A reinforcement-learning drone controller, trained on synthetic random visual features, lands on moving maritime platforms without any explicit platform-state estimate and transfers zero-shot to A-KAZE and SURF extractors.
Demonstrating Agile Flight from Pixels without State Estima- tion
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.RO 2years
2026 2representative citing papers
RL framework for agile drone racing combines task-aware switching and physically informed procedural track generation to achieve 7.4x better zero-shot generalization to unseen tracks while maintaining competitive speeds.
citing papers explorer
-
Vision-Based Agile Landing on Turbulent Waters
A reinforcement-learning drone controller, trained on synthetic random visual features, lands on moving maritime platforms without any explicit platform-state estimate and transfers zero-shot to A-KAZE and SURF extractors.
-
Bridging Performance and Generalization in Reinforcement Learning for Agile Flight
RL framework for agile drone racing combines task-aware switching and physically informed procedural track generation to achieve 7.4x better zero-shot generalization to unseen tracks while maintaining competitive speeds.