Improving Robot Controller Transparency Through Autonomous Policy Explanation

• Published in: 2017 12th ACM/IEEE International Conference on Human-Robot Interaction (HRI pp. 303 - 312
• Main Authors: Hayes, Bradley, Shah, Julie A.
• Format: Conference Proceeding
• Language: English
• Published: New York, NY, USA ACM 06.03.2017
• Series: ACM Conferences
• Subjects: Behavioral sciences; Codes; Computer systems organization > Embedded and cyber-physical systems > Robotics; Computer systems organization > Embedded and cyber-physical systems > Robotics > External interfaces for robotics; Computing methodologies > Machine learning; Computing methodologies > Machine learning > Machine learning approaches > Learning in probabilistic graphical models; Computing methodologies > Machine learning > Machine learning approaches > Markov decision processes; Deep reinforcement learning; Fault diagnosis; Human-centered computing > Human computer interaction (HCI); Human-centered computing > Human computer interaction (HCI) > Interaction paradigms > Natural language interfaces; Human-centered computing > Interaction design; Human-robot interaction; Logic; Robot control; Statistical analysis; Teamwork; human-robot interaction; human-robot collaboration; human-robot teaming; interpretable machine learning
• ISBN: 9781450343367; 1450343368
• ISSN: 2167-2148
• DOI: 10.1145/2909824.3020233

Shared expectations and mutual understanding are critical facets of teamwork. Achieving these in human-robot collaborative contexts can be especially challenging, as humans and robots are unlikely to share a common language to convey intentions, plans, or justifications. Even in cases where human co-workers can inspect a robot's control code, and particularly when statistical methods are used to encode control policies, there is no guarantee that meaningful insights into a robot's behavior can be derived or that a human will be able to efficiently isolate the behaviors relevant to the interaction. We present a series of algorithms and an accompanying system that enables robots to autonomously synthesize policy descriptions and respond to both general and targeted queries by human collaborators. We demonstrate applicability to a variety of robot controller types including those that utilize conditional logic, tabular reinforcement learning, and deep reinforcement learning, synthesizing informative policy descriptions for collaborators and facilitating fault diagnosis by non-experts.