Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
102 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Savvy: Trustworthy Autonomous Vehicles Architecture (2402.14580v1)

Published 8 Feb 2024 in cs.AI, cs.SY, and eess.SY

Abstract: The increasing interest in Autonomous Vehicles (AV) is notable due to business, safety, and performance reasons. While there is salient success in recent AV architectures, hinging on the advancements in AI models, there is a growing number of fatal incidents that impedes full AVs from going mainstream. This calls for the need to revisit the fundamentals of building safety-critical AV architectures. However, this direction should not deter leveraging the power of AI. To this end, we propose Savvy, a new trustworthy intelligent AV architecture that achieves the best of both worlds. Savvy makes a clear separation between the control plane and the data plane to guarantee the safety-first principles. The former assume control to ensure safety using design-time defined rules, while launching the latter for optimizing decisions as much as possible within safety time-bounds. This is achieved through guided Time-aware predictive quality degradation (TPQD): using dynamic ML models that can be tuned to provide either richer or faster outputs based on the available safety time bounds. For instance, Savvy allows to safely identify an elephant as an obstacle (a mere object) the earliest possible, rather than optimally recognizing it as an elephant when it is too late. This position paper presents the Savvy's motivations and concept, whereas empirical evaluation is a work in progress.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (54)
  1. M. Abdar, F. Pourpanah, S. Hussain, D. Rezazadegan, L. Liu, M. Ghavamzadeh, P. Fieguth, X. Cao, A. Khosravi, U. R. Acharya et al., “A review of uncertainty quantification in deep learning: Techniques, applications and challenges,” Information Fusion, vol. 76, pp. 243–297, 2021.
  2. V. Badrinarayanan, A. Kendall, and R. Cipolla, “Segnet: A deep convolutional encoder-decoder architecture for image segmentation,” IEEE transactions on pattern analysis and machine intelligence, vol. 39, no. 12, pp. 2481–2495, 2017.
  3. S. Bak, T. T. Johnson, M. Caccamo, and L. Sha, “Real-time reachability for verified simplex design,” in 2014 IEEE Real-Time Systems Symposium, 2014, pp. 138–148.
  4. S. Cai, Y. Shu, and W. Wang, “Dynamic routing networks,” in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2021, pp. 3588–3597.
  5. A. Casimiro, J. Kaiser, E. M. Schiller, P. Costa, J. Parizi, R. Johansson, and R. Librino, “The karyon project: Predictable and safe coordination in cooperative vehicular systems,” in 2013 43rd Annual IEEE/IFIP Conference on Dependable Systems and Networks Workshop (DSN-W).   IEEE, 2013, pp. 1–12.
  6. Y. Chen, X. Dai, M. Liu, D. Chen, L. Yuan, and Z. Liu, “Dynamic convolution: Attention over convolution kernels,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 11 030–11 039.
  7. CLEPA, “Safety first for automated driving,” European Association of Automotive Suppliers, 2019.
  8. L. De Raedt, S. Dumančić, R. Manhaeve, and G. Marra, “From statistical relational to neuro-symbolic artificial intelligence,” arXiv preprint arXiv:2003.08316, 2020.
  9. S. Deevy, “Sentinel: A software architecture for safe artificial intelligence in autonomous vehicles,” Ph.D. dissertation, 2019.
  10. A. Desai, S. Ghosh, S. A. Seshia, N. Shankar, and A. Tiwari, “Soter: a runtime assurance framework for programming safe robotics systems,” in 2019 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN).   IEEE, 2019, pp. 138–150.
  11. K. P. Divakarla, A. Emadi, and S. Razavi, “A cognitive advanced driver assistance systems architecture for autonomous-capable electrified vehicles,” IEEE Transactions on Transportation Electrification, vol. 5, no. 1, pp. 48–58, 2019.
  12. M. R. Endsley, “Autonomous driving systems: A preliminary naturalistic study of the tesla model s,” Journal of Cognitive Engineering and Decision Making, vol. 11, no. 3, pp. 225–238, 2017.
  13. J. Ferlez, M. Elnaggar, Y. Shoukry, and C. Fleming, “Shieldnn: A provably safe nn filter for unsafe nn controllers,” arXiv preprint arXiv:2006.09564, 2020.
  14. I. I. for Highway Safety (IIHS), “Driver death rates by make and model,” 2023, last accessed 6 July 2023. [Online]. Available: https://www.iihs.org/ratings/driver-death-rates-by-make-and-model
  15. L. Fridman, L. Ding, B. Jenik, and B. Reimer, “Arguing machines: Human supervision of black box ai systems that make life-critical decisions,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019, pp. 0–0.
  16. A. d. Garcez and L. C. Lamb, “Neurosymbolic ai: The 3 rd wave,” Artificial Intelligence Review, pp. 1–20, 2023.
  17. S. Grigorescu, B. Trasnea, T. Cocias, and G. Macesanu, “A survey of deep learning techniques for autonomous driving,” Journal of Field Robotics, vol. 37, no. 3, pp. 362–386, 2020.
  18. M.-H. Guo, T.-X. Xu, J.-J. Liu, Z.-N. Liu, P.-T. Jiang, T.-J. Mu, S.-H. Zhang, R. R. Martin, M.-M. Cheng, and S.-M. Hu, “Attention mechanisms in computer vision: A survey,” Computational Visual Media, vol. 8, no. 3, pp. 331–368, 2022.
  19. S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural computation, vol. 9, no. 8, pp. 1735–1780, 1997.
  20. G. Huang, D. Chen, T. Li, F. Wu, L. Van Der Maaten, and K. Q. Weinberger, “Multi-scale dense networks for resource efficient image classification,” arXiv preprint arXiv:1703.09844, 2017.
  21. B. Huval, T. Wang, S. Tandon, J. Kiske, W. Song, J. Pazhayampallil, M. Andriluka, P. Rajpurkar, T. Migimatsu, R. Cheng-Yue et al., “An empirical evaluation of deep learning on highway driving,” arXiv preprint arXiv:1504.01716, 2015.
  22. Incidentdatabase.ai, “Incident 293,” 2022, last accessed Dec 2023. [Online]. Available: {https://incidentdatabase.ai/cite/293/}
  23. A. D. Jagtap, E. Kharazmi, and G. E. Karniadakis, “Conservative physics-informed neural networks on discrete domains for conservation laws: Applications to forward and inverse problems,” Computer Methods in Applied Mechanics and Engineering, vol. 365, p. 113028, 2020.
  24. G. E. Karniadakis, I. G. Kevrekidis, L. Lu, P. Perdikaris, S. Wang, and L. Yang, “Physics-informed machine learning,” Nature Reviews Physics, vol. 3, no. 6, pp. 422–440, 2021.
  25. E. Kharazmi, Z. Zhang, and G. E. Karniadakis, “hp-vpinns: Variational physics-informed neural networks with domain decomposition,” Computer Methods in Applied Mechanics and Engineering, vol. 374, p. 113547, 2021.
  26. Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” nature, vol. 521, no. 7553, pp. 436–444, 2015.
  27. C. Li, G. Wang, B. Wang, X. Liang, Z. Li, and X. Chang, “Dynamic slimmable network,” in Proceedings of the IEEE/CVF Conference on computer vision and pattern recognition, 2021, pp. 8607–8617.
  28. M. Li and L. Eckstein, “Fail-operational steer-by-wire system for autonomous vehicles,” in 2019 IEEE International Conference on Vehicular Electronics and Safety (ICVES), 2019, pp. 1–6.
  29. J. Lin, Y. Rao, J. Lu, and J. Zhou, “Runtime neural pruning,” Advances in neural information processing systems, vol. 30, 2017.
  30. J. C. Linares, A. Barrientos, and E. M. Márquez, “Hybrid bio-inspired architecture for walking robots through central pattern generators using open source fpgas,” in 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).   IEEE, 2018, pp. 7071–7076.
  31. X. Meng, Z. Li, D. Zhang, and G. E. Karniadakis, “Ppinn: Parareal physics-informed neural network for time-dependent pdes,” Computer Methods in Applied Mechanics and Engineering, vol. 370, p. 113250, 2020.
  32. V. Mnih, N. Heess, A. Graves et al., “Recurrent models of visual attention,” Advances in neural information processing systems, vol. 27, 2014.
  33. B. Moseley, A. Markham, and T. Nissen-Meyer, “Finite basis physics-informed neural networks (fbpinns): a scalable domain decomposition approach for solving differential equations,” arXiv preprint arXiv:2107.07871, 2021.
  34. N. T. S. B. (NTSB), “Accident Report NTSB/HAR-19/03,” 2019, last accessed Dec 2023. [Online]. Available: {https://www.ntsb.gov/investigations/accidentreports/reports/har1903.pdf}
  35. P. Pinheiro and R. Collobert, “Recurrent convolutional neural networks for scene labeling,” in International conference on machine learning.   PMLR, 2014, pp. 82–90.
  36. A. E. Sallab, M. Abdou, E. Perot, and S. Yogamani, “Deep reinforcement learning framework for autonomous driving,” arXiv preprint arXiv:1704.02532, 2017.
  37. E. Schwalb, “Analysis of safety of the intended use (sotif),” 2019.
  38. L. Sha et al., “Using simplicity to control complexity.”
  39. S. A. Shah, “Safe-av: A fault tolerant safety architecture for autonomous vehicles,” Ph.D. dissertation, 2019.
  40. S. Shalev-Shwartz, S. Shammah, and A. Shashua, “On a formal model of safe and scalable self-driving cars,” arXiv preprint arXiv:1708.06374, 2017.
  41. R. S. Sutton, “Learning to predict by the methods of temporal differences,” Machine learning, vol. 3, pp. 9–44, 1988.
  42. S. Teerapittayanon, B. McDanel, and H.-T. Kung, “Branchynet: Fast inference via early exiting from deep neural networks,” in 2016 23rd International Conference on Pattern Recognition (ICPR).   IEEE, 2016, pp. 2464–2469.
  43. Tesladeaths.com, “Tesla deaths,” 2023, last accessed 6 July 2023. [Online]. Available: https://www.tesladeaths.com/
  44. M. Törngren, X. Zhang, N. Mohan, M. Becker, L. Svensson, X. Tao, D.-J. Chen, and J. Westman, “Architecting safety supervisors for high levels of automated driving,” in 2018 21st International Conference on Intelligent Transportation Systems (ITSC), 2018, pp. 1721–1728.
  45. W. Wang and J. Shen, “Deep visual attention prediction,” IEEE Transactions on Image Processing, vol. 27, no. 5, pp. 2368–2378, 2017.
  46. X. Wang, F. Yu, Z.-Y. Dou, T. Darrell, and J. E. Gonzalez, “Skipnet: Learning dynamic routing in convolutional networks,” in Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 409–424.
  47. N. Webb, D. Smith, C. Ludwick, T. Victor, Q. Hommes, F. Favaro, G. Ivanov, and T. Daniel, “Waymo’s safety methodologies and safety readiness determinations,” arXiv preprint arXiv:2011.00054, 2020.
  48. S. Woo, J. Park, J.-Y. Lee, and I. S. Kweon, “Cbam: Convolutional block attention module,” in Proceedings of the European conference on computer vision (ECCV), 2018, pp. 3–19.
  49. E. Workgroup, “Standardized e-gas monitoring concept for gasoline and diesel engine control units,” Version, vol. 5, p. 38, 2013.
  50. K. Xu, J. Ba, R. Kiros, K. Cho, A. Courville, R. Salakhudinov, R. Zemel, and Y. Bengio, “Show, attend and tell: Neural image caption generation with visual attention,” in International conference on machine learning.   PMLR, 2015, pp. 2048–2057.
  51. Y. Yang and P. Perdikaris, “Adversarial uncertainty quantification in physics-informed neural networks,” Journal of Computational Physics, vol. 394, pp. 136–152, 2019.
  52. J. Yu, P. Jin, H. Liu, G. Bender, P.-J. Kindermans, M. Tan, T. Huang, X. Song, R. Pang, and Q. Le, “Bignas: Scaling up neural architecture search with big single-stage models,” in Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part VII 16.   Springer, 2020, pp. 702–717.
  53. Y. Zhu, N. Zabaras, P.-S. Koutsourelakis, and P. Perdikaris, “Physics-constrained deep learning for high-dimensional surrogate modeling and uncertainty quantification without labeled data,” Journal of Computational Physics, vol. 394, pp. 56–81, 2019.
  54. B. Zoph and Q. V. Le, “Neural architecture search with reinforcement learning,” arXiv preprint arXiv:1611.01578, 2016.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Ali Shoker (14 papers)
  2. Rehana Yasmin (3 papers)
  3. Paulo Esteves-Verissimo (21 papers)