HPC Platform for Railway Safety-Critical Functionalities Based on Artificial Intelligence
Source abstract
Abstract
The automation of railroad operations is a rapidly growing industry. In 2023, a new European standard for the automated Grade of Automation (GoA) 2 over European Train Control System (ETCS) driving is anticipated. Meanwhile, railway stakeholders are already planning their research initiatives for driverless and unattended autonomous driving systems. As a result, the industry is particularly active in research regarding perception technologies based on Computer Vision (CV) and Artificial Intelligence (AI), with outstanding results at the application level. However, executing high-performance and safety-critical applications on embedded systems and in real-time is a challenge. There are not many commercially available solutions, since High-Performance Computing (HPC) platforms are typically seen as being beyond the business of safety-critical systems. This work proposes a novel safety-critical and high-performance computing platform for CV- and AI-enhanced technology execution used for automatic accurate stopping and safe passenger transfer railway functionalities. The resulting computing platform is compatible with the majority of widely-used AI inference methodologies, AI model architectures, and AI model formats thanks to its design, which enables process separation, redundant execution, and HW acceleration in a transparent manner. The proposed technology increases the portability of railway applications into embedded systems, isolates crucial operations, and effectively and securely maintains system resources.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Remote Sensing and LiDAR Applications · Hand Gesture Recognition Systems · Autonomous Vehicle Technology and Safety
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Autonomous Vehicle Department, CAF Signalling, 20018 Donostia, Spain
Computer Sciences and Artificial Intelligence Department, University of the Basque Country, 20018 Donostia, Spain
Computer Engineering Department, Universitat Politècnica de València, 46022 Valencia, Spain
Embedded Systems Department, Ikerlan Technology Research Centre, 20500 Arrasate/Mondragón, Spain
Funding
RIA
References (33)
Show source-provided references
1. (2023, May 05). Shift2Rail—Home. Available online: https://shift2rail.org/.
2. Reddi, V.J.e.a. (2019). MLPerf Inference Benchmark. arXiv.
3. (2023, May 05). CORDIS—SELENE. Available online: https://cordis.europa.eu/project/id/871467/en.
4. Waterman, A., Lee, Y., Patterson, D.A., and Asanović, K. (2014). The RISC-V Instruction Set Manual, Volume I: User-Level ISA, Version 2.0., EECS Department, University of California. Technical Report UCB/EECS-2014-54.10.21236/ADA605735 ↗
5. Palmer, A.W., Sema, A., Martens, W., Rudolph, P., and Waizenegger, W. (2020, January 20–23). The Autonomous Siemens Tram. Proceedings of the IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC), Rhodes, Greece.10.1109/ITSC45102.2020.9294699 ↗
6. Smart Tramway Systems for Smart Cities: A Deep Learning Application in ADAS Systems
7. Ristić-Durrant, D., Franke, M., and Michels, K. (2021). A Review of Vision-Based On-Board Obstacle Detection and Distance Estimation in Railways. Sensors, 21.10.3390/s21103452 ↗
8. (2023, May 05). Alstom Demonstrates Fully Autonomous Driving of a Shunting Locomotive in the Netherlands. Available online: https://www.alstom.com/press-releases-news/2022/11/alstom-demonstrates-fully-autonomous-driving-shunting-locomotive-netherlands.
9. (2023, May 05). Train Autonome Service Voyageurs: Essais Réussis. Available online: https://www.youtube.com/watch?v=vlEy7GYe684&ab_channel=GroupeSNCF.
10. (2023, May 05). Autonomous Train Tests Were Carried Out Succesfully in Finland. Available online: https://www.proxion.fi/en/autonomous-train-tests-were-carried-out-succesfully-in-finland/.
11. (2023, May 05). Railtech—DB Cargo Automates Shunting to Boost Single Wagon Load Traffic. Available online: https://www.railfreight.com/railfreight/2021/10/27/db-cargo-automates-shunting-to-boost-single-wagon-load-traffic/?gdpr=accept.
12. (2023, May 05). Cognitive Pilot—Tram Automation Software Contract Awarded in Shanghai. Available online: https://en.cognitivepilot.com/breaking-news/fitsco-tram-english/.
13. (2023, May 05). RailTech—Remote-Controlled Shunting. Available online: https://www.railtech.com/digitalisation/2020/09/25/remote-controlled-shunting-on-tests-in-switzerland/.
14. (2023, May 05). Digitale Schiene—Fourteen Eyes on the Road Ahead: Second Sensors4Rail Test Project Successful. Available online: https://digitale-schiene-deutschland.de/en/Sensors4Rail-test-project.
15. (2023, May 05). Youtube—Train Autonome: Automatisation de la Lecture de la Signalisation Latérale. Available online: https://www.youtube.com/watch?v=WiYavvqh7Bk&ab_channel=GroupeSNCF.
16. (2023, May 05). La Reconnaissance Faciale des Signaux, le Projet ARTE D’alstom. Available online: https://mediarail.wordpress.com/2022/10/23/alstom-projet-arte-basse-saxe/.
17. Multi-Core Devices for Safety-Critical Systems: A Survey
18. Mc Guire, N., and Allende, I. (July, January 29). Approaching certification of complex systems. Proceedings of the 50th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W), Valencia, Spain.
19. Bochkovskiy, A., Wang, C.Y., and Liao, H.Y.M. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv.
20. Stereo Processing by Semiglobal Matching and Mutual Information10.1109/TPAMI.2007.1166 ↗
21. Siemens (2023, May 05). JAILHOUSE. Available online: https://github.com/siemens/jailhouse.
22. Gerstinger, A., Kantz, H., and Scherrer, C. (2008). TAS Control Platform: A Platform for Safety-Critical Railway Applications. ERCIM News, 2008.
23. Cancilla, M., Canalini, L., Bolelli, F., Allegretti, S., Carrión, S., Paredes, R., Gómez, J.A., Leo, S., Piras, M.E., and Pireddu, L. (2021, January 10–15). The DeepHealth Toolkit: A Unified Framework to Boost Biomedical Applications. Proceedings of the 25th International Conference on Pattern Recognition (ICPR), Milan, Italy.10.1109/ICPR48806.2021.9411954 ↗
24. Flich, J., Medina, L., Catalán, I., Hernández, C., Bragagnolo, A., Auzanneau, F., and Briand, D. (2022, January 16–19). Efficient Inference Of Image-Based Neural Network Models In Reconfigurable Systems With Pruning And Quantization. Proceedings of the 2022 IEEE International Conference on Image Processing (ICIP), Bordeaux, France.10.1109/ICIP46576.2022.9897752 ↗
25. (2023, May 05). NOEL-V. Available online: https://www.gaisler.com/index.php/products/processors/noel-v.
26. (2023, May 05). OpenCV. Available online: https://opencv.org/.
27. (2023, May 05). Accelerating DNNs with Xilinx Alveo Accelerator Cards. Available online: https://docs.xilinx.com/v/u/en-US/wp504-accel-dnns.
28. (2023, May 05). Jetson AGX Xavier and the New Era of Autonomous Machines. Available online: https://info.nvidia.com/rs/156-OFN-742/images/Jetson_AGX_Xavier_New_Era_Autonomous_Machines.pdf.
29. Visual Odometry in Challenging Environments: An Urban Underground Railway Scenario Case10.1109/ACCESS.2022.3187209 ↗
30. Biddle, P., England, P., Peinado, M., and Willman, B. (2002, January 18). The Darknet and the Future of Content Protection. Proceedings of the ACM Workshop on Digital Rights Management, Washington, DC, USA.10.1007/10941270_23 ↗
31. (2023, May 05). QEMU—A Generic and Open Source Machine Emulator and Virtualizer. Available online: https://www.qemu.org/.
32. (2023, May 05). Ensuring Software Timing Behavior in Critical Multicore-Based Embedded Systems. Available online: https://www.embedded.com/ensuring-software-timing-behavior-in-critical-multicore-based-embedded-systems/.
33. (2023, May 05). DAVOS—A Fault Injection Toolkit for Dependability Assessment, Verification, Optimization and Selection of Hardware Desings. Available online: https://github.com/IlyaTuzov/DAVOS.