Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
134 tokens/sec
GPT-4o
10 tokens/sec
Gemini 2.5 Pro Pro
47 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Communication Resources Constrained Hierarchical Federated Learning for End-to-End Autonomous Driving (2306.16169v1)

Published 28 Jun 2023 in cs.RO, cs.DC, and cs.LG

Abstract: While federated learning (FL) improves the generalization of end-to-end autonomous driving by model aggregation, the conventional single-hop FL (SFL) suffers from slow convergence rate due to long-range communications among vehicles and cloud server. Hierarchical federated learning (HFL) overcomes such drawbacks via introduction of mid-point edge servers. However, the orchestration between constrained communication resources and HFL performance becomes an urgent problem. This paper proposes an optimization-based Communication Resource Constrained Hierarchical Federated Learning (CRCHFL) framework to minimize the generalization error of the autonomous driving model using hybrid data and model aggregation. The effectiveness of the proposed CRCHFL is evaluated in the Car Learning to Act (CARLA) simulation platform. Results show that the proposed CRCHFL both accelerates the convergence rate and enhances the generalization of federated learning autonomous driving model. Moreover, under the same communication resource budget, it outperforms the HFL by 10.33% and the SFL by 12.44%.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (33)
  1. L. Zhang, X. Lei, Y. Shi, H. Huang, and C. Chen, “Federated learning with domain generalization,” CoRR, vol. abs/2111.10487, 2021. [Online]. Available: https://arxiv.org/abs/2111.10487
  2. X. Liang, Y. Liu, T. Chen, M. Liu, and Q. Yang, “Federated transfer reinforcement learning for autonomous driving,” CoRR, vol. abs/1910.06001, 2019. [Online]. Available: http://arxiv.org/abs/1910.06001
  3. B. Liu, L. Wang, M. Liu, and C. Xu, “Lifelong federated reinforcement learning: A learning architecture for navigation in cloud robotic systems,” CoRR, vol. abs/1901.06455, 2019. [Online]. Available: http://arxiv.org/abs/1901.06455
  4. B. Yang, H. Shi, and X. Xia, “Federated imitation learning for uav swarm coordination in urban traffic monitoring,” IEEE Transactions on Industrial Informatics, pp. 1–10, 2022.
  5. S. Wang, C. Li, Q. Hao, C. Xu, D. W. K. Ng, Y. C. Eldar, and H. V. Poor, “Federated deep learning meets autonomous vehicle perception: Design and verification,” 2022. [Online]. Available: https://arxiv.org/abs/2206.01748
  6. Z. Zhang, S. Wang, Y. Hong, L. Zhou, and Q. Hao, “Distributed dynamic map fusion via federated learning for intelligent networked vehicles,” CoRR, vol. abs/2103.03786, 2021. [Online]. Available: https://arxiv.org/abs/2103.03786
  7. H. Zhang, J. Bosch, and H. H. Olsson, “Real-time end-to-end federated learning: An automotive case study,” CoRR, vol. abs/2103.11879, 2021. [Online]. Available: https://arxiv.org/abs/2103.11879
  8. A. Nguyen, T. Do, M. Tran, B. X. Nguyen, C. Duong, T. Phan, E. Tjiputra, and Q. D. Tran, “Deep federated learning for autonomous driving,” CoRR, vol. abs/2110.05754, 2021. [Online]. Available: https://arxiv.org/abs/2110.05754
  9. B. Liu, L. Wang, X. Chen, L. Huang, and C. Xu, “Peer-assisted robotic learning: A data-driven collaborative learning approach for cloud robotic systems,” CoRR, vol. abs/2010.08303, 2020. [Online]. Available: https://arxiv.org/abs/2010.08303
  10. S. Savazzi, M. Nicoli, M. Bennis, S. Kianoush, and L. Barbieri, “Opportunities of federated learning in connected, cooperative, and automated industrial systems,” IEEE Communications Magazine, vol. 59, pp. 16–21, 2021.
  11. Z. Zhao, Y. Mao, Y. Liu, L. Song, Y. Ouyang, X. Chen, and W. Ding, “Towards efficient communications in federated learning: A contemporary survey,” 2022. [Online]. Available: https://arxiv.org/abs/2208.01200
  12. R. M. Gray and D. L. Neuhoff, “Quantization,” IEEE Trans. Inf. Theory, vol. 44, pp. 2325–2383, 2022.
  13. N. F. Eghlidi and M. Jaggi, “Sparse communication for training deep networks,” CoRR, vol. abs/2009.09271, 2020. [Online]. Available: https://arxiv.org/abs/2009.09271
  14. G. Hinton, O. Vinyals, and J. Dean, “Distilling the knowledge in a neural network,” 2015. [Online]. Available: https://arxiv.org/abs/1503.02531
  15. S. Salehkalaibar and S. Rini, “Lossy gradient compression: How much accuracy can one bit buy?” CoRR, vol. abs/2202.02812, 2022. [Online]. Available: https://arxiv.org/abs/2202.02812
  16. A. Dosovitskiy, G. Ros, F. Codevilla, A. Lopez, and V. Koltun, “Carla: An open urban driving simulator,” in Proceedings of The 1st Annual Conference on Robot Learning, Mountain View, CA, Oct. 2017, pp. 1–16.
  17. Z. Sun, Z. Huang, Q. Zhu, X. Li, and D. Liu, “High-precision motion control method and practice for autonomous driving in complex off-road environments,” in 2016 IEEE Intelligent Vehicles Symposium (IV), 2016, pp. 767–773.
  18. Y. Jiang, H. Yedidsion, S. Zhang, G. Sharon, and P. Stone, “Multi-robot planning with conflicts and synergies,” Autonomous Robots, vol. 43, no. 8, pp. 2011–2032, 2019.
  19. M. Kelly, C. Sidrane, K. R. Driggs-Campbell, and M. J. Kochenderfer, “Hg-dagger: Interactive imitation learning with human experts,” CoRR, vol. abs/1810.02890, 2018. [Online]. Available: http://arxiv.org/abs/1810.02890
  20. S. Rosbach, V. James, S. Großjohann, S. Homoceanu, and S. Roth, “Driving with style: Inverse reinforcement learning in general-purpose planning for automated driving,” CoRR, vol. abs/1905.00229, 2019. [Online]. Available: http://arxiv.org/abs/1905.00229
  21. Y. Pan, C.-A. Cheng, K. Saigol, K. Lee, X. Yan, E. A. Theodorou, and B. Boots, “Imitation learning for agile autonomous driving,” The International Journal of Robotics Research, vol. 39, no. 2-3, pp. 286–302, 2020. [Online]. Available: https://doi.org/10.1177/0278364919880273
  22. B. Liu, L. Wang, M. Liu, and C.-Z. Xu, “Federated imitation learning: A novel framework for cloud robotic systems with heterogeneous sensor data,” IEEE Robotics and Automation Letters, vol. 5, no. 2, pp. 3509–3516, 2020.
  23. Y. Xiao, F. Codevilla, A. Gurram, O. Urfalioglu, and A. M. López, “Multimodal end-to-end autonomous driving,” IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 1, pp. 537–547, 2022.
  24. J. Yuan, M. Xu, X. Ma, A. Zhou, X. Liu, and S. Wang, “Hierarchical federated learning through LAN-WAN orchestration,” CoRR, vol. abs/2010.11612, 2020. [Online]. Available: https://arxiv.org/abs/2010.11612
  25. D. Alistarh, J. Li, R. Tomioka, and M. Vojnovic, “QSGD: randomized quantization for communication-optimal stochastic gradient descent,” CoRR, vol. abs/1610.02132, 2016. [Online]. Available: http://arxiv.org/abs/1610.02132
  26. A. N. Sahu, A. Dutta, A. M. Abdelmoniem, T. Banerjee, M. Canini, and P. Kalnis, “Rethinking gradient sparsification as total error minimization,” CoRR, vol. abs/2108.00951, 2021. [Online]. Available: https://arxiv.org/abs/2108.00951
  27. D. Li and J. Wang, “Fedmd: Heterogenous federated learning via model distillation,” CoRR, vol. abs/1910.03581, 2019. [Online]. Available: http://arxiv.org/abs/1910.03581
  28. H. B. McMahan, E. Moore, D. Ramage, and B. A. y Arcas, “Federated learning of deep networks using model averaging,” CoRR, vol. abs/1602.05629, 2016. [Online]. Available: http://arxiv.org/abs/1602.05629
  29. M. Chen, Z. Yang, W. Saad, C. Yin, H. V. Poor, and S. Cui, “A joint learning and communications framework for federated learning over wireless networks,” IEEE Transactions on Wireless Communications, vol. 20, pp. 269–283, 2021.
  30. H. SEUNG, H. SOMPOLINSKY, and N. TISHBY, “Statistical-mechanics of learning from examples,” Physical review. A, Atomic, molecular, and optical physics, vol. 45, no. 8, pp. 6056–6091, 1992.
  31. S. Diamond and S. Boyd, “CVXPY: A Python-embedded modeling language for convex optimization,” Journal of Machine Learning Research, vol. 17, no. 83, pp. 1–5, 2016.
  32. M. Bojarski, D. D. Testa, D. Dworakowski, B. Firner, B. Flepp, P. Goyal, L. D. Jackel, M. Monfort, U. Muller, J. Zhang, X. Zhang, J. Zhao, and K. Zieba, “End to end learning for self-driving cars,” CoRR, vol. abs/1604.07316, 2016. [Online]. Available: http://arxiv.org/abs/1604.07316
  33. J. Tursunboev, Y.-S. Kang, S.-B. Huh, D.-W. Lim, J.-M. Kang, and H. Jung, “Hierarchical federated learning for edge-aided unmanned aerial vehicle networks,” Applied Sciences, vol. 12, no. 2, 2022. [Online]. Available: https://www.mdpi.com/2076-3417/12/2/670
Citations (9)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Github Logo Streamline Icon: https://streamlinehq.com

GitHub

  1. GitHub - WeibinKOU/CRCHFL (3 stars)
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets