Reinforcement Learning Approach for Autonomous UAV Navigation in 3D Space
Апстракт
In the last two decades, the rapid development of unmanned aerial vehicles (UAVs) resulted in their usage for a wide range of applications. Miniaturization and cost reduction of electrical components have led to their commercialization, and today they can be utilized for various tasks in an unknown environment. Finding the optimal path based on the start and target pose information is one of the most complex demands for any intelligent UAV system. As this problem requires a high level of adaptability and learning capability of the UAV, the framework based
on reinforcement learning is proposed for the localization and navigation tasks. In this paper, Q-learning algorithm for the autonomous navigation of the UAV in 3D space is implemented. To test the proposed methodology for UAV intelligent control, the simulation is conducted in ROS-Gazebo environment. The obtained simulation results have shown that the UAV can reach the target pose autonomously in an efficient way.
Кључне речи:
Unmanned Aerial Vehicles (UAVs) / Autonomous localization and navigation / Reinforcement learning / Q-learning / Unknown environment. / Simulation / UAV in 3D space / UAV intelligent control / ROS-Gazebo environmentИзвор:
Proceedings of the 14th International Scientific Conference MMA 2021 – Flexible Technologies, Novi Sad, September 23-25, 2021, 2021, 189-192Издавач:
- Novi Sad : Faculty of Technical Sciences
Финансирање / пројекти:
- MISSION4.0 - Deep Machine Learning and Swarm Intelligence-Based Optimization Algorithms for Control and Scheduling of Cyber-Physical Systems in Industry 4.0 (RS-ScienceFundRS-AI-6523109)
- Министарство науке, технолошког развоја и иновација Републике Србије, институционално финансирање - 200105 (Универзитет у Београду, Машински факултет) (RS-MESTD-inst-2020-200105)
Колекције
Институција/група
Mašinski fakultetTY - CONF AU - Miljković, Zoran AU - Jevtić, Đorđe AU - Svorcan, Jelena PY - 2021 UR - https://machinery.mas.bg.ac.rs/handle/123456789/4625 AB - In the last two decades, the rapid development of unmanned aerial vehicles (UAVs) resulted in their usage for a wide range of applications. Miniaturization and cost reduction of electrical components have led to their commercialization, and today they can be utilized for various tasks in an unknown environment. Finding the optimal path based on the start and target pose information is one of the most complex demands for any intelligent UAV system. As this problem requires a high level of adaptability and learning capability of the UAV, the framework based on reinforcement learning is proposed for the localization and navigation tasks. In this paper, Q-learning algorithm for the autonomous navigation of the UAV in 3D space is implemented. To test the proposed methodology for UAV intelligent control, the simulation is conducted in ROS-Gazebo environment. The obtained simulation results have shown that the UAV can reach the target pose autonomously in an efficient way. PB - Novi Sad : Faculty of Technical Sciences C3 - Proceedings of the 14th International Scientific Conference MMA 2021 – Flexible Technologies, Novi Sad, September 23-25, 2021 T1 - Reinforcement Learning Approach for Autonomous UAV Navigation in 3D Space EP - 192 SP - 189 SP - UR - https://hdl.handle.net/21.15107/rcub_machinery_4625 ER -
@conference{ author = "Miljković, Zoran and Jevtić, Đorđe and Svorcan, Jelena", year = "2021", abstract = "In the last two decades, the rapid development of unmanned aerial vehicles (UAVs) resulted in their usage for a wide range of applications. Miniaturization and cost reduction of electrical components have led to their commercialization, and today they can be utilized for various tasks in an unknown environment. Finding the optimal path based on the start and target pose information is one of the most complex demands for any intelligent UAV system. As this problem requires a high level of adaptability and learning capability of the UAV, the framework based on reinforcement learning is proposed for the localization and navigation tasks. In this paper, Q-learning algorithm for the autonomous navigation of the UAV in 3D space is implemented. To test the proposed methodology for UAV intelligent control, the simulation is conducted in ROS-Gazebo environment. The obtained simulation results have shown that the UAV can reach the target pose autonomously in an efficient way.", publisher = "Novi Sad : Faculty of Technical Sciences", journal = "Proceedings of the 14th International Scientific Conference MMA 2021 – Flexible Technologies, Novi Sad, September 23-25, 2021", title = "Reinforcement Learning Approach for Autonomous UAV Navigation in 3D Space", pages = "192-189-", url = "https://hdl.handle.net/21.15107/rcub_machinery_4625" }
Miljković, Z., Jevtić, Đ.,& Svorcan, J.. (2021). Reinforcement Learning Approach for Autonomous UAV Navigation in 3D Space. in Proceedings of the 14th International Scientific Conference MMA 2021 – Flexible Technologies, Novi Sad, September 23-25, 2021 Novi Sad : Faculty of Technical Sciences., 189-192. https://hdl.handle.net/21.15107/rcub_machinery_4625
Miljković Z, Jevtić Đ, Svorcan J. Reinforcement Learning Approach for Autonomous UAV Navigation in 3D Space. in Proceedings of the 14th International Scientific Conference MMA 2021 – Flexible Technologies, Novi Sad, September 23-25, 2021. 2021;:189-192. https://hdl.handle.net/21.15107/rcub_machinery_4625 .
Miljković, Zoran, Jevtić, Đorđe, Svorcan, Jelena, "Reinforcement Learning Approach for Autonomous UAV Navigation in 3D Space" in Proceedings of the 14th International Scientific Conference MMA 2021 – Flexible Technologies, Novi Sad, September 23-25, 2021 (2021):189-192, https://hdl.handle.net/21.15107/rcub_machinery_4625 .