A Social-GAN-style LSTM generator predicts UAS landing trajectories and beats a Gaussian Mixture Regression baseline on real drone data, though the advantage disappears on simulated data beyond four steps.
Optimized landing of drones in the context of congested air traffic and limited vertiports,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Landing Trajectory Prediction for UAS Based on Generative Adversarial Network
A Social-GAN-style LSTM generator predicts UAS landing trajectories and beats a Gaussian Mixture Regression baseline on real drone data, though the advantage disappears on simulated data beyond four steps.