Enabling a Social Robot to Process Social Cues to Detect when to Help a User

Wilson, Jason R.; Aung, Phyo Thuta; Boucher, Isabelle

doi:10.48550/arxiv.2110.11075

Cited by 1 publication

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We subdivide assistive explanations into task-oriented assistive explanations and general knowledge explanations. Taskoriented explanations are about helping the user in situations where they are stuck due to missing knowledge about the task and environment (e.g., [31]) or due to high task complexity that does not allow them to quickly identify the best action (e.g., [32]). An example of a question coming from the user that demands a task-oriented assistive explanation is "What do I have to do next?".…”

Section: Assistive Explanationsmentioning

confidence: 99%

“…The user does not understand the agent's behavior, task, or environment as some piece of knowledge about them is missing from the user's mental model [9,31]. Filling in those missing pieces via explanations helps with solving the task and predicting and understanding agent behavior, thus generating trust [18] The user does not understand the task goals, what preconditions need to be fulfilled to execute some action, or where an object is Mismatch of the user's and the agent's mental model User and agent model differ in regards to the environment, task, or each other.…”

Section: Incomplete User Mental Model Of the Agent Or Taskmentioning

confidence: 99%

See 1 more Smart Citation

A Taxonomy of Explanation Types and Need Indicators in Human–Agent Collaborations

Wachowiak,

Coles,

Canal

et al. 2024

Int J of Soc Robotics

View full text Add to dashboard Cite

In recent years, explanations have become a pressing matter in AI research. This development was caused by the increased use of black-box models and a realization of the importance of trustworthy AI. In particular, explanations are necessary for human–agent interactions to ensure that the user can trust the agent and that collaborations are effective. Human–agent interactions are complex social scenarios involving a user, an autonomous agent, and an environment or task with its own distinct properties. Thus, such interactions require a wide variety of explanations, which are not covered by the methods of a single AI discipline, such as computer vision or natural language processing. In this paper, we map out what types of explanations are important for human–agent interactions, surveying the field via a scoping review. In addition to the typical introspective explanation tackled by explainability researchers, we look at assistive explanations, aiming to support the user with their task. Secondly, we survey what causes the need for an explanation in the first place. We identify a variety of human–agent interaction-specific causes and categorize them by whether they are centered on the agent’s behavior, the user’s mental state, or an external entity. Our overview aims to guide robotics practitioners in designing agents with more comprehensive explanation-related capacities, considering different explanation types and the concrete times when explanations should be given.

show abstract

Section: Assistive Explanationsmentioning

confidence: 99%