Explainable Planning

Abstract

As AI is increasingly being adopted into application solutions, the challenge of supporting interaction with humans is becoming more apparent. Partly this is to support integrated working styles, in which humans and intelligent systems cooperate in problem-solving, but also it is a necessary step in the process of building trust as humans migrate greater responsibility to such systems. The challenge is to find effective ways to communicate the foundations of AI-driven behaviour, when the algorithms that drive it are far from transparent to humans. In this paper we consider the opportunities that arise in AI planning, exploiting the model-based representations that form a familiar and common basis for communication with users, while acknowledging the gap between planning algorithms and human problem-solving.

Presented at the IJCAI-17 workshop on Explainable AI (http://home.earthlink.net/~dwaha/research/meetings/ijcai17-xai/). Melbourne, August 2017

Cited by in corpus (22)

• What Do We Want From Explainable Artificial Intelligence (XAI)? -- A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research
• Generating Natural Language Explanations for Visual Question Answering using Scene Graphs and Visual Attention
• A framework for step-wise explaining how to solve constraint satisfaction problems
• Towards a Grounded Dialog Model for Explainable Artificial Intelligence
• Balancing Explicability and Explanation in Human-Aware Planning
• Towards Explainable AI Planning as a Service
• MAPS-X: Explainable Multi-Robot Motion Planning via Segmentation
• Towards Providing Explanations for AI Planner Decisions
• Human collective visualization transparency
• Transparency's Influence on Human-Collective Interactions
• Hierarchical Expertise-Level Modeling for User Specific Robot-Behavior Explanations
• Identification of Unexpected Decisions in Partially Observable Monte-Carlo Planning: a Rule-Based Approach
• Desiderata for Planning Systems in General-Purpose Service Robots
• Iterative Planning with Plan-Space Explanations: A Tool and User Study
• A Game-Based Approach for Helping Designers Learn Machine Learning Concepts
• Dungeon Crawl Stone Soup as an Evaluation Domain for Artificial Intelligence
• Towards Social HRI for Improving Children's Healthcare Experiences
• Economics of Human-AI Ecosystem: Value Bias and Lost Utility in Multi-Dimensional Gaps
• Argument Schemes and Dialogue for Explainable Planning
• Responsive Planning and Recognition for Closed-Loop Interaction
• Encoding Compositionality in Classical Planning Solutions
• Provenance-Based Assessment of Plans in Context