FW-ORB-SLAM: A Monocular Visual SLAM Algorithm for Flapping-Wing Flying Robots
Zheng Zhong, Shou Chen, Qiang Fu, Jiubin Wang, Wei He
AI summary
Problem
Existing visual SLAM algorithms fail on flapping-wing flying robots due to intense high-frequency image vibrations from wing flapping and unpredictable outdoor illumination changes.
Approach
The method modifies ORB-SLAM3 by applying FFT-based frequency domain decomposition to stabilize images and a local adaptive contrast enhancement algorithm to maintain feature tracking under varying light.
Key results
- Developed a custom monocular dataset with four outdoor flight trajectories for FWFRs
- Implemented FFT-based frequency decomposition to isolate and filter flapping-induced jitter
- Designed a local adaptive contrast enhancement and color correction method for dynamic lighting
- Achieved lower Absolute Trajectory Error than ORB-SLAM3 on both custom and FWAF-VID datasets
Why it matters
Enables reliable autonomous navigation for biomimetic flapping-wing robots in complex outdoor environments, advancing their practical deployment for reconnaissance and surveying.
Abstract
Visual simultaneous localization and mapping (SLAM) is of great significance for flapping-wing flying robots (FWFRs) to enhance their autonomous navigation capabilities in complex environments. However, during the motion of FWFRs, there are intense image vibrations accompanied by significant illumination changes, which would prevent existing visual SLAM algorithms from being directly applied to FWFRs. Therefore, this paper proposes a modified ORB-SLAM3 algorithm called FW-ORB-SLAM for FWFRs. First, we adopt the fast Fourier transform (FFT) method to map the original images to the frequency domain. Then, based on the characteristic flapping motion of the FWFR, we decompose the frequency domain jitter to obtain stabilized images. Moreover, to mitigate the impact of illumination variations on feature point tracking during outdoor flight, a local adaptive contrast enhancement method is proposed, which enhances the stability of feature point tracking and augments the robustness of the SLAM algorithm. Finally, flight experiments carried out using our self-developed FWFR named U-Dove demonstrate that FW-ORB-SLAM outperforms the state- of-the-art ORB-SLAM3 algorithm, which provides insights into performing vision-based SLAM tasks for the FWFR.