Event
Proposes a monocular camera and IMU fusion method for UAV state estimation
1 reports · 1 sources
Filip Novák et al. propose an onboard state estimation method for high-speed UAVs using only a monocular RGB camera and IMU, fusing visual-inertial odometry (VIO), onboard landmark camera measurements, and IMU data, and estimating and compensating for VIO drift through a new mathematical drift model. The paper states that the method was validated through 1,600 simulations and multiple real-world experiments, and was applied to the A2RL Drone Racing Competition 2025, where their team reached the top four among 210 teams and won a medal.
Report timeline
- Monocular RGB Camera and IMU Fusion for Onboard UAV State Estimation, A2RL Drone Racing Semifinalist
The paper proposes an onboard state estimation method for high-speed UAVs using only a monocular RGB camera and an IMU, fusing visual-inertial odometry (VIO), onboard landmark camera measurements, and IMU data, and estimating and compensating for VIO drift through a new mathematical drift model.
arXiv cs.RO ·