Balancing Explicability and Explanation in Human-Aware Planning

Human aware planning requires an agent to be aware of the intentions, capabilities and mental model of the human in the loop during its decision process. This can involve generating plans that are explicable to a human observer as well as the ability to provide explanations when such plans cannot be generated. This has led to the notion "multi-model planning" which aim to incorporate effects of human expectation in the deliberative process of a planner - either in the form of explicable task planning or explanations produced thereof. In this paper, we bring these two concepts together and show how a planner can account for both these needs and achieve a trade-off during the plan generation process itself by means of a model-space search method MEGA. This in effect provides a comprehensive perspective of what it means for a decision making agent to be "human-aware" by bringing together existing principles of planning under the umbrella of a single plan generation process. We situate our discussion specifically keeping in mind the recent work on explicable planning and explanation generation, and illustrate these concepts in modified versions of two well known planning domains, as well as a demonstration on a robot involved in a typical search and reconnaissance task with an external supervisor.

[1]  Simon Parsons,et al.  Argumentation strategies for plan resourcing , 2011, AAMAS.

[2]  Rachid Alami,et al.  On human-aware task and motion planning abilities for a teammate robot , 2014 .

[3]  Bernhard Nebel,et al.  Better Eager Than Lazy? How Agent Types Impact the Successfulness of Implicit Coordination , 2018, KR.

[4]  Subbarao Kambhampati,et al.  Explicability versus Explanations in Human-Aware Planning , 2018, AAMAS.

[5]  Siddhartha S. Srinivasa,et al.  Legibility and predictability of robot motion , 2013, 2013 8th ACM/IEEE International Conference on Human-Robot Interaction (HRI).

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

[7]  Cade Earl Bartlett.  Communication between Teammates in Urban Search and Rescue , 2015 .

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

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

[10]  Rachid Alami,et al.  Toward Human-Aware Robot Task Planning , 2006, AAAI Spring Symposium: To Boldly Go Where No Human-Robot Team Has Gone Before.

[11]  Yu Zhang,et al.  Planning with Resource Conflicts in Human-Robot Cohabitation , 2016, AAMAS.

[12]  Stefanos Nikolaidis,et al.  Improved human–robot team performance through cross-training, an approach inspired by human team training practices , 2015, Int. J. Robotics Res..

[13]  Anca D. Dragan,et al.  Cooperative Inverse Reinforcement Learning , 2016, NIPS.

[14]  S. Kambhampati,et al.  Plan Explicability for Robot Task Planning , 2010 .

[15]  Iyad Rahwan,et al.  Agreeing on plans through iterated disputes , 2010, AAMAS.

[16]  J. Dessalles,et al.  Reasoning as a lie detection device , 2011, Behavioral and Brain Sciences.

[17]  Yu Zhang,et al.  Explicable Robot Planning as Minimizing Distance from Expected Behavior , 2016, ArXiv.

[18]  Subbarao Kambhampati,et al.  Explanations as Model Reconciliation - A Multi-Agent Perspective , 2017, AAAI Fall Symposia.

[19]  James F. Allen,et al.  TRAINS-95: Towards a Mixed-Initiative Planning Assistant , 1996, AIPS.

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

[21]  Subbarao Kambhampati,et al.  AI-MIX: Using Automated Planning to Steer Human Workers Towards Better Crowdsourced Plans , 2014, HCOMP.

[22]  Yu Zhang,et al.  Planning for serendipity , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[23]  Alessandro Saffiotti,et al.  Human-aware task planning: An application to mobile robots , 2010, TIST.

[24]  Subbarao Kambhampati,et al.  Explicability? Legibility? Predictability? Transparency? Privacy? Security? The Emerging Landscape of Interpretable Agent Behavior , 2018, ICAPS.

[25]  Anca D. Dragan,et al.  Planning for Autonomous Cars that Leverage Effects on Human Actions , 2016, Robotics: Science and Systems.

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

[27]  Alessandro Saffiotti,et al.  Too cool for school - adding social constraints in human aware planning , 2014 .

[28]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

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

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

[32]  Tim Miller,et al.  Logics of Common Ground , 2017, J. Artif. Intell. Res..

[33]  Christian J. Muise,et al.  Planning for a Single Agent in a Multi-Agent Environment Using FOND , 2016, IJCAI.

[34]  Subbarao Kambhampati,et al.  Plan Explanations as Model Reconciliation - An Empirical Study , 2018, ArXiv.

[35]  Erez Karpas,et al.  Privacy Preserving Plans in Partially Observable Environments , 2016, IJCAI.

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

[37]  R. Adams.  Proceedings , 1947 .

[38]  Rodney A. Brooks,et al.  A Robust Layered Control Syste For A Mobile Robot , 2022 .

[39]  Marc Hanheide,et al.  Robot task planning and explanation in open and uncertain worlds , 2017, Artif. Intell..

[40]  Matthias Scheutz,et al.  Coordination in human-robot teams using mental modeling and plan recognition , 2014, 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[41]  Ari K. Jónsson,et al.  MAPGEN: Mixed-Initiative Planning and Scheduling for the Mars Exploration Rover Mission , 2004, IEEE Intell. Syst..

[42]  Yu Zhang,et al.  AI Challenges in Human-Robot Cognitive Teaming , 2017, ArXiv.

[43]  Lars Karlsson,et al.  Grandpa Hates Robots - Interaction Constraints for Planning in Inhabited Environments , 2014, AAAI.