A compact DQN model for mobile agents with collision avoidance

• Autorzy: Kamola Mariusz

Identyfikatory

DOI

10.14313/JAMRIS/2‐2023/13

• Języki publikacji: EN

Abstrakty

EN

This paper presents a complete simulation and reinforce‐ ment learning solution to train mobile agents’ strategy of route tracking and avoiding mutual collisions. The aim was to achieve such functionality with limited resources, w.r.t. model input and model size itself. The designed models prove to keep agents safely on the track. Colli‐ sion avoidance agent’s skills developed in the course of model training are primitive but rational. Small size of the model allows fast training with limited computational resources.

Słowa kluczowe

EN

Q‐learning; DQN; reinforcement learning

• Wydawca: Łukasiewicz Industrial Research Institute for Automation and Measurements PIAP
• Czasopismo: Journal of Automation Mobile Robotics and Intelligent Systems
• Rocznik: 2023
• Tom: Vol. 17, No. 2
• Strony: 28--35
• Opis fizyczny: Bibliogr. 14 poz., rys.

Twórcy

autor

Kamola Mariusz

• Institute of Control and Computation Engineering, Warsaw University of Technology, Warsaw, 00‐665, Poland
• NASK – National Research Institute, Warsaw, 01‐045, Poland

• https://orcid.org/0000-0003-1550-5901

Bibliografia

• [1] E. Strubell, Ananya Ganesh, and Andrew McCallum. “Energy and Policy Considerations for Deep Learning in NLP,” Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019. doi: 10.48550/arXiv.1906.02243.
• [2] Y. Cheng, et al. “Model compression and acceleration for deep neural networks: The principles, progress, and challenges.” IEEE Signal Processing Magazine vol. 35, no. 1, 126–136, 2018. doi: 10.48550/arXiv.1710.09282.
• [3] S. Grigorescu, et al. “A survey of deep learning techniques for autonomous driving,” Journal of Field Robotics, vol. 37, no. 3, 362–386, 2020.
• [4] M. Hessel, et al. “Rainbow: Combining improvements in deep reinforcement learning,”Proceedings of the AAAI conference on artificial intelligence, vol. 32, no. 1, 2018.
• [5] W. Dabney, et al. “Distributional reinforcement learning with quantile regression,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32, no. 1, 2018.
• [6] M. Ahmed, C. P. Lim, and S. Nahavandi. “A Deep Q‐Network Reinforcement Learning‐Based Model for Autonomous Driving,” 2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC), IEEE, 2021.
• [7] J. Carreira, and A. Zisserman. “Quo vadis, action recognition? a new model and the kinetics dataset,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017. doi: 10.48550/arXiv.1705.07750.
• [8] “How do self‐driving cars know their way around without a map?”, https://bigthink.com/technology‐innovation/how‐do‐self‐driving‐cars‐know‐ their‐ way‐ around‐ without‐ a‐map/(accessed 2023.03.31).
• [9] M. Sewak. “Deep Q Network (DQN), Double DQN, and Dueling DQN: A Step Towards General Artificial Intelligence,” Deep Reinforcement Learning: Frontiers of ArtiFicial Intelligence 2019, 95–108. doi: 10.1007/978‐981‐13‐8285‐7_8.
• [10] W. Dudek, N. Miguel, and T. Winiarski. “SPSysML: A meta‐model for quantitative evaluation of Simulation‐Physical Systems,” arXiv preprint arXiv:2303.09565 (2023). doi: 10.48550/arXiv.2303.09565.
• [11] F. S. Chance. “Interception from a DragonFly Neural Network Model,” International Conference on Neuromorphic Systems, 2020.
• [12] “Self‐driving cars with Carla and Python,” https://pythonprogramming.net/introduction‐self‐driving‐autonomous‐cars‐carla‐python (accessed 2023.03.31).
• [13] OpenAI Gym homepage, https://openai.com/research/openai‐gym‐beta (accessed 2023.03.31).
• [14] J. Lin, C. Gan, and S. Han. “TSM: Temporal shift module for efficient video understanding.” Proceedings of the IEEE/CVF international conference on computer vision, 2019.

Uwagi

Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024).