-theoretic framework. However, pure-strategy Nash equilibrium often fails to exist in this model. To address this, we introduce the concept of a trust boundary within the mixed strategy space, aiding in the discovery of optimal monitoring strategies. Human studies demonstrate the necessity of optimal strategies and the benefits of our suggested approaches.

In this work, we design an Artificially Intelligent Task Allocator (AITA) that proposes a task allocation for a team of humans. A key property of this allocation is that when an agent with imperfect knowledge (about their teammate's costs and/or the team's performance metric) contests the allocation with a counterfactual, a contrastive explanation can always be provided to showcase why the proposed allocation is better than the proposed counterfactual. For this, we consider a negotiation process that produces a negotiation-aware task allocation and, when contested, leverages a negotiation tree to provide a contrastive explanation. With human subject studies, we show that the proposed allocation indeed appears fair to a majority of participants and, when not, the explanations generated are judged as convincing and easy to comprehend.

Trust between team members is an essential requirement for any successful cooperation. Thus, engendering and maintaining the fellow team members' trust becomes a central responsibility for any member trying to not only successfully participate in the task but to ensure the team achieves its goals. The problem of trust management is particularly challenging in mixed human-robot teams where the human and the robot may have different models about the task at hand and thus may have different expectations regarding the current course of action, thereby forcing the robot to focus on the costly explicable behavior. We propose a computational model for capturing and modulating trust in such iterated human-robot interaction settings, where the human adopts a supervisory role. In our model, the robot integrates human's trust and their expectations about the robot into its planning process to build and maintain trust over the interaction horizon. By establishing the required level of trust, the robot can focus on maximizing the team goal by eschewing explicit explanatory or explicable behavior without worrying about the human supervisor monitoring and intervening to stop behaviors they may not necessarily understand. We model this reasoning about trust levels as a meta reasoning process over individual planning tasks. We additionally validate our model through a human subject experiment.

In this work, we investigate and model how human trust affects monitoring. We present a web-based human subject study in which the robot is a worker and the human plays the role of a supervisor. First, we evaluate the correlation between the human trust and monitoring by using statistical tests, and then we learn probabilistic models of the behavioral data collected through our user studies. These models can provide us with the likelihood of a human user monitoring a system given their level of trust. Such models can be leveraged in many systems including the ones designed to be resilient to automation bias and complacency.

Recent work has formalized the explanation process in the context of automated planning as one of model reconciliation - i.e. a process by which the planning agent can bring the explainee's (possibly faulty) model of a planning problem closer to its understanding of the ground truth until both agree that its plan is the best possible. The content of explanations can thus range from misunderstandings about the agent's beliefs (state), desires (goals) and capabilities (action model). Though existing literature has considered different kinds of these model differences to be equivalent, literature on the explanations in social sciences has suggested that explanations with similar logical properties may often be perceived differently by humans. In this brief report, we explore to what extent humans attribute importance to different kinds of model differences that have been traditionally considered equivalent in the model reconciliation setting. Our results suggest that people prefer the explanations which are related to the effects of actions.