skip to main content

Explore Research Products in the NSF-PAR

Title: A Logic-Based Explanation Generation Framework for Classical and Hybrid Planning Problems
In human-aware planning systems, a planning agent might need to explain its plan to a human user when that plan appears to be non-feasible or sub-optimal. A popular approach, called model reconciliation, has been proposed as a way to bring the model of the human user closer to the agent’s model. To do so, the agent provides an explanation that can be used to update the model of human such that the agent’s plan is feasible or optimal to the human user. Existing approaches to solve this problem have been based on automated planning methods and have been limited to classical planning problems only. In this paper, we approach the model reconciliation problem from a different perspective, that of knowledge representation and reasoning, and demonstrate that our approach can be applied not only to classical planning problems but also hybrid systems planning problems with durative actions and events/processes. In particular, we propose a logic-based framework for explanation generation, where given a knowledge base KBa (of an agent) and a knowledge base KBh (of a human user), each encoding their knowledge of a planning problem, and that KBa entails a query q (e.g., that a proposed plan of the agent is valid), the goal is to identify an explanation ε ⊆ KBa such that when it is used to update KBh, then the updated KBh also entails q. More specifically, we make the following contributions in this paper: (1) We formally define the notion of logic-based explanations in the context of model reconciliation problems; (2) We introduce a number of cost functions that can be used to reflect preferences between explanations; (3) We present algorithms to compute explanations for both classical planning and hybrid systems planning problems; and (4) We empirically evaluate their performance on such problems. Our empirical results demonstrate that, on classical planning problems, our approach is faster than the state of the art when the explanations are long or when the size of the knowledge base is small (e.g., the plans to be explained are short). They also demonstrate that our approach is efficient for hybrid systems planning problems. Finally, we evaluate the real-world efficacy of explanations generated by our algorithms through a controlled human user study, where we develop a proof-of-concept visualization system and use it as a medium for explanation communication.  more » « less
Award ID(s):
1812628
NSF-PAR ID:
10353076
Author(s) / Creator(s):
; ; ; ; ;
Date Published:
Journal Name:
Journal of Artificial Intelligence Research
Volume:
73
ISSN:
1076-9757
Page Range / eLocation ID:
1473 to 1534
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ( , Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems)
    null (Ed.)
    In explainable planning, the planning agent needs to explain its plan to a human user, especially when the plan appears infeasible or suboptimal for the user. A popular approach is called model reconciliation, where the agent reconciles the differences between its model and the model of the user such that its plan is also feasible and optimal to the user. This problem can be viewed as a more general problem as follows: Given two knowledge bases πa and πh and a query q such that πa entails q and πh does not entail q, where the notion of entailment is dependent on the logical theories underlying πa and πh, how to change πh–given πa and the support for q in πa–so that πh does entail q. In this paper, we study this problem under the context of answer set programming. To achieve this goal, we (1) define the notion of a conditional update between two logic programs πa and πh with respect to a query q;(2) define the notion of an explanation for a query q from a program πa to a program πh using conditional updates;(3) develop algorithms for computing explanations; and (4) show how the notion of explanation based on conditional updates can be used in explainable planning. 
    more » « less
  2. ; ; ; ( , International Conference on Principles of Knowledge Representation and Reasoning ()
    null (Ed.)
    In human-aware planning problems, the planning agent may need to explain its plan to a human user, especially when the plan appears infeasible or suboptimal for the user. A popular approach to do so is called model reconciliation, where the planning agent tries to reconcile the differences between its model and the model of the user such that its plan is also feasible and optimal to the user. This problem can be viewed as an optimization problem, where the goal is to find a subset-minimal explanation that one can use to modify the model of the user such that the plan of the agent is also feasible and optimal to the user. This paper presents an algorithm for solving such problems using answer set programming. 
    more » « less
  3. ; ; ; ( , Proceedings of the International Conference on Principles of Knowledge Representation and Reasoning)
    null (Ed.)

    In human-aware planning problems, the planning agent may need to explain its plan to a human user, especially when the plan appears infeasible or suboptimal for the user. A popular approach to do so is called model reconciliation, where the planning agent tries to reconcile the differences between its model and the model of the user such that its plan is also feasible and optimal to the user. This problem can be viewed as an optimization problem, where the goal is to find a subset-minimal explanation that one can use to modify the model of the user such that the plan of the agent is also feasible and optimal to the user. This paper presents an algorithm for solving such problems using answer set programming.

     
    more » « less
  4. ( , Procs. IJCAI-2022 Workshop on Explainable AI)
    We describe a human-centered and design-based stance towards generating explanations in AI agents. We collect questions about the working of an AI agent through participatory design by fo- cus groups. We capture an agent’s design through a Task-Method-Knowledge model that explicitly specifies the agent’s tasks and goals, as well as the mechanisms, knowledge and vocabulary it uses for accomplishing the tasks. We illustrate our approach through the generation of explanations in Skillsync, an AI agent that links companies and colleges for worker upskilling and reskilling. In particular, we embed a question-answering agent called AskJill in Skillsync, where AskJill contains a TMK model of Skillsync’s design. AskJill presently answers human-generated questions about Skillsync’s tasks and vocabulary, and thereby helps explain how it produces its recommendations. 
    more » « less
  5. ; ( , Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing)
    Explanations promise to bridge the gap between humans and AI, yet it remains difficult to achieve consistent improvement in AI-augmented human decision making. The usefulness of AI explanations depends on many factors, and always showing the same type of explanation in all cases is suboptimal—so is relying on heuristics to adapt explanations for each scenario. We propose learning to explain”selectively”: for each decision that the user makes, we use a model to choose the best explanation from a set of candidates and update this model with feedback to optimize human performance. We experiment on a question answering task, Quizbowl, and show that selective explanations improve human performance for both experts and crowdworkers. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email