Scan data based fusion strategy for high level perception
24 Jun 2026
ADAS and Level 2 takes off with +++ performance. A review of regulation, design, digital and physical validation, tooling and methods to reach safety performance globally
In this presentation we analyse different high-level perception architectures for L3 ADAS utilizing LiDAR and HD Radar data. First, we evaluate standard fusion strategies, highlighting the limitations of both early and late-stage fusion approaches. We then propose a robust mid-level fusion framework, based on clustering and feature extraction level, which ensures significant performance "goodness" by incorporating LiDAR accuracy together with movement estimation from HDR.
Furthermore, we address the difficulties in multi-modal sensing related to managing extreme pointcloud density disparities and mitigating sensor-specific artifacts.
- High level perception
- Scan data fusion
- LiDAR
- HD Radar
