Designing Environments Conducive to Interpretable Robot Behavior
Preprint
Abstract
Designing robots capable of generating interpretable behavior is a prerequisite for achieving effective human-robot collaboration. This means that the robots need to be capable of generating behavior that aligns with human expectations and, when required, provide explanations to the humans in the loop. However, exhibiting such behavior in arbitrary environments could be quite expensive for robots, and in some cases, the robot may not even be able to exhibit the expected behavior. Given structured environments (like warehouses and restaurants), it may be possible to design the environment so as to boost the interpretability of the robot's behavior or to shape the human's expectations of the robot's behavior. In this paper, we investigate the opportunities and limitations of environment design as a tool to promote a type of interpretable behavior -- known in the literature as explicable behavior. We formulate a novel environment design framework that considers design over multiple tasks and over a time horizon. In addition, we explore the longitudinal aspect of explicable behavior and the trade-off that arises between the cost of design and the cost of generating explicable behavior over a time horizon.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Generating Plans that Predict ThemselvesSpringer Proceedings in Advanced Robotics, 2020
- A Unified Framework for Planning in Adversarial and Cooperative EnvironmentsProceedings of the AAAI Conference on Artificial Intelligence, 2019
- Explicability? Legibility? Predictability? Transparency? Privacy? Security? The Emerging Landscape of Interpretable Agent BehaviorProceedings of the International Conference on Automated Planning and Scheduling, 2019
- Goal and Plan Recognition Design for Plan LibrariesACM Transactions on Intelligent Systems and Technology, 2019
- Plan explicability and predictability for robot task planning2017
- A Concise Introduction to Models and Methods for Automated PlanningSynthesis Lectures on Artificial Intelligence and Machine Learning, 2013
- Game Theory and Mechanism Design2013
- Legibility and predictability of robot motion2013
- The influence of agent reliability on trust in human-agent collaboration2008
- The Fast Downward Planning SystemJournal of Artificial Intelligence Research, 2006