English

Explain Yourself: A Natural Language Interface for Scrutable Autonomous Robots

Computation and Language 2018-03-07 v1 Artificial Intelligence Human-Computer Interaction

Abstract

Autonomous systems in remote locations have a high degree of autonomy and there is a need to explain what they are doing and why in order to increase transparency and maintain trust. Here, we describe a natural language chat interface that enables vehicle behaviour to be queried by the user. We obtain an interpretable model of autonomy through having an expert 'speak out-loud' and provide explanations during a mission. This approach is agnostic to the type of autonomy model and as expert and operator are from the same user-group, we predict that these explanations will align well with the operator's mental model, increase transparency and assist with operator training.

Keywords

Cite

@article{arxiv.1803.02088,
  title  = {Explain Yourself: A Natural Language Interface for Scrutable Autonomous Robots},
  author = {Francisco J. Chiyah Garcia and David A. Robb and Xingkun Liu and Atanas Laskov and Pedro Patron and Helen Hastie},
  journal= {arXiv preprint arXiv:1803.02088},
  year   = {2018}
}

Comments

2 pages. Peer reviewed position paper accepted in the Explainable Robotic Systems Workshop, ACM Human-Robot Interaction conference, March 2018, Chicago, IL USA

R2 v1 2026-06-23T00:43:30.014Z