Kaspar Causally Explains: Causal Explanation in an Assistive Robot for Children with Autism Spectrum Disorder

Hugo Araujo, Patrick Holthaus, Marina Sarda Gou, Gabriella Lakatos, Giulia Galizia, Luke Wood, Ben Robins, Mohammadreza Mousavi, Farshid Amirabdollahian

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Downloads (Pure)


The Kaspar robot has been used with great success to work as an education and social mediator with children with autism spectrum disorder. Enabling the robot to automatically generate causal explanations is considered a key to enrich the interaction scenarios for children and thereby promote additional trust in the robot. To this end, we present a formal theory of causal explanation to be embedded in Kaspar. Based on this theory, we build a causal model and an efficient causal analysis method to calculate causal explanations. We implement our method using Java with inputs provided by a human operator. This model automatically generates the causal explanation that are then spoken by Kaspar. We validate our explanations for user satisfaction in an empirical evaluation.
Original languageEnglish
Title of host publicationSocial Robotics
Subtitle of host publication14th International Conference, ICSR 2022
Publication statusAccepted/In press - 14 Oct 2022
Event14th International Conference on Social Robotics - Florence, Italy
Duration: 13 Dec 202216 Dec 2022

Publication series

NameLecture Notes in Computer Science


Conference14th International Conference on Social Robotics
Abbreviated titleICSR
Internet address


Dive into the research topics of 'Kaspar Causally Explains: Causal Explanation in an Assistive Robot for Children with Autism Spectrum Disorder'. Together they form a unique fingerprint.

Cite this