Building the Foundation of Robot Explanation Generation Using Behavior Trees

Bibliographic Data

ID22190850
AuthorsHan Zhao (0000-0002-8579-1600, University of Massachusetts Lowell), Zhao Han (0000-0002-0743-6806, University of Massachusetts Lowell, Lowell, MA, USA), Daniel Giger (University of Massachusetts Lowell), Jordan Allspaw (University of Massachusetts Lowell), Michael S Lee (0000-0001-8407-3423, Carnegie Mellon University), Henny Admoni (0000-0003-1796-2196, Carnegie Mellon University), Holly A Yanco (0000-0002-9962-5865, University of Massachusetts Lowell)
Year2021
Volume10
Issue3
Pages1-31
Publication date2021-09-30
Peer ReviewedYes
Open AccessYes
TypeARTICLE
VenueACM Transactions on Human-Robot Interaction (JOURNAL)
Journal identifiersISSN: 2573-9522 • E-ISSN: 2573-9522
PublisherAssociation for Computing Machinery (ACM) (PUBLISHER)
DOI10.1145/3457185
OpenAlexW3180252218
LanguageEN
Citations received3
References cited33

As autonomous robots continue to be deployed near people, robots need to be able to explain their actions. In this article, we focus on organizing and representing complex tasks in a way that makes them readily explainable. Many actions consist of sub-actions, each of which may have several sub-actions of their own, and the robot must be able to represent these complex actions before it can explain them. To generate explanations for robot behavior, we propose using Behavior Trees (BTs), which are a powerful and rich tool for robot task specification and execution. However, for BTs to be used for robot explanations, their free-form, static structure must be adapted. In this work, we add structure to previously free-form BTs by framing them as a set of semantic sets {goal, subgoals, steps, actions} and subsequently build explanation generation algorithms that answer questions seeking causal information about robot behavior. We make BTs less static with an algorithm that inserts a subgoal that satisfies all dependencies. We evaluate our BTs for robot explanation generation in two domains: a kitting task to assemble a gearbox, and a taxi simulation. Code for the behavior trees (in XML) and all the algorithms is available at github.com/uml-robotics/robot-explanation-BTs

Behavior-based robotics · Human–computer interaction · Programming language · Robot · Robotics · Bayesian Modeling and Causal Inference · Computer Science · Engineering · Logic, Reasoning, and Knowledge · Reinforcement Learning in Robotics · Artificial Intelligence

Tools

Open DOIOpen Access