TY - GEN
T1 - A Decentralized Explanatory System for Intelligent Cyber-Physical Systems
AU - Houzé, Étienne
AU - Dessalles, Jean Louis
AU - Diaconescu, Ada
AU - Menga, David
AU - Schumann, Mathieu
N1 - Publisher Copyright:
© 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
PY - 2022/1/1
Y1 - 2022/1/1
N2 - The Internet of Things (IoT) has been a prominent application for Intelligent Systems in recent years. While the increasing demand for explanations led to many advances in Explainable Artificial Intelligence (XAI), most solutions focus on systems where a single agent takes all decisions to be explained. However within the IoT context, Cyber-Physical Systems (CPS) are decentralized, with multiple agents coordinating their decisions to control the overall CPS. By contrast users expect coherent system-wide explanations, as if they were generated by a single agent. We propose a decentralized Explanation System generating such explanations while preserving the advantages of decentralized control: separation of concerns, heterogeneity, flexibility,..Our architecture relies on: i) decentralized XAI Component specialists for providing partial explanations based on local knowledge; ii) a central generic Spotlight composing local explanations into a global explanation. We illustrate and qualitatively evaluate our approach via a proof-of-concept implementation for a smart home system.
AB - The Internet of Things (IoT) has been a prominent application for Intelligent Systems in recent years. While the increasing demand for explanations led to many advances in Explainable Artificial Intelligence (XAI), most solutions focus on systems where a single agent takes all decisions to be explained. However within the IoT context, Cyber-Physical Systems (CPS) are decentralized, with multiple agents coordinating their decisions to control the overall CPS. By contrast users expect coherent system-wide explanations, as if they were generated by a single agent. We propose a decentralized Explanation System generating such explanations while preserving the advantages of decentralized control: separation of concerns, heterogeneity, flexibility,..Our architecture relies on: i) decentralized XAI Component specialists for providing partial explanations based on local knowledge; ii) a central generic Spotlight composing local explanations into a global explanation. We illustrate and qualitatively evaluate our approach via a proof-of-concept implementation for a smart home system.
KW - Cyber-Physical Systems
KW - Decentralization
KW - Explanation
UR - https://www.scopus.com/pages/publications/85113204192
U2 - 10.1007/978-3-030-82193-7_48
DO - 10.1007/978-3-030-82193-7_48
M3 - Conference contribution
AN - SCOPUS:85113204192
SN - 9783030821920
T3 - Lecture Notes in Networks and Systems
SP - 719
EP - 738
BT - Intelligent Systems and Applications - Proceedings of the 2021 Intelligent Systems Conference IntelliSys
A2 - Arai, Kohei
PB - Springer Science and Business Media Deutschland GmbH
T2 - Intelligent Systems Conference, IntelliSys 2021
Y2 - 2 September 2021 through 3 September 2021
ER -