Visualizations for an Explainable Planning Agent

In this demonstration, we report on the visualization capabilities of an Explainable AI Planning (XAIP) agent that can support human-in-the-loop decision-making. Imposing transparency and explainability requirements on such agents is crucial for establishing human trust and common ground with an end-to-end automated planning system. Visualizing the agent's internal decision making processes is a crucial step towards achieving this. This may include externalizing the "brain" of the agent: starting from its sensory inputs, to progressively higher order decisions made by it in order to drive its planning components. We demonstrate these functionalities in the context of a smart assistant in the Cognitive Environments Laboratory at IBM's T.J. Watson Research Center.

[1]  Kshitij P. Fadnis,et al.  DEMO : Visualizations for an Explainable Planning Agent , 2018 .

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

[3]  John Kaneshige,et al.  CHAP-E: A Plan Execution Assistant for Pilots , 2018, ICAPS.

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

[5]  Rachel K. E. Bellamy,et al.  Mr. Jones - Towards a Proactive Smart Room Orchestrator , 2017, AAAI Fall Symposia.

[6]  Subbarao Kambhampati,et al.  Herding the Crowd: Using Automated Planning for Better Crowdsourced Planning , 2017, Hum. Comput..

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

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

[9]  Sailik Sengupta,et al.  RADAR - A Proactive Decision Support System for Human-in-the-Loop Planning , 2017, AAAI Fall Symposia.

[10]  Felipe Meneguzzi,et al.  A Tool to Develop Classical Planning Domains and Visualize Heuristic State-Space Search , 2017 .

[11]  Joseph Kim,et al.  Towards Intelligent Decision Support in Human Team Planning , 2017, AAAI Fall Symposia.

[12]  Rachel K. E. Bellamy,et al.  Symbiotic Cognitive Computing , 2016, AI Mag..

[13]  Joseph Kim,et al.  Improving Team's Consistency of Understanding in Meetings , 2016, IEEE Transactions on Human-Machine Systems.

[14]  David E. Smith,et al.  A Fast Goal Recognition Technique Based on Interaction Estimates , 2015, IJCAI.

[15]  Jeffrey O. Kephart,et al.  A Symbiotic Cognitive Computing Perspective on Autonomic Computing , 2015, 2015 IEEE International Conference on Autonomic Computing.

[16]  Been Kim,et al.  Inferring Team Task Plans from Human Meetings: A Generative Modeling Approach with Logic-Based Prior , 2015, J. Artif. Intell. Res..

[17]  Subbarao Kambhampati,et al.  Herding the Crowd: Automated Planning for Crowdsourced Planning , 2013, HCOMP.

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

[19]  M. Sheelagh T. Carpendale,et al.  A Visual Backchannel for Large-Scale Events , 2010, IEEE Transactions on Visualization and Computer Graphics.

[20]  Hector Geffner,et al.  Probabilistic Plan Recognition Using Off-the-Shelf Classical Planners , 2010, AAAI.

[21]  E. Whaites,et al.  David Smith , 1905, BDJ.

[22]  Eric Horvitz,et al.  Reflections on Challenges and Promises of Mixed-Initiative Interaction , 2007, AI Mag..

[23]  Malte Helmert,et al.  The Fast Downward Planning System , 2006, J. Artif. Intell. Res..

[24]  Maria Fox,et al.  VAL: automatic plan validation, continuous effects and mixed initiative planning using PDDL , 2004, 16th IEEE International Conference on Tools with Artificial Intelligence.

[25]  Jay F. Nunamaker,et al.  Meeting analysis: findings from research and practice , 2001, Proceedings of the 34th Annual Hawaii International Conference on System Sciences.

[26]  Eric Horvitz,et al.  Principles of mixed-initiative user interfaces , 1999, CHI '99.

[27]  Karen L. Myers.  Advisable Planning Systems , 1996 .

[28]  E. Groves.  A Dissertation ON , 1928 .