Team Samsung-RAL: Technical Report for 2024 RoboDrive Challenge-Robust Map Segmentation Track

TL;DR

The paper addresses robustness of BEV semantic map segmentation for autonomous driving under adverse conditions, evaluating how temporal information, backbone strength, and data augmentation affect performance. Building on the BEVerse baseline, it conducts large-scale ablations across backbones (Tiny/Small/Base), temporal fusion, and augmentation methods, on the nuScenes-derived dataset under various corruptions. Key findings show that a strong Swin-Base backbone substantially improves corruption robustness, temporal fusion boosts robustness during degraded conditions, and selective augmentations (e.g., GridMask, hue/saturation variations) yield notable gains in mIoU. The results advance reliable map segmentation for autonomous driving and inform design choices for RoboDrive Challenge robustness. The work also points to future direction in exploring more advanced augmentations and backbone configurations to further close the robustness gap.

Abstract

In this report, we describe the technical details of our submission to the 2024 RoboDrive Challenge Robust Map Segmentation Track. The Robust Map Segmentation track focuses on the segmentation of complex driving scene elements in BEV maps under varied driving conditions. Semantic map segmentation provides abundant and precise static environmental information crucial for autonomous driving systems' planning and navigation. While current methods excel in ideal circumstances, e.g., clear daytime conditions and fully functional sensors, their resilience to real-world challenges like adverse weather and sensor failures remains unclear, raising concerns about system safety. In this paper, we explored several methods to improve the robustness of the map segmentation task. The details are as follows: 1) Robustness analysis of utilizing temporal information; 2) Robustness analysis of utilizing different backbones; and 3) Data Augmentation to boost corruption robustness. Based on the evaluation results, we draw several important findings including 1) The temporal fusion module is effective in improving the robustness of the map segmentation model; 2) A strong backbone is effective for improving the corruption robustness; and 3) Some data augmentation methods are effective in improving the robustness of map segmentation models. These novel findings allowed us to achieve promising results in the 2024 RoboDrive Challenge-Robust Map Segmentation Track.

Figures (3)

• Figure 1: An overview of Our method. We explored several methods to improve the robustness of the baseline map segmentation model.
• Figure 2: Examples of augmentation methods used in our method.
• Figure 3: Illustration of different augmentation methods.