EUVIMEDEUVIMED entdecken
Crossref

Towards Explainable Goal Recognition Using Weight of Evidence (WoE): A Human-Centered Approach

Abeer Alshehri, Amal Abdulrahman, Hajar Alamri, Tim Miller, Mor Vered

Journal of Artificial Intelligence Research · 30.04.2025 · 82 · 2535-2594

DOI: 10.1613/jair.1.17173 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Artificial Intelligence Research, online erschienen am 30.04.2025. Verfasst von Abeer Alshehri und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Goal recognition (GR) involves inferring an agent's unobserved goal from a sequence of observations. This is a critical problem in AI with diverse applications. Traditionally, GR has been addressed using 'inference to the best explanation' or abduction, where hypotheses about the agent's goals are generated as the most plausible explanations for observed behavior. Alternatively, some approaches enhance interpretability by ensuring that an agent's behavior aligns with an observer's expectations or by making the reasoning behind decisions more transparent. In this work, we tackle a different challenge: explaining the GR process in a way that is comprehensible to humans. We introduce and evaluate an explainable model for goal recognition (GR) agents, grounded in the theoretical framework and cognitive processes underlying human behavior explanation. Drawing on insights from two human-agent studies, we propose a conceptual framework for human-centered explanations of GR. Using this framework, we develop the eXplainable Goal Recognition (XGR) model, which generates explanations for both why and why not questions. We evaluate the model computationally across eight GR benchmarks and through three user studies. The first study assesses the efficiency of generating human-like explanations within the Sokoban game domain, the second examines perceived explainability in the same domain, and the third evaluates the model's effectiveness in aiding decision-making in illegal fishing detection. Results demonstrate that the XGR model significantly enhances user understanding, trust, and decision-making compared to baseline models, underscoring its potential to improve human-agent collaboration.

Zitieren

APA

Alshehri, A., Abdulrahman, A., Alamri, H., Miller, T., & Vered, M. (2025). Towards Explainable Goal Recognition Using Weight of Evidence (WoE): A Human-Centered Approach. Journal of Artificial Intelligence Research, 82, 2535-2594. https://doi.org/10.1613/jair.1.17173

Vancouver

Alshehri A, Abdulrahman A, Alamri H, Miller T, Vered M. Towards Explainable Goal Recognition Using Weight of Evidence (WoE): A Human-Centered Approach. Journal of Artificial Intelligence Research. 2025;82:2535-2594. doi:10.1613/jair.1.17173

BibTeX
@article{Alshehri2025,
  author = {Alshehri, Abeer and Abdulrahman, Amal and Alamri, Hajar and Miller, Tim and Vered, Mor},
  title = {Towards Explainable Goal Recognition Using Weight of Evidence (WoE): A Human-Centered Approach},
  journal = {Journal of Artificial Intelligence Research},
  year = {2025},
  volume = {82},
  pages = {2535--2594},
  doi = {10.1613/jair.1.17173}
}
Kostenlos starten →