No AccessFull-Length Papers

Benchmarking Deep Learning Models on Myriad and Snapdragon Processors for Space Applications

Emily R. Dunkel

https://orcid.org/0000-0002-9105-5458

Jet Propulsion Laboratory, California Institute of Technology, Pasadena, California 91109

*Data Scientist, 4800 Oak Grove Dr., Mail Stop 158-242; .

Search for more papers by this author

Jason Swope

https://orcid.org/0000-0002-3733-3242

Jet Propulsion Laboratory, California Institute of Technology, Pasadena, California 91109

†Data Scientist, 4800 Oak Grove Dr.

Search for more papers by this author

Alberto Candela

https://orcid.org/0000-0002-5510-7935

Jet Propulsion Laboratory, California Institute of Technology, Pasadena, California 91109

‡Data Scientist, 4800 Oak Grove Dr., Mail Stop T1721.

Search for more papers by this author

Lauren West

Jet Propulsion Laboratory, California Institute of Technology, Pasadena, California 91109

§Jet Propulsion Laboratory Student Intern, Harvey Mudd College, Claremont, California 91711; currently Software Engineer at Netflix, Los Gatos, California.

Search for more papers by this author

Steve A. Chien

https://orcid.org/0000-0003-1023-9480

Jet Propulsion Laboratory, California Institute of Technology, Pasadena, California 91109

¶Engineering Fellow, Senior Research Scientist, and Group Supervisor, 4800 Oak Grove Dr., Mail Stop 301-221.

Search for more papers by this author

Zaid Towfic

Jet Propulsion Laboratory, California Institute of Technology, Pasadena, California 91109

**Group Supervisor, 4800 Oak Grove Dr., Mail Stop 161-260.

Search for more papers by this author

Léonie Buckley

Ubotica Technologies, Dublin D11 KXN4, Republic of Ireland

††Computer Engineer, Old Finglas Rd., Glasnevin.

Search for more papers by this author

Juan Romero-Cañas

Ubotica Technologies, 13005 Ciudad Real, Spain

‡‡Software Engineer, Camino de Moledores s/n, Incubadora de Empresas, Local 0.32.

Search for more papers by this author

Jose Luis Espinosa-Aranda

Ubotica Technologies, 13005 Ciudad Real, Spain

§§Principal Engineer, Camino de Moledores s/n, Incubadora de Empresas, Local 0.32.

Search for more papers by this author

Elena Hervas-Martin

Ubotica Technologies, 13005 Ciudad Real, Spain

¶¶Software Engineer, Camino de Moledores s/n, Incubadora de Empresas, Local 0.32.

Search for more papers by this author

and

Mark R. Fernandez

Hewlett Packard Enterprise, Spring, Texas 77389

***Principal Investigator, Spaceborne Computer-2, 1701 E. Mossy Oaks Rd.

Search for more papers by this author

Published Online:5 Sep 2023https://doi.org/10.2514/1.I011216

Abstract

Future space missions can benefit from processing imagery on board to detect science events, create insights, and respond autonomously. One of the challenges to this mission concept is that traditional space flight computing has limited capabilities because it is derived from much older computing to ensure reliable performance in the extreme environments of space: particularly radiation. Modern commercial-off-the-shelf processors, such as the Movidius Myriad X and the Qualcomm Snapdragon, provide significant improvements in small size, weight, and power packaging; and they offer direct hardware acceleration for deep neural networks, although these processors are not radiation hardened. We deploy neural network models on these processors hosted by Hewlett Packard Enterprise’s Spaceborne Computer-2 on board the International Space Station (ISS). We find that the Myriad and Snapdragon digital signal processors (DSP)/artificial intelligence processors (AIP) provide speed improvement over the Snapdragon CPU in all cases except single-pixel networks (typically greater than 10 times for DSP/AIP). In addition, the discrepancy introduced through quantization and porting of our Jet Propulsion Laboratory models was usually quite low (less than 5%). Models were run multiple times, and memory checkers were deployed to test for radiation effects. To date, we have found no difference in output between ground and ISS runs, and no memory checker errors.

References

[1] “Intel Movidius Vision Processing Units,” 2022, https://www.intel.com/content/www/us/en/products/details/processors/movidius-vpu/movidius-myriad-x.html [retrieved 9 Aug. 2023]. Google Scholar
[2] “Snapdragon 855 Mobile Platform,” 2022, https://www.qualcomm.com/snapdragon [retrieved 9 Aug. 2023]. Google Scholar
[3] Giuffrida G., Fanucci L., Meoni G., Batič M., Buckley L., Dunne A., van Dijk C., Esposito M., Hefele J., Vercruyssen N. and Furano G., “The $Φ$ -Sat-1 Mission: The First On-Board Deep Neural Network Demonstrator for Satellite Earth Observation,” Institute of Electrical and Electronics Engineers (IEEE) Transactions on Geoscience and Remote Sensing, Vol. 60, Nov. 2021, pp. 1–14. https://doi.org/10.1109/TGRS.2021.3125567 Google Scholar
[4] “HPE Spaceborne Computer,” 2022, https://www.hpe.com/us/en/compute/hpc/supercomputing/spaceborne.html [retrieved 9 Aug. 2023]. Google Scholar
[5] Benton E. R. and Benton E., “Space Radiation Dosimetry in Low-Earth Orbit and Beyond,” Nuclear Instruments and Methods in Physics Research Section B: Beam Interactions with Materials and Atoms, Vol. 184, Nos. 1–2, 2001, pp. 255–294. https://doi.org/10.1016/S0168-583X(01)00748-0 Crossref Google Scholar
[6] Akopova A., Manaseryan M., Melkonyan A., Tatikyan S. S. and Potapov Y., “Radiation Measurement on the International Space Station,” Radiation Measurements, Vol. 39, No. 2, 2005, pp. 225–228. https://doi.org/10.1016/j.radmeas.2004.06.013 Crossref Google Scholar
[7] “Qualcomm Neural Processing SDK for AI,” 2022, https://developer.qualcomm.com/software/qualcomm-neural-processing-sdk [retrieved 9 Aug. 2023]. Google Scholar
[8] Pedregosa F., Varoquaux G., Gramfort A., Michel V., Thirion B., Grisel O., Blondel M., Prettenhofer P., Weiss R., Dubourg V., Vanderplas J., Passos A., Cournapeau D., Brucher M., Perrot M. and Duchesnay E., “Scikit-Learn: Machine Learning in Python,” Journal of Machine Learning Research, Vol. 12, Nov. 2011, pp. 2825–2830, https://www.jmlr.org/papers/volume12/pedregosa11a/pedregosa11a.pdf [retrieved 9 Aug. 2023]. Google Scholar
[9] “Python-for-Android by Kivy,” 2022, https://kivy.org/doc/stable/guide/packaging-android.html [retrieved 9 Aug. 2023]. Google Scholar
[10] “OpenVINO,” 2021, https://docs.openvino.ai/latest/index.html [retrieved 9 Aug. 2023]. Google Scholar
[11] “Journey to Mars: How Our Collaboration with Jet Propulsion Laboratory Fostered Innovation,” 2022, https://www.qualcomm.com/news/onq/2021/03/17/journey-mars-how-our-collaboration-jet-propulsion-laboratory-fostered-innovation [retrieved 9 Aug. 2023]. Google Scholar
[12] Sheldon D., Gagne J., Daniel A., Vartanian S., Riley R., Kallal E. and Allen G., “Radiation Effects Characterization and System Architecture Options for the 7 nm Snapdragon SA8155P Automotive Grade System on Chip (SoC),” Radiation and its Effects on Components and Systems Conference, NASA TR, 2022, pp. 1–16, https://ntrs.nasa.gov/citations/20230005645 [retrieved 9 Aug. 2023]. Google Scholar
[13] “Ubotica CogniSat-TK,” 2022, https://ubotica.com [retrieved 9 Aug. 2023]. Google Scholar
[14] Buckley L., Dunne A., Furano G. and Tali M., “Radiation Test and in Orbit Performance of MpSoC AI Accelerator,” 2022 Institute of Electrical and Electronics Engineers (IEEE) Aerospace Conference (AERO), IEEE, New York, 2022, pp. 1–9. https://doi.org/10.1109/AERO53065.2022.9843440 Google Scholar
[15] “NVIDIA Jetson Nano Developer,” 2022, https://developer.nvidia.com/embedded/jetson-nano-developer-kit [retrieved 9 Aug. 2023]. Google Scholar
[16] “AI with Jetson Processors,” 2022, https://www.nvidia.com/en-us/autonomous-machines/ [retrieved 9 Aug. 2023]. Google Scholar
[17] “TensorFlow,” Software Package, May 2022, tensorflow.org [retrieved 8 Aug. 2023]. https://doi.org/10.5281/zenodo.6574269 Google Scholar
[18] “NVIDIA T4,” 2022, https://www.nvidia.com/en-us/data-center/tesla-t4/ [retrieved 9 Aug. 2023]. Google Scholar
[19] Jia Y., Shelhamer E., Donahue J., Karayev S., Long J., Girshick R., Guadarrama S. and Darrell T., “Caffe: Convolutional Architecture for Fast Feature Embedding,” Proceedings of the 22nd Association for Computing Machinery (ACM) International Conference on Multimedia, Assoc. for Computing Machinery, New York, 2014, pp. 675–678. https://doi.org/10.1145/2647868.2654889 Google Scholar
[20] “Qualcomm SNPE Software Development Kit Versions,” 2022, https://developer.qualcomm.com/sites/default/files/docs/snpe/revision_history.html [retrieved 9 Aug. 2023]. Google Scholar
[21] Chollet F., “Keras Applications,” 2021, https://keras.io/getting_started/faq/#how-should-i-cite-keras, https://keras.io/api/applications/ [retrieved 9 Aug. 2023]. Google Scholar
[22] Dunkel E., Swope J., Towfic Z., Chien S., Russell D., Sauvageau J., Sheldon D., Romero-Cañas J., Espinosa-Aranda J., Buckley L., Hervas-Martin E., Fernandez M. and Knox C., “Benchmarking Deep Learning Inference of Remote Sensing Imagery on the Qualcomm Snapdragon and Intel Movidius Myriad X Processors Onboard the International Space Station,” Institute of Electrical and Electronics Engineers (IEEE) International Geoscience and Remote Sensing Symposium (IGARSS), IEEE, New York, 2022, pp. 1–4. https://doi.org/10.1109/IGARSS46834.2022.9884906 Google Scholar
[23] Dunkel E., Swope J., Candela A., West L., Chien S., Buckley L., Romero-Canas J., Espinosa-Aranda J. L., Hervas-Martin E., Towfic Z., Russell D., Sauvageau J., Sheldon D., Fernandez M. and Knox C., “Testing Mars Rover, Spectral Unmixing, and Ship Detection Neural Networks, and Memory Checkers on Embedded Systems Onboard the ISS,” Proceedings of 16th Symposium on Advanced Space Technologies in Robotics and Automation, European Space Agency, JPL AI, 2022, pp. 1–8, https://ai.jpl.nasa.gov/public/documents/papers/Dunkel-DL-ISS-ASTRA-2022.pdf [retrieved 7 Aug. 2023]. Google Scholar
[24] Wagstaff K., Lu S., Dunkel E., Grimes K., Zhao B., Cai J., Cole S. B., Doran G., Francis R., Lee J. and Mandrake L., “Mars Image Content Classification: Three Years of NASA Deployment and Recent Advances,” Proceedings of the Association of Artificial Intelligence (AAAI) Conference on Artificial Intelligence, Vol. 35, 2021, pp. 15,204–15,213. https://doi.org/10.1609/aaai.v35i17.17784 Google Scholar
[25] Krizhevsky A., Sutskever I. and Hinton G. E., “Imagenet Classification with Deep Convolutional Neural Networks,” Advances in Neural Information Processing Systems, Vol. 25, NIPS, 2012, pp. 1–9, https://papers.nips.cc/paper/2012/file/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf [retrieved 9 Aug. 2023]. Google Scholar
[26] “Snapdragon Profiler,” 2022, https://developer.qualcomm.com/software/snapdragon-profiler [retrieved 9 Aug. 2023]. Google Scholar
[27] Wagstaff K., Lu Y., Stanboli A., Grimes K., Gowda T. and Padams J., “Deep Mars: CNN Classification of Mars Imagery for the PDS Imaging Atlas,” Proceedings of the Association for the Advancement of Artificial Intelligence (AAAI) Conference on Artificial Intelligence, Vol. 32, Assoc. for the Advancement of Artificial Intelligence, 2018, pp. 7867–7872. https://doi.org/10.1609/aaai.v32i1.11404 Google Scholar
[28] Atha D., Swan R. M., Didier A., Hasnain Z. and Ono M., “Multi-Mission Terrain Classifier for Safe Rover Navigation and Automated Science,” 2022 Institute of Electrical and Electronics Engineers (IEEE) Aerospace Conference (AERO), IEEE, New York, 2022, pp. 1–13. https://doi.org/10.1109/AERO53065.2022.9843615 Google Scholar
[29] Chen L.-C., Papandreou G., Schroff F. and Adam H., “Rethinking Atrous Convolution for Semantic Image Segmentation,” Preprint, submitted 17 June 2017, https://arxiv.org/abs/1706.05587. https://doi.org/10.48550/arXiv.1706.05587 Google Scholar
[30] Towfic Z., Ogbe D., Sauvageau J., Sheldon D., Jongeling A., Chien S., Mirza F., Dunkel E., Swope J., Cretu V. and Ogut M., “Benchmarking and Testing of Qualcomm Snapdragon System-on-Chip for JPL Space Applications and Missions,” Institute of Electrical and Electronics Engineers (IEEE) Aerospace Conference (AERO), IEEE, New York, 2022, pp. 1–12. https://doi.org/10.1109/AERO53065.2022.9843518 Google Scholar
[31] Denbina M., Towfic Z. J., Thill M., Bue B., Kasraee N., Peacock A. and Lou Y., “Flood Mapping Using UAVSAR and Convolutional Neural Networks,” 2020 Institute of Electrical and Electronics Engineers (IEEE) International Geoscience and Remote Sensing Symposium (IGARSS), IEEE, New York, 2020, pp. 3247–3250, https://ieeexplore.ieee.org/document/9324379 [retrieved 7 Aug. 2023]. https://doi.org/10.1109/IGARSS39084.2020.9324379 Google Scholar
[32] Ronneberger O., Fischer P. and Brox T., “U-Net: Convolutional Networks for Biomedical Image Segmentation,” International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer, Berlin, 2015, pp. 234–241. https://doi.org/10.1007/978-3-319-24574-4_28 Google Scholar
[33] Swope J., Chien S., Bosch-Lluis X., Yue Q., Tavallali P., Ogut M., Ramos I., Kangaslahti P., Deal W. and Cooke C., “Using Intelligent Targeting to Increase the Science Return of a Smart Ice Storm Hunting Radar,” International Workshop on Planning and Scheduling for Space (IWPSS), JPL AI (Artificial Intelligence) Website, 2021, pp. 1–9, https://ai.jpl.nasa.gov/public/documents/papers/Swope-SMICES-targeting-IWPSS-2021.pdf [retrieved 7 Aug. 2023]. Google Scholar
[34] Bosch-Lluis X., Chien S, ., Yue Q., Swope J., P. P. T., Ogut M., Ramos I., Kangaslahti P., Deal W. and Cooke C., “Developing Radiometer and Radar Synergies Using Machine Learning,” International Geoscience and Remote Sensing Symposium (IGARSS), IEEE Xplore, 2021, pp. 1–4. Google Scholar
[35] “Advanced Information Systems Technology 2019 Awards,” Dec. 2021, https://esto.nasa.gov/files/solicitations/IIP_19/ROSES2019_IIP_A49_awards.html#deal [retrieved 9 Aug. 2023]. Google Scholar
[36] Chien S., Swope J., Yue Q., Lluis-Bosch J. and Deal W., “Using a Digital Twin Weather Research and Forecasting (WRF) Model for Machine Learning of Deep Convective Ice Storms,” Proceedings of the Fall Meeting of the American Geophysical Union, American Geophysical Union, Washington, D.C., 2021, https://agu.confex.com/agu/fm21/meetingapp.cgi/Paper/804752 [retrieved 9 Aug. 2023]. Google Scholar
[37] Candela Garza A., “Bayesian Models for Science-Driven Robotic Exploration,” Ph.D. Thesis, Carnegie–Mellon Univ., Pittsburgh, PA, Sept. 2021, https://www.ri.cmu.edu/app/uploads/2021/09/albertoc_phd_ri_2021.pdf [retrieved 9 Aug. 2023]. Google Scholar
[38] Hochberg E. J. and Gierach M. M., “Missing the Reef for the Corals: Unexpected Trends between Coral Reef Condition and the Environment at the Ecosystem Scale,” Frontiers in Marine Science, Vol. 8, Aug. 2021, Paper 727038, https://www.frontiersin.org/article/10.3389/fmars.2021.727038 [retrieved 9 Aug. 2023]. https://doi.org/10.3389/fmars.2021.727038 Crossref Google Scholar
[39] Thompson D. R., Hochberg E. J., Asner G. P., Green R. O., Knapp D. E., Gao B.-C., Garcia R., Gierach M., Lee Z., Maritorena S. and Fick R., “Airborne Mapping of Benthic Reflectance Spectra with Bayesian Linear Mixtures,” Remote Sensing of Environment, Vol. 200, Oct. 2017, pp. 18–30, https://www.sciencedirect.com/science/article/pii/S0034425717303449 [retrieved 9 Aug. 2023]. https://doi.org/10.1016/j.rse.2017.07.030 Crossref Google Scholar
[40] Candela A., Thompson D. R., Wettergreen D., Cawse-Nicholson K., Geier S., Eastwood M. L. and Green R. O., “Probabilistic Super Resolution for Mineral Spectroscopy,” Proceedings of the Association for the Advancement of Artificial Intelligence (AAAI) Conference on Artificial Intelligence, Vol. 34, Assoc. for the Advancement of Artificial Intelligence, 2020, pp. 13,241–13,247. https://doi.org/10.1609/aaai.v34i08.7030 Google Scholar
[41] Swayze G. A., Clark R. N., Goetz A. F., Livo K. E., Breit G. N., Kruse F. A., Sutley S. J., Snee L. W., Lowers H. A., Post J. L., Stoffregen R. E. and Ashley R. P., “Mapping Advanced Argillic Alteration at Cuprite, Nevada, Using Imaging Spectroscopy,” Economic Geology, Vol. 109, No. 5, 2014, pp. 1179–1221. https://doi.org/10.2113/econgeo.109.5.1179 Crossref Google Scholar
[42] Deng J., Dong W., Socher R., Li L.-J., Li K. and Fei-Fei L., “Imagenet: A Large-Scale Hierarchical Image Database,” 2009 Institute of Electrical and Electronics Engineers (IEEE) Conference on Computer Vision and Pattern Recognition, IEEE, New York, 2009, pp. 248–255, https://image-net.org/static_files/papers/imagenet_cvpr09.pdf [retrieved 9 Aug. 2023]. Google Scholar
[43] “Imagenette,” GitHub (online database), 2021, https://github.com/fastai/imagenette [retrieved 9 Aug. 2023]. Google Scholar
[44] Yun S. and Wong A., “Do All MobileNets Quantize Poorly? Gaining Insights into the Effect of Quantization on Depthwise Separable Convolutional Networks Through the Eyes of Multi-Scale Distributional Dynamics,” Proceedings of the Institute of Electrical and Electronics Engineers (IEEE)/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Publ., Piscataway, NJ, 2021, pp. 2447–2456, https://openaccess.thecvf.com/content/CVPR2021W/MAI/papers/Yun_Do_All_MobileNets_Quantize_Poorly_Gaining_Insights_Into_the_Effect_CVPRW_2021_paper.pdf [retrieved 9 Aug. 2023]. Google Scholar
[45] “AI Model Efficiency Toolkit,” 2022, https://developer.qualcomm.com/software/ai-model-efficiency-toolkit [retrieved 9 Aug. 2023]. Google Scholar
[46] Murphy J., Ward J. E. and Mac Namee B., “Machine Learning in Space: A Review of Machine Learning Algorithms and Hardware for Space Applications,” Artificial Intelligence and Computer Science (AICS), CEUR (Sun SITE Central Europe), 2021, pp. 72–83, http://star.informatik.rwth-aachen.de/Publications/CEUR-WS/Vol-3105/paper21.pdf [retrieved 9 Aug. 2023]. Google Scholar
[47] Bruhn F. C., Tsog N., Kunkel F., Flordal O. and Troxel I., “Enabling Radiation Tolerant Heterogeneous GPU-Based Onboard Data Processing in Space,” CEAS Space Journal, Vol. 12, No. 4, 2020, pp. 551–564. https://doi.org/10.1007/s12567-020-00321-9 Crossref Google Scholar
[48] Furano G., Meoni G., Dunne A., Moloney D., Ferlet-Cavrois V., Tavoularis A., Byrne J., Buckley L., Psarakis M., Voss K.-O. and Fanucci L., “Towards the Use of Artificial Intelligence on the Edge in Space Systems: Challenges and Opportunities,” Institute of Electrical and Electronics Engineers (IEEE) Aerospace and Electronic Systems Magazine, Vol. 35, No. 12, 2020, pp. 44–56. https://doi.org/10.1109/MAES.2020.3008468 Crossref Google Scholar
[49] Ignatov A., Timofte R., Kulik A., Yang S., Wang K., Baum F., Wu M., Xu L. and Van Gool L., “AI Benchmark: All About Deep Learning on Smartphones in 2019,” 2019 Institute of Electrical and Electronics Engineers (IEEE) International Conference on Computer Vision Workshops (ICCV Workshops), IEEE, New York, 2019, pp. 3617–3635. https://doi.org/10.1109/ICCVW.2019.00447 Google Scholar
[50] Truong N. Q., Nguyen P. H., Nam S. H. and Park K. R., “Deep Learning-Based Super-Resolution Reconstruction and Marker Detection for Drone Landing,” Institute of Electrical and Electronics Engineers (IEEE) Access, Vol. 7, May 2019, pp. 61,639–61,655. https://doi.org/10.1109/ACCESS.2019.2915944 Google Scholar
[51] “Rasbperry Pi 3 Model B,” 2022, https://www.raspberrypi.com/products/raspberry-pi-3-model-b/ [retrieved 9 Aug. 2023]. Google Scholar
[52] Hochstetler J., Padidela R., Chen Q., Yang Q. and Fu S., “Embedded Deep Learning for Vehicular Edge Computing,” 2018 Institute of Electrical and Electronics Engineers/Association for Computing Machinery (IEEE/ACM) Symposium on Edge Computing (SEC), IEEE, New York, 2018, pp. 341–343. https://doi.org/10.1109/SEC.2018.00038 Google Scholar
[53] Sethi K., Parmar V. and Suri M., “Low-Power Hardware-Based Deep-Learning Diagnostics Support Case Study,” 2018 Institute of Electrical and Electronics Engineers (IEEE) Biomedical Circuits and Systems Conference (BioCAS), IEEE, New York, 2018, pp. 1–4. https://doi.org/10.1109/BIOCAS.2018.8584697 Google Scholar
[54] Çambay V. Y., Uçar A. and Arserim M. A., “Object Detection on FPGAs and GPUs by Using Accelerated Deep Learning,” 2019 International Artificial Intelligence and Data Processing Symposium (IDAP), IEEE, New York, 2019, pp. 1–5. https://doi.org/10.1109/IDAP.2019.8875870 Google Scholar
[55] Hoiem D., Divvala S. K. and Hays J. H., “Pascal VOC 2008 Challenge,” World Literature Today, Vol. 24, No. 1, 2009, pp. 1–4, https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=9c327cf1bb8435a8fba27b6ace50bb907078d8d1. Google Scholar
[56] Sahu P., Yu D. and Qin H., “Apply Lightweight Deep Learning on Internet Of Things for Low-Cost and Easy-to-Access Skin Cancer Detection,” Medical Imaging 2018: Imaging Informatics for Healthcare, Research, and Applications, Vol. 10579, International Soc. for Optics and Photonics (SPIE), Bellingham, WA, 2018, pp. 254–262. https://doi.org/10.1117/12.2293350 Google Scholar
[57] Meena S. D. and Agilandeeswari L., “Adaboost Cascade Classifier for Classification and Identification of Wild Animals Using Movidius Neural Compute Stick,” International Journal of Engineering and Advanced Technology (IJEAT), Vol. 9, No. 13, 2019, pp. 495–499. https://doi.org/10.35940/ijeat.A1089.1291S319 Crossref Google Scholar
[58] Agarwal S., Hervas-Martin E., Byrne J., Dunne A., Luis Espinosa-Aranda J. and Rijlaarsdam D., “An Evaluation of Low-Cost Vision Processors for Efficient Star Identification,” Sensors, Vol. 20, No. 21, 2020, Paper 6250. https://doi.org/10.3390/s20216250 Crossref Google Scholar
[59] Giuffrida G., Diana L., de Gioia F., Benelli G., Meoni G., Donati M. and Fanucci L., “Cloudscout: A Deep Neural Network for On-Board Cloud Detection on Hyperspectral Images,” Remote Sensing, Vol. 12, No. 14, 2020, Paper 2205. https://doi.org/10.3390/rs12142205 Crossref Google Scholar
[60] Kljucaric L., Johnson A. and George A. D., “Architectural Analysis of Deep Learning on Edge Accelerators,” 2020 Institute of Electrical and Electronics Engineers (IEEE) High Performance Extreme Computing Conference (HPEC), IEEE, New York, 2020, pp. 1–7. https://doi.org/10.1109/HPEC43674.2020.9286209 Google Scholar
[61] Tham M.-L. and Tan W. K., “IoT Based License Plate Recognition System Using Deep Learning and OpenVINO,” 2021 4th International Conference on Sensors, Signal and Image Processing, Association for Computing Machinery, 2021, pp. 7–14. https://doi.org/10.1145/3502814.3502816 Google Scholar
[62] Thangavel K., Spiller D., Sabatini R., Amici S., Sasidharan S. T., Fayek H. and Marzocca P., “Autonomous Satellite Wildfire Detection Using Hyperspectral Imagery and Neural Networks: A Case Study on Australian Wildfire,” Remote Sensing, Vol. 15, No. 3, 2023, Paper 720. https://doi.org/10.3390/rs15030720 Crossref Google Scholar
[63] Murphy J., Ward J. E. and Namee B. M., “Developing Machine Learning Models for Space Based Edge AI Platforms,” 36th Annual Small Satellite Conference, Digital Commons Utah State Univ., 2022, pp. 1–13, https://digitalcommons.usu.edu/smallsat/2022/all2022/79/ [retrieved 9 Aug. 2023]. Google Scholar
[64] Furano G., Meoni G., Dunne A., Moloney D., Ferlet-Cavrois V., Tavoularis A., Byrne J., Buckley L., Psarakis M., Voss K.-O. and Fanucci L., “Towards the Use of Artificial Intelligence on the Edge in Space Systems: Challenges and Opportunities,” IEEE Aerospace and Electronic Systems Magazine, Vol. 35, No. 12, 2020, pp. 44–56. https://doi.org/10.1109/MAES.2020.3008468 Crossref Google Scholar
[65] Navarro J., Samuelsson A., Gingsjö H., Barendt J., Dunne A., Buckley L., Reisis D., Kyriakos A., Papatheofanous E., Bezaitis C., Matthijs P., Ramos J. and Steenari D., “High-Performance Compute Board: A Fault-Tolerant Module for On-Board Vision Processing,” European Workshop on On-Board Data Processing (OBDP2021), academia.edu and Ubotica.com, 2021, pp. 1–7, https://ubotica.com/wp-content/uploads/2021/08/10.05_OBDP2021_Espana_Navarro.pdf [retrieved 9 Aug. 2023]. Google Scholar
[66] Leon V., Bezaitis C., Lentaris G., Soudris D., Reisis D., Papatheofanous E.-A., Kyriakos A., Dunne A., Samuelsson A. and Steenari D., “FPGA and VPU Co-Processing in Space Applications: Development and Testing with DSP/AI Benchmarks,” 2021 28th Institute of Electrical and Electronic Engineers (IEEE) International Conference on Electronics, Circuits, and Systems (ICECS), IEEE, New York, 2021, pp. 1–5. https://doi.org/10.1109/ICECS53924.2021.9665462 Google Scholar
[67] Chien S., Sherwood R., Tran D., Cichy B., Rabideau G., Castano R., Davies A., Mandl D., Frye S., Trout B., Shulman S. and Boyer D., “Using Autonomy Flight Software to Improve Science Return on Earth Observing One,” Journal of Aerospace Computing, Information, and Communication, Vol. 2, No. 4, 2005, pp. 196–216, https://ai.jpl.nasa.gov/public/documents/papers/chien-JACIC2005-UsingAutonomy.pdf [retrieved 7 Aug. 2023]. https://doi.org/10.2514/1.12923 Link Google Scholar
[68] Wagstaff K., Chien S., Altinok A., Rebbapragada U., Thompson D., Schaffer S. and Tran D., “Cloud Filtering and Novelty Detection Using Onboard Machine Learning for the EO-1 Spacecraft,” International Symposium on Artificial Intelligence, Robotics, and Automation for Space (ISAIRAS 2018), JPL AI Website, 2018, pp. 1–4; also AI in the Oceans and Space Workshop, International Joint Conference on Artificial Intelligence (IJCAI 2017), https://ai.jpl.nasa.gov/public/documents/papers/wagstaff-ijcai2017-novelty.pdf [retrieved 7 Aug. 2023]. Google Scholar
[69] Chien S., Doubleday J., Thompson D. R., Wagstaff K., Bellardo J., Francis C., Baumgarten E., Williams A., Yee E., Stanton E. and Piug-Suari J., “Onboard Autonomy on the Intelligent Payload Experiment CubeSat Mission,” Journal of Aerospace Information Systems, Vol. 14, No. 6, 2016, pp. 307–315. https://doi.org/10.2514/1.I010386 Link Google Scholar
[70] Goodwill J., Crum G., MacKinnon J., Brewer C., Monaghan M., Wise T. and Wilson C., “NASA SpaceCube Edge TPU SmallSat Card for Autonomous Operations and Onboard Science-Data Analysis,” 35th Annual Small Satellite Conference, AIAA, Reston, VA, 2021, pp. 1–13, https://digitalcommons.usu.edu/smallsat/2021/all2021/185/ [retrieved 9 Aug. 2023]. Google Scholar
[71] “Google Coral,” 2020, https://coral.ai/products/ [retrieved 9 Aug. 2023]. Google Scholar
[72] Zynq DPU, Software Package, Ver. 3.3, Xilinx Corp., AMD (Advanced Micro Deviced) Document Portal, 2021, p. 338, https://docs.xilinx.com/r/en-US/pg338-dpu?tocId=3xsG16y_QFTWvAJKHbisEw [retrieved 8 Aug. 2023]. Google Scholar
[73] Perryman N., Wilson C. and George A., “Evaluation of Xilinx Versal Architecture for Next-Gen Edge Computing in Space,” 2023 Institute of Electrical and Electronics Engineers (IEEE) Aerospace Conference, IEEE, New York, 2023, pp. 1–11. https://doi.org/10.1109/AERO55745.2023.10115906 Google Scholar
[74] Petry M., Gest P., Koch A., Ghiglione M. and Werner M., “Accelerated Deep-Learning inference on FPGAs in the Space Domain,” Association for Computing Machinery (ACM) International Conference on Computing Frontiers, ACM (Association for Computing Machinery) Digital Library, 2023, pp. 222–228. https://doi.org/10.1145/3587135.3592763 Google Scholar
[75] Cannizzaro M. and George A., “Evaluation of RISC-V Silicon Under Neutron Radiation,” 2023 Institute of Electrical and Electronics Engineers (IEEE) Aerospace Conference, IEEE, New York, 2023, pp. 1–9. https://doi.org/10.1109/AERO55745.2023.10115689 Google Scholar

Journal of Aerospace Information Systems, volume 20 issue 10 cover

Volume 20, Number 10October 2023

Metrics

Crossmark

Information

Copyright © 2023 by the American Institute of Aeronautics and Astronautics, Inc. Under the copyright claimed herein, the U.S. Government has a royalty-free license to exercise all rights for Governmental purposes. All other rights are reserved by the copyright owner. All requests for copying and permission to reprint should be submitted to CCC at www.copyright.com; employ the eISSN 2327-3097 to initiate your request. See also AIAA Rights and Permissions www.aiaa.org/randp.

Topics

Keywords

Acknowledgments

Portions of this research were carried out at the Jet Propulsion Laboratory (JPL) of the California Institute of Technology under a contract with NASA (80NM0018D0004). The JPL element of this work was sponsored by the NASA Science Mission Directorate and the JPL Foundry. Government sponsorship acknowledged.

We would like to thank Damon Russell, Joseph Sauvageau, and Douglas Sheldon for their support via the JPL Foundry Snapdragon initiative. We thank Carrie Knox for her system administration work on Hewlett Packard Enterprise’s Spaceborne Computer program. We thank Alexandra Holloway from JPL for her work with the RAD750 processor. We would also like to thank the many application providers who supported the testing of their applications, including Kiri Wagstaff, Steven Lu, Michael Denbina, Deegan Atha, Michael Swan, and Hiro Ono.

Reference herein to any specific commercial product, process, or service by trade name, trademark, manufacturer, or otherwise does not constitute or imply its endorsement by the U.S. Government or the Jet Propulsion Laboratory, California Institute of Technology.

PDF

Received4 November 2022
Accepted11 July 2023
Published online5 September 2023

Benchmarking Deep Learning Models on Myriad and Snapdragon Processors for Space Applications

Abstract

References

What's Popular

Metrics

Information