Explain Yourself: A Natural Language Interface for Scrutable Autonomous Robots

By Javier Chiyah-Garcia, David A. Robb, Xingkun Liu, Atanas Laskov, Pedro Patrón, Helen Wright Hastie. 2018

26 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Social Psychology, Human-Computer Interaction, Robotics & Control

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. David A. Robb
2. Sethu Vijayakumar
3. Paul N. Bennett
4. Subramanian Ramamoorthy
5. Helen Wright Hastie
6. Saleema Amershi
7. Rafal Kocielnik
8. Ronald P. A. Petrick

In Social Psychology

1. David A. Robb
2. Sethu Vijayakumar
3. Helen Wright Hastie
4. Saleema Amershi

In Human-Computer Interaction

1. Paul N. Bennett
2. Saleema Amershi
3. Rafal Kocielnik

In Robotics & Control

1. Sethu Vijayakumar
2. Saleema Amershi

Citations in the corpus

• Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI) (2018, background): “Recent works have investigated the possibilities of explainability of advanced autonomous agents like socially interactive robots [175]–[178].”
• Will You Accept an Imperfect AI?: Exploring Designs for Adjusting End-user Expectations of AI Systems (2019, methodology): “Furthermore, the strategies proposed in many of these works, with notable exceptions of [18, 40], rely on a technical ability to generate end-user explanations from the algorithms themselves (i.e., in Lim et al. [35] decision tree path traversal was used to generate free-text description presented…”
• FLIN: A Flexible Natural Language Interface for Web Navigation (2020, unknown): “…Gao et al., 2015), robot navigation (Artzi and Zettlemoyer, 2013; Tellex et al., 2011; Janner et al., 2018; Guu et al., 2017; Fried et al., 2018; Garcia et al., 2018), object manipulation (Frank and Goodman, 2012), object selection in commands (Golland et al., 2010; Smith et al., 2013;…”
• The ORCA Hub: Explainable Offshore Robotics through Intelligent Interfaces (2018, background): “This could be done through natural language, building on prior work on the MIRIAM System (see Figure 1) [2, 3]; or through visualisation.”