This paper proposes an improved deep reinforcement learning algorithm, which uses meta-learning pre-training and a new exploration mechanism to accelerate the convergence in large-scale trajectory planning problems. The algorithm can eliminate neural network non-convergence caused by the excessive planning range and has high portability in different flight scenarios.
The Trajectory Planning Method for UAV in Large Airspace Based on Deep Reinforcement Learning
Lect. Notes Electrical Eng.
International Conference on Autonomous Unmanned Systems ; 2021 ; Changsha, China September 24, 2021 - September 26, 2021
Proceedings of 2021 International Conference on Autonomous Unmanned Systems (ICAUS 2021) ; Kapitel : 88 ; 890-899
18.03.2022
10 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
The Trajectory Planning Method for UAV in Large Airspace Based on Deep Reinforcement Learning
British Library Conference Proceedings | 2022
|Crossroad lighthouse trajectory planning method based on deep reinforcement learning
Europäisches Patentamt | 2024
|