Summary of Explainable Interface For Human-autonomy Teaming: a Survey, by Xiangqi Kong et al.
Explainable Interface for Human-Autonomy Teaming: A Survey
by Xiangqi Kong, Yang Xing, Antonios Tsourdos, Ziyue Wang, Weisi Guo, Adolfo Perrusquia, Andreas Wikander
First submitted to arxiv on: 4 May 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper addresses the critical issue of transparency in human-autonomy teaming (HAT) applications, where large-scale foundation models are integrated to improve safety-critical tasks. The authors focus on Explainable Interface (EI) within HAT systems from a human-centric perspective, enriching the field of Explainable Artificial Intelligence (XAI). They clarify the concepts of EI, explanations, and model explainability, providing a structured understanding for researchers and practitioners. The paper presents a novel framework for EI in XAI-enhanced HAT systems, addressing unique challenges and offering a holistic evaluation framework that considers model performance, human-centered factors, and group task objectives. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps make robots and computers work better with people. It looks at how to explain what machines are doing, so humans can trust them more. The authors explore Explainable Interface (EI) in systems where humans and machines work together. They create a new way of designing EI and evaluate its performance. The research combines ideas from artificial intelligence, human-computer interaction, and psychology to improve our understanding of how humans and machines can work together safely. |
