Contrastive Explanations of Plans Through Model Restrictions

@article{Krarup2021ContrastiveEO,
  title={Contrastive Explanations of Plans Through Model Restrictions},
  author={Benjamin Krarup and Senka Krivic and Daniele Magazzeni and Derek Long and Michael Cashmore and David E. Smith},
  journal={J. Artif. Intell. Res.},
  year={2021},
  volume={72},
  pages={533-612}
}
In automated planning, the need for explanations arises when there is a mismatch between a proposed plan and the user’s expectation. We frame Explainable AI Planning as an iterative plan exploration process, in which the user asks a succession of contrastive questions that lead to the generation and solution of hypothetical planning problems that are restrictions of the original problem. The object of the exploration is for the user to understand the constraints that govern the original plan… 
Contrastive Natural Language Explanations for Multi-Objective Path Planning
TLDR
This paper introduces a flexible, scalable approach that generates contrastive explanations of navigation plans based on multiple objectives that provide counterfactual ex-chance explanations of a robot controller’s beliefs, intentions, and confidence.
Evaluating Plan-Property Dependencies: A Web-Based Platform and User Study
TLDR
A Web-based platform for iterative planning with explanations elucidating the dependencies between plan properties and it is found that the explanations enable users to iden- tify better trade-offs between the plan properties, indicating an improved understanding of the planning task.
Diagnosing AI Explanation Methods with Folk Concepts of Behavior
When explaining AI behavior to humans, how does a human explainee comprehend the communicated information, and does it match what the explanation attempted to communicate? When can we say that an
A Review of Plan-Based Approaches for Dialogue Management
TLDR
The results indicate that AI planning is still an emerging strategy for dialogue management, especially to those that require predictability, some relevant challenges might still limit its adoption.
Understanding a Robot's Guiding Ethical Principles via Automatically Generated Explanations
The continued development of robots has enabled their wider usage in human surroundings. Robots are more trusted to make increasingly important decisions with potentially critical outcomes.

References

SHOWING 1-10 OF 79 REFERENCES
A New Approach to Plan-Space Explanation: Analyzing Plan-Property Dependencies in Oversubscription Planning
TLDR
It is shown how, via compilation, one can analyze dependencies between a richer form of plan properties, specifying formulas over action subsets touched by the plan, and find that the suggested analyses are reasonably feasible at the global level, and become significantly more effective at the local level.
A Domain-Independent Algorithm for Plan Adaptation
TLDR
The algorithm's completeness ensures that the adaptation algorithm will eventually search the entire graph and its systematicity ensures that it will do so without redundantly searching any parts of the graph.
Plan Explanations as Model Reconciliation: Moving Beyond Explanation as Soliloquy
TLDR
It is shown how explanation can be seen as a "model reconciliation problem" (MRP), where the AI system in effect suggests changes to the human's model, so as to make its plan be optimal with respect to that changed human model.
Preferred Explanations: Theory and Generation via Planning
TLDR
This paper provides a logical characterization of the notion of an explanation and identifies and exploits a correspondence between explanation generation and planning, and illustrates the feasibility of generating (preferred) explanations via planning.
Towards Providing Explanations for AI Planner Decisions
TLDR
This paper presents a methodology to provide initial explanations for the decisions made by the planner, and allows the user to suggest alternative actions in plans and then compare the resulting plans with the one found by the planning system.
Plan Stability: Replanning versus Plan Repair
TLDR
This work presents arguments to support the claim that plan stability is a valuable property, and proposes an implementation, based on LPG, of a plan repair strategy that adapts a plan to its new context.
Plan Repair as an Extension of Planning
TLDR
A straightforward method to extend planning techniques such that they are able to repair plans is proposed, and a heuristic for unrefinement that can make use of an arbitrary existing planning technique is presented.
Handling Model Uncertainty and Multiplicity in Explanations via Model Reconciliation
TLDR
This paper shows how the explanation process evolves in the presence of such model uncertainty or incompleteness by generating conformant explana- tions that are applicable to a set of possible models and demonstrates the trade-offs in the different forms of explanations.
Efficient Plan Adaptation through Replanning Windows and Heuristic Goals
TLDR
This paper investigates a domain-independent method for plan adaptation that modifies the original plan by replanning within limited temporal windows containing portions of the plan that need to be revised.
Coming up With Good Excuses: What to do When no Plan Can be Found
TLDR
This work will present an algorithm that is able to find excuses and demonstrate that such excuses can be found in practical settings in reasonable time.
...
...