GaussFly decouples representation learning from policy optimization via 3D Gaussian Splatting reconstruction and contrastive features to achieve superior sample efficiency and zero-shot sim-to-real transfer for AAV visuomotor policies.
Gaussian splatting to real world flight navigation transfer with liquid networks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.RO 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
LNN-Fly is a structured recurrent policy for continuous-time UAV obstacle avoidance trained with perturbed differentiable rollouts that shows improved tolerance to timing issues and zero-shot transfer to physical hardware with 100% success in real tests.
citing papers explorer
-
GaussFly: Contrastive Reinforcement Learning for Visuomotor Policies in 3D Gaussian Fields
GaussFly decouples representation learning from policy optimization via 3D Gaussian Splatting reconstruction and contrastive features to achieve superior sample efficiency and zero-shot sim-to-real transfer for AAV visuomotor policies.
-
LNN-Fly: Continuous-Time UAV Navigation for Robust Obstacle Avoidance under Timing Mismatch
LNN-Fly is a structured recurrent policy for continuous-time UAV obstacle avoidance trained with perturbed differentiable rollouts that shows improved tolerance to timing issues and zero-shot transfer to physical hardware with 100% success in real tests.