Enregistré dans:
Détails bibliographiques
Auteurs principaux: Kenny, Eoin M., Dharmavaram, Akshay, Lee, Sang Uk, Phan-Minh, Tung, Rajesh, Shreyas, Hu, Yunqing, Major, Laura, Tomov, Momchil S., Shah, Julie A.
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2411.18714
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911333105008640
author Kenny, Eoin M.
Dharmavaram, Akshay
Lee, Sang Uk
Phan-Minh, Tung
Rajesh, Shreyas
Hu, Yunqing
Major, Laura
Tomov, Momchil S.
Shah, Julie A.
author_facet Kenny, Eoin M.
Dharmavaram, Akshay
Lee, Sang Uk
Phan-Minh, Tung
Rajesh, Shreyas
Hu, Yunqing
Major, Laura
Tomov, Momchil S.
Shah, Julie A.
contents Self-driving cars increasingly rely on deep neural networks to achieve human-like driving. The opacity of such black-box planners makes it challenging for the human behind the wheel to accurately anticipate when they will fail, with potentially catastrophic consequences. While research into interpreting these systems has surged, most of it is confined to simulations or toy setups due to the difficulty of real-world deployment, leaving the practical utility of such techniques unknown. Here, we introduce the Concept-Wrapper Network (CW-Net), a method for explaining the behavior of machine-learning-based planners by grounding their reasoning in human-interpretable concepts. We deploy CW-Net on a real self-driving car and show that the resulting explanations improve the human driver's mental model of the car, allowing them to better predict its behavior. To our knowledge, this is the first demonstration that explainable deep learning integrated into self-driving cars can be both understandable and useful in a realistic deployment setting. CW-Net accomplishes this level of intelligibility while providing explanations which are causally faithful and do not sacrifice driving performance. Overall, our study establishes a general pathway to interpretability for autonomous agents by way of concept-based explanations, which could help make them more transparent and safe.
format Preprint
id arxiv_https___arxiv_org_abs_2411_18714
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Explainable deep learning improves human mental models of self-driving cars
Kenny, Eoin M.
Dharmavaram, Akshay
Lee, Sang Uk
Phan-Minh, Tung
Rajesh, Shreyas
Hu, Yunqing
Major, Laura
Tomov, Momchil S.
Shah, Julie A.
Robotics
Artificial Intelligence
Machine Learning
Self-driving cars increasingly rely on deep neural networks to achieve human-like driving. The opacity of such black-box planners makes it challenging for the human behind the wheel to accurately anticipate when they will fail, with potentially catastrophic consequences. While research into interpreting these systems has surged, most of it is confined to simulations or toy setups due to the difficulty of real-world deployment, leaving the practical utility of such techniques unknown. Here, we introduce the Concept-Wrapper Network (CW-Net), a method for explaining the behavior of machine-learning-based planners by grounding their reasoning in human-interpretable concepts. We deploy CW-Net on a real self-driving car and show that the resulting explanations improve the human driver's mental model of the car, allowing them to better predict its behavior. To our knowledge, this is the first demonstration that explainable deep learning integrated into self-driving cars can be both understandable and useful in a realistic deployment setting. CW-Net accomplishes this level of intelligibility while providing explanations which are causally faithful and do not sacrifice driving performance. Overall, our study establishes a general pathway to interpretability for autonomous agents by way of concept-based explanations, which could help make them more transparent and safe.
title Explainable deep learning improves human mental models of self-driving cars
topic Robotics
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2411.18714