A Framework for Explaining Accident Scenarios for Self-Driving Cars

Omar Wahbi, Yasmin Mansy, Nourhan Ehab, Amr Elmougy

2023

Abstract

In the current state of the art, intelligent decision-making in autonomous vehicles is not typically comprehensible by humans. This deficiency prevents this technology from becoming socially acceptable. In fact, one of the most critical challenges that autonomous vehicles face is the need for making instantaneous decisions as there are reports of self-driving cars unnecessarily hesitating and deviating when objects are detected near the vehicle, hence possibly having car accidents. As a result, gaining a thorough understanding of autonomous vehicle reported accidents is becoming increasingly important. In addition to making real-time decisions, the autonomous car AI system must be able to explain how its decisions are made. Therefore, in this paper, we propose an explanation framework capable of providing the reasons why an autonomous vehicle made a particular decision, specifically in the occurrence of a car accident. Overall, results showed that the framework generates correct explanations for the decisions that were taken by an autonomous car by getting the nearest possible and feasible counterfactual.

Paper Citation

in Harvard Style

Wahbi O., Mansy Y., Ehab N. and Elmougy A. (2023). A Framework for Explaining Accident Scenarios for Self-Driving Cars. In Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART, ISBN 978-989-758-623-1, pages 366-373. DOI: 10.5220/0011674000003393

in Bibtex Style

@conference{icaart23,
author={Omar Wahbi and Yasmin Mansy and Nourhan Ehab and Amr Elmougy},
title={A Framework for Explaining Accident Scenarios for Self-Driving Cars},
booktitle={Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART,},
year={2023},
pages={366-373},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011674000003393},
isbn={978-989-758-623-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART,
TI - A Framework for Explaining Accident Scenarios for Self-Driving Cars
SN - 978-989-758-623-1
AU - Wahbi O.
AU - Mansy Y.
AU - Ehab N.
AU - Elmougy A.
PY - 2023
SP - 366
EP - 373
DO - 10.5220/0011674000003393