Titlebook: Explainable Human-AI Interaction; A Planning Perspecti Sarath Sreedharan,Anagha Kulkarni,Subbarao Kambham Book 2022 Springer Nature Switzer

MAPLE

Explanation as Model Reconciliation,xplanations. Rather than force the robot to choose behaviors that are inherently explicable in the human model, here we will let the robot choose a behavior optimal in its model and use communication to address the central reason why the human is confused about the behavior in the first place, i.e.,

maintenance

Acquiring Mental Models for Explanations, strong assumptions. Particularly, the setting assumes that the human’s model of the robot is known exactly upfront. In this chapter, we will look at how we can relax this assumption and see how we can perform model reconciliation in scenarios where the robot has progressively less information about

可能性

Balancing Communication and Behavior,del of the robot. We have been quantifying some of the interaction between the behavior and human’s model in terms of three interpretability scores, each of which corresponds to some desirable property one would expect the robot behavior to satisfy under cooperative scenarios. With these measures de

ineluctable

Explaining in the Presence of Vocabulary Mismatch,. This suggests that the human and the robot share a common vocabulary that can be used to describe the model. However, this cannot be guaranteed unless the robots are using models that are specified by an expert. Since many of the modern AI systems rely on learned models, they may use representatio

落叶剂

PET-scan

Applications,in this chapter will explicitly model the human’s mental model of the task and among other things use it to generate explanations. In particular, we will look at two broad application domains. One where the systems are designed for collaborative decision-making, i.e., systems designed to help user c

为现场

WAIL

1939-4608 ons when needed. The authors draw from several years of research in their lab to discuss how an AI agent can use these mental models to either conform to human 978-3-031-03757-3978-3-031-03767-2Series ISSN 1939-4608 Series E-ISSN 1939-4616

Aids209

https://doi.org/10.1007/978-0-387-30441-0nication of objectives might not always be suitable. For instance, the . and . of explicit communication may require additional thought. Further, several other aspects like cost of communication (in terms of resources or time), delay in communication (communications signals may take time to reach th

Tidious

An Overview of Stochastic Approximation, plan is only limited by the agent’s ability to effectively explain it. In this chapter, in addition to introducing the basic framework of explanation as model reconciliation under a certain set of assumptions, we will also look at several types of model reconciliation explanations, study some of th