A Memristive Associative Learning Circuit for Fault-Tolerant Multi-Sensor Fusion in Autonomous Vehicle

Simple item page
dc.contributor.authorBhardwaj, Kapilcs
dc.contributor.authorSemenov, Dmitriics
dc.contributor.authorĹ otner, Romancs
dc.contributor.authorMajumdar, Sayanics
dc.coverage.issue8cs
dc.coverage.volume7cs
dc.date.accessioned2025-10-17T06:19:53Z
dc.date.available2025-10-17T06:19:53Z
dc.date.issued2025-07-10cs
dc.description.abstractAutonomous vehicles completely rely on accurate multi-sensor fusion to perceive their environment and make driving decisions. However, conventional AI-based perception systems face challenges in irregular conditions such as poor visibility, occlusions, or adverse weather conditions, which can lead to incomplete or degraded information from sensors reaching the central computing/navigation system. This severely impacts perception accuracy, potentially compromising vehicle, and pedestrian safety. This work presents a memristor-based associative learning circuit that enhances fault tolerance by dynamically adapting to multi-sensor inputs, including camera, LiDAR, radar, and ultrasonic sensors. The proposed circuit dynamically reinforces patterns, allowing the system to retain decision-making capabilities even when certain sensors fail or provide incomplete data. The fault tolerance of the circuit is validated through error analysis, proving that accurate outputs are generated even with missing sensor inputs. The system demonstrates an average error of 6.98% across 10 critical driving scenarios, with a power consumption of approximate to 152 mW per scenario, confirming its robustness, energy efficiency and adaptability in case of sensor failures and under-performance. The response time of the circuit has been optimized from milliseconds to seconds, aligning with realistic human-like reaction times required for autonomous navigation.en
dc.description.abstractAutonomous vehicles completely rely on accurate multi-sensor fusion to perceive their environment and make driving decisions. However, conventional AI-based perception systems face challenges in irregular conditions such as poor visibility, occlusions, or adverse weather conditions, which can lead to incomplete or degraded information from sensors reaching the central computing/navigation system. This severely impacts perception accuracy, potentially compromising vehicle, and pedestrian safety. This work presents a memristor-based associative learning circuit that enhances fault tolerance by dynamically adapting to multi-sensor inputs, including camera, LiDAR, radar, and ultrasonic sensors. The proposed circuit dynamically reinforces patterns, allowing the system to retain decision-making capabilities even when certain sensors fail or provide incomplete data. The fault tolerance of the circuit is validated through error analysis, proving that accurate outputs are generated even with missing sensor inputs. The system demonstrates an average error of 6.98% across 10 critical driving scenarios, with a power consumption of approximate to 152 mW per scenario, confirming its robustness, energy efficiency and adaptability in case of sensor failures and under-performance. The response time of the circuit has been optimized from milliseconds to seconds, aligning with realistic human-like reaction times required for autonomous navigation.en
dc.formattextcs
dc.format.extent1-16cs
dc.format.mimetypeapplication/pdfcs
dc.identifier.citationAdvanced Intelligent Systems. 2025, vol. 7, issue 8, p. 1-16.en
dc.identifier.doi10.1002/aisy.202500215cs
dc.identifier.issn2640-4567cs
dc.identifier.orcid0000-0002-2430-1815cs
dc.identifier.other198464cs
dc.identifier.researcheridG-4209-2017cs
dc.identifier.scopus21834721500cs
dc.identifier.urihttps://hdl.handle.net/11012/255587
dc.language.isoencs
dc.relation.ispartofAdvanced Intelligent Systemscs
dc.relation.urihttps://advanced.onlinelibrary.wiley.com/doi/full/10.1002/aisy.202500215cs
dc.rightsCreative Commons Attribution 4.0 Internationalcs
dc.rights.accessopenAccesscs
dc.rights.sherpahttp://www.sherpa.ac.uk/romeo/issn/2640-4567/cs
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/cs
dc.subjectanalog circuitsen
dc.subjectassociative learningen
dc.subjectautonomous vehiclesen
dc.subjectfault toleranceen
dc.subjectmemristorsen
dc.subjectsensor fusionen
dc.subjectanalog circuits
dc.subjectassociative learning
dc.subjectautonomous vehicles
dc.subjectfault tolerance
dc.subjectmemristors
dc.subjectsensor fusion
dc.titleA Memristive Associative Learning Circuit for Fault-Tolerant Multi-Sensor Fusion in Autonomous Vehicleen
dc.title.alternativeA Memristive Associative Learning Circuit for Fault-Tolerant Multi-Sensor Fusion in Autonomous Vehicleen
dc.type.driverarticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen
sync.item.dbidVAV-198464en
sync.item.dbtypeVAVen
sync.item.insts2025.10.17 08:19:53en
sync.item.modts2025.10.16 10:33:15en
thesis.grantorVysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií. Ústav radioelektronikycs
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Advanced Intelligent Systems 2025 Bhardwaj A Memristive Associative Learning Circuit for FaultTolerant MultiSensor.pdf
Size:
2.14 MB
Format:
Adobe Portable Document Format
Description:
file Advanced Intelligent Systems 2025 Bhardwaj A Memristive Associative Learning Circuit for FaultTolerant MultiSensor.pdf
Download
Collections
Ăšstav radioelektroniky