Adaptive monitoring for autonomous vehicles using the HAFLoop architecture
Artikel i vetenskaplig tidskrift, 2021

Current Self-Adaptive Systems (SASs) such as Autonomous Vehicles (AVs) are systems able to deal with highly complex contexts. However, due to the use of static feedback loops they are not able to respond to unanticipated situations such as sensor faults. Previously, we have proposed HAFLoop (Highly Adaptive Feedback control Loop), an architecture for adaptive loops in SASs. In this paper, we incorporate HAFLoop into an AV solution that leverages machine learning techniques to determine the best monitoring strategy at runtime. We have evaluated our solution using real vehicles. Evaluation results are promising and demonstrate the great potential of our proposal.

Författare

Edith Zavala

Universitat Politecnica de Catalunya

Xavier Franch

Universitat Politecnica de Catalunya

Jordi Marco

Universitat Politecnica de Catalunya

Christian Berger

Software Engineering 2

Göteborgs universitet

Enterprise Information Systems

1751-7575 (ISSN) 1751-7583 (eISSN)

Vol. 15 2 270-298

Ämneskategorier (SSIF 2025)

Datavetenskap (datalogi)

Inbäddad systemteknik

Datorsystem

DOI

10.1080/17517575.2020.1844305

Mer information

Senast uppdaterat

2025-06-27