Enhancing navigation of autonomous mobile robots through permanent federated learning

Бесплатный доступ

Deep learning is crucial for advancing artificial intelligence in robotics. Deep learning enables autonomous robots to perceive and control their environment. Federated learning allows distributed robots to train models while maintaining privacy. This paper focuses on using FL to overcome vision-based obstacles in mobile robotic navigation. We evaluate FL’s performance in both simulated and real-world environments. Our research compares FL’s multiple image classifiers to cloud-based central learning using existing data. We also implement a continuous learning system on mobile bots with autonomous data generation. Training models in simulation and reality improves accuracy and enables continuous model updates.


Federated learning, robot navigation, continuous learning, obstacle avoidance, efficientnet, lifelong learning, privacy

Короткий адрес: https://sciup.org/148327118

IDR: 148327118   |   DOI: 10.18137/RNU.V9187.23.03.P.119

Список литературы Enhancing navigation of autonomous mobile robots through permanent federated learning

  • Mateus Mendes, AP Coimbray, and MM Crisostomoy (2018) Assis-cicerone robot with visual obstacle avoidance using a stack of odometric data. IA ENG Int. J. Comput. Sci, 45:219–227.
  • Harry A Pierson and Michael S Gashler (2017) Deep learning in robotics: a review of recent research. Advanced Robotics, 31(16):821–835.
  • Wenshuai Zhao, Jorge Pena Queralta, and TomiWesterlund (2020) Sim-to-real ˜ transfer in deep reinforcement learning for robotics: a survey. In IEEE Symposium Series on Computational Intelligence. IEEE, 2020.
  • Boyi Liu, Lujia Wang, Xinquan Chen, Lexiong Huang, Dong Han, and Cheng-Zhong Xu (2021) Peerassisted robotic learning: a data-driven collaborative learning approach for cloud robotic systems. In 2021 IEEE International Conference on Robotics and Automation (ICRA ), pp. 4062–4070. IEEE, 2021.
  • Ying Li, Lingfei Ma, ZilongZhong, Fei Liu, Michael A Chapman, Dongpu Cao, and Jonathan Li (2020) Deep learning for lidar point clouds in autonomous driving: A review. IEEE Transactions on Neural Networks and Learning Systems, 32(8):3412–3432.
  • Lingping Gao, Jianchuan Ding, Wenxi Liu, HaiyinPiao, Yuxin Wang, Xin Yang, and Baocai Yin (2021) A vision-based irregular obstacle avoidance framework via deep reinforcement learning. In IEEE/RSJ International Conference on Intelligent Robots and Systems, 2021.
  • Xianjia Yu, Jorge Pena Queralta, and TomiWesterlund (2022) Federated learning for vision-based obstacle avoidance in the internet of robotic things. arXiv preprint arXiv:2204.06949.
  • Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. (2021) Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 25:1097–1105.
  • Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun (2016) Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, 2016.
  • Abhik Singla, Sindhu Padakandla, and Shalabh Bhatnagar (2021) Memorybased deep reinforcement learning for obstacle avoidance in uav with limited environment knowledge. IEEE Transactions on Intelligent Transportation Systems, 22(1):107–118.
  • Bo Liu, Xuesu Xiao, and Peter Stone (2021) A lifelong learning approach to mobile robot navigation. IEEE Robotics and Automation Letters, 6(2):1090–1096.
  • Ahmed Imteaj, UrmishThakker, Shiqiang Wang, Jian Li, and M HadiAmini (2021) A survey on federated learning for resource-constrained iot devices. IEEE Internet of Things Journal, 9(1):1–24.
  • Hamidreza Kasaei S., Jorik Melsen, Floris van Beers, Christiaan Steenkist, and Klemen Voncina (2021) The state of lifelong learning in service robots. Journal of Intelligent & Robotic Systems, 103(1):1–31.
Статья научная