Explainability and Knowledge Representation in Robotics: The Green Button Challenge

As robots get closer to human environments, a fundamental task for the community is to design system behaviors that foster trust. In this context, we have posed the "Green Button Challenge": every robot should have a green button that, when pressed, makes the robot explain what it is doing and why, in natural language. In this paper, we motivate why explainability is important in robotics, an why explicit knowledge representations are essential to achieving it. We highlight this with a concrete proof-of-concept implementation on our humanoid space assistant Rollin' Justin, which interprets its PDDL plans to explain what it is doing and why.

[1]  Daniel Sebastian Leidner,et al.  Cognitive Reasoning for Compliant Robot Manipulation , 2018, Springer Tracts in Advanced Robotics.

[2]  Zachary Chase Lipton.  The mythos of model interpretability , 2016, ACM Queue.

[3]  Jürgen Pripfl,et al.  A Long-Term Autonomous Robot at a Care Hospital: A Mixed Methods Study on Social Acceptance and Experiences of Staff and Older Adults , 2017, Int. J. Soc. Robotics.

[4]  Florian Nothdurft,et al.  Plan, Repair, Execute, Explain - How Planning Helps to Assemble your Home Theater , 2014, ICAPS.

[5]  Andre Schiele,et al.  Simulating an Extraterrestrial Environment for Robotic Space Exploration: The METERON SUPVIS-JUSTIN Telerobotic Experiment and the SOLEX Proving Ground , 2015 .

[6]  Song-Chun Zhu,et al.  A tale of two explanations: Enhancing human trust by explaining robot behavior , 2019, Science Robotics.

[7]  Manuela Veloso.  Learning by analogical reasoning in general problem-solving , 1992 .

[8]  Craig A. Knoblock,et al.  PDDL-the planning domain definition language , 1998 .

[9]  Subbarao Kambhampati,et al.  The Emerging Landscape of Explainable Automated Planning & Decision Making , 2020, IJCAI.

[10]  Subbarao Kambhampati,et al.  Mapping and Retrieval During Plan Reuse: A Validation Structure Based Approach , 1990, AAAI.

[11]  Florian Schmidt,et al.  Rollin' Justin - Mobile platform with variable base , 2009, 2009 IEEE International Conference on Robotics and Automation.

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

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

[14]  Daniel Leidner,et al.  Iteratively Refined Feasibility Checks in Robotic Assembly Sequence Planning , 2019, IEEE Robotics and Automation Letters.