An end-to-end RL policy trained via high-fidelity differentiable simulation maps depth images straight to bodyrate commands, achieving top success rates, low jerk, and zero-shot real-world generalization up to 7.5 m/s in dense environments.
Back to newton’s laws: Learning vision-based agile flight via differentiable physics
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.RO 3years
2026 3representative citing papers
Reinforcement learning sensorimotor policies enable quadrotors to traverse narrow gaps at extreme tilts with 5 cm clearance using only vision and proprioception, including reactive traversal of moving gaps.
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
-
Simple but Stable, Fast and Safe: Achieve End-to-end Control by High-Fidelity Differentiable Simulation
An end-to-end RL policy trained via high-fidelity differentiable simulation maps depth images straight to bodyrate commands, achieving top success rates, low jerk, and zero-shot real-world generalization up to 7.5 m/s in dense environments.
-
Precise Aggressive Aerial Maneuvers with Sensorimotor Policies
Reinforcement learning sensorimotor policies enable quadrotors to traverse narrow gaps at extreme tilts with 5 cm clearance using only vision and proprioception, including reactive traversal of moving gaps.
-
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.