Explainable Goal Recognition: A Framework Based on Weight of Evidence
-
Published:2023-07-01
Issue:1
Volume:33
Page:7-16
-
ISSN:2334-0843
-
Container-title:Proceedings of the International Conference on Automated Planning and Scheduling
-
language:
-
Short-container-title:ICAPS
Author:
Alshehri Abeer,Miller Tim,Vered Mor
Abstract
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 goal recognition domains showing it does not significantly increase the underlying recognition run time. 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 40 participants who observe agents playing a Sokoban game and then receive explanations of the goal recognition output. We investigated participants’ understanding obtained by explanations through task prediction, explanation satisfaction, and trust.
Publisher
Association for the Advancement of Artificial Intelligence (AAAI)
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Exploring the Cost of Interruptions in Human-Robot Teaming;2023 IEEE-RAS 22nd International Conference on Humanoid Robots (Humanoids);2023-12-12