Sensor Fusion by Spatial Encoding for Autonomous Driving
This work addresses perception challenges in autonomous driving, offering incremental improvements over existing methods.
The paper tackles sensor fusion for autonomous driving by introducing a method that fuses camera and LiDAR data using Transformer modules at multiple resolutions, achieving 8% and 19% improvements in driving scores on challenging benchmarks compared to TransFuser.
Sensor fusion is critical to perception systems for task domains such as autonomous driving and robotics. Recently, the Transformer integrated with CNN has demonstrated high performance in sensor fusion for various perception tasks. In this work, we introduce a method for fusing data from camera and LiDAR. By employing Transformer modules at multiple resolutions, proposed method effectively combines local and global contextual relationships. The performance of the proposed method is validated by extensive experiments with two adversarial benchmarks with lengthy routes and high-density traffics. The proposed method outperforms previous approaches with the most challenging benchmarks, achieving significantly higher driving and infraction scores. Compared with TransFuser, it achieves 8% and 19% improvement in driving scores for the Longest6 and Town05 Long benchmarks, respectively.