Assessment of Radiation-Induced Soft Error on Unmanned Surface Vehicles

Marcos A. Fleck; Elisa G. Pereira; Jonas F. Gava; Henrique B. Silva; Fernando G. Moraes; Ney L. V. Calazans; Felipe Meneguzzi; Rodrigo P. Bastos; Ricardo A. L. Reis; Luciano Ost; Rafael Garibotti

doi:10.1109/TNS.2024.3378807

Assessment of Radiation-Induced Soft Error on Unmanned Surface Vehicles

Marcos A. Fleck, Elisa G. Pereira, Jonas F. Gava, Henrique B. Silva, Fernando G. Moraes, Ney L. V. Calazans, Felipe Meneguzzi, Rodrigo P. Bastos, Ricardo A. L. Reis, Luciano Ost, Rafael Garibotti

Research output: Contribution to journal › Article › peer-review

Abstract

The presence of Unmanned Surface Vehicles (USVs) is increasingly frequent on lakes and water reservoirs, performing tasks such as monitoring water quality or delivering goods across the water. However, the emergence of such autonomous vessels raises concerns in terms of safety for people sharing the same environment and the risk of collisions with fixed structures and floating bodies, including other vessels. Therefore, the detection of obstacles and its reliable operation become primary in USVs. This work explores the effects caused by neutron radiation on an object detection algorithm tailored for USVs. Results report 77 silent data corruption (SDC)-induced failures, showing that radiation-induced soft errors contribute to missed and false detection of respectively existing and non-existent objects. Furthermore, results suggest that object detection algorithms running with the multi-core strategy ( FITSDC rate of 34.3 at sea level and 308.6 at Lake Titicaca) exhibit a 16.4% greater resilience to SDCs compared to the single-core strategy.

Original language	English
Journal	IEEE Transactions on Nuclear Science
Early online date	18 Mar 2024
DOIs	https://doi.org/10.1109/TNS.2024.3378807
Publication status	E-pub ahead of print - 18 Mar 2024

Keywords

Reliability
YOLO
Neutrons
Inference algorithms
Autonomous vehicles
Safety
Feature extraction
Object Recognition Algorithm
Neutron Radiation
Unmanned Surface Vehicles
Uncrewed Surface Vessels
USVs

Access to Document

10.1109/TNS.2024.3378807Licence: Unspecified

Cite this

@article{4911fa073d784fa1bc4d6782a660574b,

title = "Assessment of Radiation-Induced Soft Error on Unmanned Surface Vehicles",

abstract = "The presence of Unmanned Surface Vehicles (USVs) is increasingly frequent on lakes and water reservoirs, performing tasks such as monitoring water quality or delivering goods across the water. However, the emergence of such autonomous vessels raises concerns in terms of safety for people sharing the same environment and the risk of collisions with fixed structures and floating bodies, including other vessels. Therefore, the detection of obstacles and its reliable operation become primary in USVs. This work explores the effects caused by neutron radiation on an object detection algorithm tailored for USVs. Results report 77 silent data corruption (SDC)-induced failures, showing that radiation-induced soft errors contribute to missed and false detection of respectively existing and non-existent objects. Furthermore, results suggest that object detection algorithms running with the multi-core strategy ( FITSDC rate of 34.3 at sea level and 308.6 at Lake Titicaca) exhibit a 16.4% greater resilience to SDCs compared to the single-core strategy.",

keywords = "Reliability, YOLO, Neutrons, Inference algorithms, Autonomous vehicles, Safety, Feature extraction, Object Recognition Algorithm, Neutron Radiation, Unmanned Surface Vehicles, Uncrewed Surface Vessels, USVs",

author = "Fleck, {Marcos A.} and Pereira, {Elisa G.} and Gava, {Jonas F.} and Silva, {Henrique B.} and Moraes, {Fernando G.} and Calazans, {Ney L. V.} and Felipe Meneguzzi and Bastos, {Rodrigo P.} and Reis, {Ricardo A. L.} and Luciano Ost and Rafael Garibotti",

year = "2024",

month = mar,

day = "18",

doi = "10.1109/TNS.2024.3378807",

language = "English",

journal = "IEEE Transactions on Nuclear Science",

issn = "0018-9499",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Assessment of Radiation-Induced Soft Error on Unmanned Surface Vehicles

AU - Fleck, Marcos A.

AU - Pereira, Elisa G.

AU - Gava, Jonas F.

AU - Silva, Henrique B.

AU - Moraes, Fernando G.

AU - Calazans, Ney L. V.

AU - Meneguzzi, Felipe

AU - Bastos, Rodrigo P.

AU - Reis, Ricardo A. L.

AU - Ost, Luciano

AU - Garibotti, Rafael

PY - 2024/3/18

Y1 - 2024/3/18

N2 - The presence of Unmanned Surface Vehicles (USVs) is increasingly frequent on lakes and water reservoirs, performing tasks such as monitoring water quality or delivering goods across the water. However, the emergence of such autonomous vessels raises concerns in terms of safety for people sharing the same environment and the risk of collisions with fixed structures and floating bodies, including other vessels. Therefore, the detection of obstacles and its reliable operation become primary in USVs. This work explores the effects caused by neutron radiation on an object detection algorithm tailored for USVs. Results report 77 silent data corruption (SDC)-induced failures, showing that radiation-induced soft errors contribute to missed and false detection of respectively existing and non-existent objects. Furthermore, results suggest that object detection algorithms running with the multi-core strategy ( FITSDC rate of 34.3 at sea level and 308.6 at Lake Titicaca) exhibit a 16.4% greater resilience to SDCs compared to the single-core strategy.

AB - The presence of Unmanned Surface Vehicles (USVs) is increasingly frequent on lakes and water reservoirs, performing tasks such as monitoring water quality or delivering goods across the water. However, the emergence of such autonomous vessels raises concerns in terms of safety for people sharing the same environment and the risk of collisions with fixed structures and floating bodies, including other vessels. Therefore, the detection of obstacles and its reliable operation become primary in USVs. This work explores the effects caused by neutron radiation on an object detection algorithm tailored for USVs. Results report 77 silent data corruption (SDC)-induced failures, showing that radiation-induced soft errors contribute to missed and false detection of respectively existing and non-existent objects. Furthermore, results suggest that object detection algorithms running with the multi-core strategy ( FITSDC rate of 34.3 at sea level and 308.6 at Lake Titicaca) exhibit a 16.4% greater resilience to SDCs compared to the single-core strategy.

KW - Reliability

KW - YOLO

KW - Neutrons

KW - Inference algorithms

KW - Autonomous vehicles

KW - Safety

KW - Feature extraction

KW - Object Recognition Algorithm

KW - Neutron Radiation

KW - Unmanned Surface Vehicles

KW - Uncrewed Surface Vessels

KW - USVs

U2 - 10.1109/TNS.2024.3378807

DO - 10.1109/TNS.2024.3378807

M3 - Article

SN - 0018-9499

JO - IEEE Transactions on Nuclear Science

JF - IEEE Transactions on Nuclear Science

ER -

Assessment of Radiation-Induced Soft Error on Unmanned Surface Vehicles

Abstract

Keywords

Access to Document

Fingerprint

Cite this