Towards Providing Explanations for AI Planner Decisions

In order to engender trust in AI, humans must understand what an AI system is trying to achieve, and why. To overcome this problem, the underlying AI process must produce justifications and explanations that are both transparent and comprehensible to the user. AI Planning is well placed to be able to address this challenge. In this paper we present a methodology to provide initial explanations for the decisions made by the planner. Explanations are created by allowing the user to suggest alternative actions in plans and then compare the resulting plans with the one found by the planner. The methodology is implemented in the new XAI-Plan framework.

[1]  Maria Fox,et al.  Heuristic Planning for PDDL+ Domains , 2016, AAAI Workshop: Planning for Hybrid Systems.

[2]  Bradley Hayes,et al.  Improving Robot Controller Transparency Through Autonomous Policy Explanation , 2017, 2017 12th ACM/IEEE International Conference on Human-Robot Interaction (HRI.

[3]  Susanne Biundo-Stephan,et al.  Making Hybrid Plans More Clear to Human Users - A Formal Approach for Generating Sound Explanations , 2012, ICAPS.

[4]  Jorge A. Baier,et al.  Preferred Explanations: Theory and Generation via Planning , 2011, AAAI.

[5]  Wolfgang Minker,et al.  Verbal Plan Explanations for Hybrid Planning , 2010, MKWI.

[6]  Peter J. Stuckey,et al.  Planning for Mining Operations with Time and Resource Constraints , 2014, ICAPS.

[7]  Pat Langley,et al.  Explainable Agency for Intelligent Autonomous Systems , 2017, AAAI.

[8]  Maria Fox,et al.  Opportunistic Planning in Autonomous Underwater Missions , 2018, IEEE Transactions on Automation Science and Engineering.

[9]  Lukás Chrpa,et al.  Efficient Macroscopic Urban Traffic Models for Reducing Congestion: A PDDL+ Planning Approach , 2016, AAAI.

[10]  Yu Zhang,et al.  Plan Explanations as Model Reconciliation: Moving Beyond Explanation as Soliloquy , 2017, IJCAI.

[11]  Carleton Coffrin,et al.  Planning with MIP for Supply Restoration in Power Distribution Systems , 2013, IJCAI.

[12]  Shirin Sohrabi,et al.  A Novel Iterative Approach to Top-k Planning , 2018, ICAPS.

[13]  Maria Fox,et al.  Solving Realistic Unit Commitment Problems Using Temporal Planning: Challenges and Solutions , 2016, ICAPS.

[14]  Natàlia Hurtós,et al.  ROSPlan: Planning in the Robot Operating System , 2015, ICAPS.

[15]  David E. Smith Planning as an Iterative Process , 2012, AAAI.

[16]  Stephanie Rosenthal,et al.  Verbalization: Narration of Autonomous Robot Experience , 2016, IJCAI.

[17]  Subbarao Kambhampati,et al.  Handling Model Uncertainty and Multiplicity in Explanations via Model Reconciliation , 2018, ICAPS.

[18]  Robert Morris,et al.  Self-Driving Aircraft Towing Vehicles: A Preliminary Report , 2015, AAAI Workshop: AI for Transportation.

[19]  Yu Zhang,et al.  Plan explicability and predictability for robot task planning , 2015, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[20]  Maria Fox,et al.  Explainable Planning , 2017, ArXiv.

[21]  Subbarao Kambhampati,et al.  Generating diverse plans to handle unknown and partially known user preferences , 2012, Artif. Intell..