WYSD 2022

“Why Didn’t I Do It?” A Study Design to Evaluate Robot Explanations

The “detect screw” subtree with Assumption Checker nodes (prefixed C, green names) and Action nodes (prefixed A, white names). The root RetryUntilSuccessful node retries the subtree up to three times if a failure or assumption violation occurs. The ReactiveSequenceNode asynchronously runs all actions including “lift torso”, “look at table”, and “detect screw” while continuously checking the assumption, “check updated head3DCamera”. An example of pre and post-conditions can be seen before and after the “detect screw” action.

As robot systems are becoming ubiquitous in more complex tasks, there is a pressing need for robots to be able to explain their behaviors in order to gain trust and acceptance. In this paper, we discuss our plan for an online human subjects study to evaluate our new system for explanation generation. Specifically, the… Continue reading “Why Didn’t I Do It?” A Study Design to Evaluate Robot Explanations

Published

THRI, 2021

Building The Foundation of Robot Explanation Generation Using Behavior Trees

Behavior tree, robot task representation

As autonomous robots continue to be deployed near people, robots need to be able to explain their actions. In this paper, 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… Continue reading Building The Foundation of Robot Explanation Generation Using Behavior Trees

Published