EXplainable Goal Recognition: A framework based on weight of evidence

Abeer Alshehri, Tim Miller, Mor Vered

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review


We introduce and evaluate an eXplainable Goal Recognition (XGR) model that uses the Weight of Evidence (WoE) framework to explain goal recognition problems. Our model provides human-centered explanations that answer 'why?' and 'why not?' questions. We computationally evaluate the performance of our system over eight different domains. Using a human behavioral study to obtain the ground truth from human annotators, we further show that the XGR model can successfully generate human-like explanations. We then report on a study with 60 participants who observe agents playing Sokoban game and then receive explanations of the goal recognition output. We investigate participants' understanding obtained by explanations through task prediction, explanation satisfaction, and trust.

Original languageEnglish
Title of host publicationProceedings of the Thirty-Third International Conference on Automated Planning and Scheduling 2023
EditorsSven Koenig, Roni Stern, Mauro Vallati
Place of PublicationPalo Alto CA USA
PublisherAssociation for the Advancement of Artificial Intelligence (AAAI)
Number of pages10
ISBN (Electronic)9781577358817
Publication statusPublished - 2023
EventInternational Conference on Automated Planning and Scheduling 2023 - Prague, Czechia
Duration: 8 Jul 202313 Jul 2023
Conference number: 33rd
https://icaps23.icaps-conference.org/ (Website)


ConferenceInternational Conference on Automated Planning and Scheduling 2023
Abbreviated titleICAPS 2023
Internet address


  • Plan recognition
  • plan management
  • goal reasoning

Cite this