Reproduce “Deep Reinforcement Learning for Sim-to-Real Policy Transfer of VTOL-UAVs Offshore Docking Operations” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Ali M. Ali, Aryaman Gupta, Hashim A. Hashim
The authors study simulated UAV landing on a wave-disturbed offshore platform, motivated by limited battery endurance. They use model-based control for the approach and train reinforcement-learning policies offline for vertical landing, randomizing wave motion. PPO is fastest among tested agents at 4.9 seconds, while Double DQN reports lower impact velocity. The simulations do not establish real-world transfer or landing success rates.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.