In urban environments, autonomous vehicles face critical challenges in localization and perception under extreme lighting conditions, including rapid illumination changes, high contrast, and nighttime low-light scenarios. To address the performance degradation of traditional LiDAR-inertial odometry systems under such conditions, this study proposes a high-precision FAST-LIO2-EC algorithm that fuses event cameras into the FAST-LIO2 framework. Event cameras, with their microsecond temporal resolution and 140 dB dynamic range, provide asynchronous edge information that complements LiDAR point clouds and IMU measurements. We validate the proposed system through real-world road tests conducted on public roads and closed test tracks, covering three typical extreme lighting scenarios: tunnel entrance/exit transitions, high-contrast shadow boundaries, and nighttime sparse-lighting conditions. The experimental platform is equipped with a 32-beam LiDAR, a 6-axis IMU, a DVS event camera, and an RTK-GNSS system for ground truth trajectory acquisition. Real-world results demonstrate that the FAST-LIO2-EC system achieves significant improvements in localization accuracy and robustness. In illumination change scenarios, the Absolute Trajectory Error (ATE) is reduced by 32.5% compared to the baseline FAST-LIO2 system, with zero tracking loss events. The point cloud quality is substantially enhanced, with more uniform distribution and clearer obstacle boundaries. In high-contrast scenarios, both systems maintain comparable performance with ATE below 0.15 m. However, in nighttime scenarios, the fusion system shows moderate improvement (15.3% ATE reduction) but reveals sensitivity to event camera noise, indicating the need for adaptive thresholding strategies. Supplementary simulation experiments validate the system’s robustness under varying speeds and sensor noise levels. This work provides a practical solution for autonomous vehicle deployment in complex urban lighting environments, with a comprehensive analysis of real-world performance boundaries and deployment considerations.
Ge et al. (Fri,) studied this question.