Autonomous FPV Flight with Translational Optical Flow and Uncertainty Mask
2026-06-08 • Robotics
Robotics
AI summaryⓘ
The authors address the challenge of flying a small drone quickly and safely using only a single camera. They improve how the drone understands its surroundings by separating the camera's motion effects and focusing only on the parts of the view that show real obstacles. They also create a special mask to better spot obstacles, even in tricky areas. Their approach was tested in both simulations and real forests, showing the drone could fly much faster and more reliably than before.
autonomous flightFPV quadrotormonocular RGB cameraoptical flowego-motionfocus of expansiontranslational flowuncertainty maskdifferentiable simulationobstacle avoidance
Authors
Yang Deng, Yu Hu, Feng Yu, Linzuo Zhang, Danping Zou
Abstract
Autonomous FPV quadrotor flight in complex environments using a monocular RGB camera as the sole exteroceptive sensor remains a fundamental challenge. Recent research has shown that using optical flow as the input of a neural network can achieve end-to-end autonomous flight in cluttered scenes. However, extracting the most relevant information from the flow estimation is the key bottleneck limiting agility and robustness. Existing methods struggle to disentangle obstacle-induced optical flow from the ego-motion background flow and suffer from low signal-to-noise ratios near the focus of expansion (FoE). To address these issues, we decompose the optical flow into translational and rotational components and utilize only the translational flow, which captures scene geometry and depth cues. In addition, we introduce an uncertainty mask derived from inconsistencies between forward and backward flow estimates. This mask highlights obstacle structures, including those within the FoE region. Both cues are fed to a control policy trained in a differentiable simulation framework, which enables efficient first-order optimization across perception and control. We validate our approach through extensive experiments in both simulated and real-world forest environments. The proposed system achieves robust flight at speeds of up to 13.91 m/s in simulation and 11.79 m/s in real-world tests, with a 93.3\% success rate over 30 real-world trials, nearly doubling the previously reported 6 m/s real-world speed of the monocular-RGB optical-flow UAV obstacle avoidance system.