CoFED-DLAD 2020

Workshop at ITSC 2020

20 September, 2020 at Rhodes, Greece

Federated Machine Learning Framework

Previous Editions:

2nd Workshop on 3D Deep Learning for Autonomous Driving IV 2020 Las Vegas, United States (3D-DLAD-V2)

Beyond-Perception : Deep learning for Autonomous Driving ITSC 2019 Auckland NewZealand (BP-DLAD),

3D Deep Learning for Autonomous Driving IV 2019 Paris, France (3D-DLAD)

Deep learning for autonomous driving, ITSC 2017 Yokohama, Japan (DLAD)

Collaborative Perception & Federated ML for Autonomous Driving

Deep learning (DL) has shown improvements in object detection, semantic segmentation, HD-Maps creation, representations for odometry, localization, automated sensor calibration, learning driving policy. Federated ML/DL is a recent development to train user specific keyboard models in a decentralized way across different mobile systems by Google. Recent workshop on Federated AI for Robotics has demonstrated a first effort to cross-fertilize domains in robotics and federated ML models. We aim to unite researchers from 1. Federated DL & ML algorithms, 2. Autonomous driving tasks. Decentralized aggregate learning on autonomous driving agents could be helpful in collaborative mapping and localization, obstacle avoidance, would become more and more prominent due to the upcoming technologies such as 5G. This also requires power efficient networks but are regularly learning from new observations.

Call for Papers:

With this workshop we are soliciting contributions in the following (but not limited to) topics :

  • Collaborative perception among Connected Vehicles & Vehicle Platooning
  • Vehicle to vehicle and Vehicle to infrastructure Communication
  • Federated ML for learning to update DNN models in vehicle fleets for object detection, semantic segmentation, Map Creation, Localization
  • Federated Filtering, Distributed Kalman Filtering, Federated Fusion
  • Co-training and self-training over mixture of labelled and unlabeled data
  • Active learning within federated ML frameworks
  • Dataset compression and distillation for Federated ML.
  • Network optimization for Federated ML
  • Collaborative Mapping and SLAM using multi-agent systems.
  • Shared Prior map updates and re-localization.
  • Multi-agent reinforcement learning (MARL) for Autonomous Driving
  • Multi-agent driving policy for decision making at intersections, merges.

The goal of this workshop would be to assemble researchers and practitioners from academic institutions as well industry.

References

  1. "Federated learning: private distributed ML" by Mike Lee Williams [Talk]
  2. Federated Learning in the real world, 'Systems for AI Track' AI Week Yuval Ne'eman Workshop for Science, Technology and Security Tel Aviv University [Talk]
  3. Training AI for Self-Driving Vehicles: the Challenge of Scale, By Adam Grzywaczewski | NVIDIA 2017 [link]
  4. Kairouz, Peter, H. Brendan McMahan, Brendan Avent, Aurélien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Keith Bonawitz et al. "Advances and open problems in federated learning." arXiv preprint arXiv:1912.04977 (2019). [link]
  5. Moratuwage, Diluka, Ba-Ngu Vo, and Danwei Wang. "Collaborative multi-vehicle SLAM with moving object tracking." 2013 IEEE International Conference on Robotics and Automation. IEEE, 2013. [link]
  6. Golodetz, Stuart, et al. "Collaborative large-scale dense 3D reconstruction with online inter-agent pose optimisation." IEEE transactions on visualization and computer graphics 24.11 (2018): 2895-2905. [link]
  7. Dubé, Renaud, et al. "An online multi-robot slam system for 3d lidars." 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2017. [link]
  8. Dubé, Renaud, et al. "SegMap: Segment-based mapping and localization using data-driven descriptors." The International Journal of Robotics Research (2019): 0278364919863090. [link]
  9. Dasari, Sudeep, Frederik Ebert, Stephen Tian, Suraj Nair, Bernadette Bucher, Karl Schmeckpeper, Siddharth Singh, Sergey Levine, and Chelsea Finn. "RoboNet: Large-Scale Multi-Robot Learning." arXiv preprint arXiv:1910.11215 (2019). [pdf]
  10. Boyi Liu, Lujia Wang, Ming Liu, Chengzhong Xu, Lifelong Federated Reinforcement Learning: A Learning Architecture for Navigation in Cloud Robotic Systems, IEEE Robotics and Automation Letters (RA-L), 2019, accepted [link]
  11. Peng, Xingchao, et al. "Federated Adversarial Domain Adaptation." arXiv preprint arXiv:1911.02054 (2019) ICLR 2020.
  12. Philippe, C., Adouane, L., Tsourdos, A., Shin, H. S., & Thuilot, B. (2019, June). Probability Collectives Algorithm applied to Decentralized Intersection Coordination for Connected Autonomous Vehicles. In 2019 IEEE Intelligent Vehicles Symposium (IV) (pp. 1928-1934). IEEE.
  13. Everett, Michael, Yu Fan Chen, and Jonathan P. How. "Motion planning among dynamic, decision-making agents with deep reinforcement learning." 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2018. [pdf]
  14. Dosovitskiy, Alexey, et al. "CARLA: An Open Urban Driving Simulator." Conference on Robot Learning. 2017. [link]
  15. Federated Machine Learning for AI Self-Driving Cars [link]
  16. Hoang, Minh, et al. "Collective Model Fusion for Multiple Black-Box Experts." International Conference on Machine Learning. 2019. [link]
  17. Govaers, Felix, and Wolfgang Koch. "Distributed Kalman filter fusion at arbitrary instants of time." 2010 13th International Conference on Information Fusion. IEEE, 2010. [link]
  18. Noack, B., Julier, S. J., Reinhardt, M., & Hanebeck, U. D. (2013, July). Nonlinear federated filtering. In Proceedings of the 16th International Conference on Information Fusion (pp. 350-356). IEEE. [link]
  19. Xu, S., Zhou, H., Wang, J., He, Z., & Wang, D. (2019). SINS/CNS/GNSS Integrated Navigation Based on an Improved Federated Sage–Husa Adaptive Filter. Sensors, 19(17), 3812. [link]
  20. Macheng Shen, Jing Sun, Huei Peng, Ding Zhao, ''Improving Localization Accuracy in Connected Vehicle Networks Using Rao-Blackwellized Particle Filters: Theory, Simulations, and Experiments,'' IEEE Transactions on Intelligent Transportation Systems, Jun. 2019. [link]
  21. Wenhao Ding, Wenshuo Wang, Ding Zhao, ''Multi-Vehicle Trajectories Generation for Vehicle-to-Vehicle Encounters,'' Proceedings of 2019 IEEE International Conference on Robotics and Automation (ICRA), Montreal, Canada, May 20-24, 2019. [link]
  22. McMahan, Brendan, et al. "Communication-Efficient Learning of Deep Networks from Decentralized Data." Artificial Intelligence and Statistics. 2017. [link]
  23. Samarakoon, Sumudu, Mehdi Bennis, Walid Saady, and Merouane Debbah. "Distributed Federated Learning for Ultra-Reliable Low-Latency Vehicular Communications." arXiv preprint arXiv:1807.08127 (2018). [link]
  24. Kamp, Michael, et al. "Efficient decentralized deep learning by dynamic model averaging." Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, Cham, 2018.
  25. Bonawitz, Keith, et al. "Towards federated learning at scale: System design." arXiv preprint arXiv:1902.01046 (2019). [link]
  26. Zhang, Hao, et al. "Poseidon: An efficient communication architecture for distributed deep learning on {GPU} clusters." 2017 {USENIX} Annual Technical Conference ({USENIX}{ATC} 17). 2017. [link]
  27. Smith, Virginia, et al. "Federated multi-task learning." Advances in Neural Information Processing Systems. 2017. [link]
  28. TensorFlow Federated: Machine Learning on Decentralized Data [Tensorflow Federated API]
  29. Blum, Avrim, and Tom Mitchell. "Combining labeled and unlabeled data with co-training." Proceedings of the eleventh annual conference on Computational learning theory. ACM, 1998. [link]
  30. Qiao, Siyuan, et al. "Deep co-training for semi-supervised image recognition." Proceedings of the European Conference on Computer Vision (ECCV). 2018. [link
  31. Teichman, Alex, and Sebastian Thrun. "Tracking-based semi-supervised learning." The International Journal of Robotics Research 31.7 (2012): 804-818. [link]
  32. Rosenberg, Chuck, Martial Hebert, and Henry Schneiderman. "Semi-Supervised Self-Training of Object Detection Models." WACV/MOTION 2 (2005). [link]
  33. Reed, Scott, et al. "Training deep neural networks on noisy labels with bootstrapping." arXiv preprint arXiv:1412.6596 (2014). [link]