通过自适应调优提升异构机器人点云分割性能
Technical Report for ICRA 2025 GOOSE 3D Semantic Segmentation Challenge: Adaptive Point Cloud Understanding for Heterogeneous Robotic Systems
- 用点提示微调结合Point Transformer v3，实现平台特异性处理
- 在复杂平台上相较基线模型提升22.59%的平均交并比
- 无需额外数据，适合野外多源机器人应用
本技术报告详述了在ICRA 2025 GOOSE 3D语义分割挑战赛中获奖方案的实现细节。该挑战聚焦于从多种机器人平台采集的多样化非结构化室外环境点云进行语义分割。解决方案采用点提示微调（PPT）与Point Transformer v3（PTv3）主干网络相结合，通过平台特定条件控制和跨数据集类别对齐策略，实现对异构激光雷达数据的自适应处理。模型训练不依赖外部附加数据。结果表明，该方法在挑战性平台上的平均交并比（mIoU）相比基线PTv3模型最高提升22.59%，验证了自适应点云理解在实际机器人应用中的有效性。
原文摘要 · Abstract (English)
This technical report presents the implementation details of the winning solution for the ICRA 2025 GOOSE 3D Semantic Segmentation Challenge. This challenge focuses on semantic segmentation of 3D point clouds from diverse unstructured outdoor environments collected from multiple robotic platforms. This problem was addressed by implementing Point Prompt Tuning (PPT) integrated with Point Transformer v3 (PTv3) backbone, enabling adaptive processing of heterogeneous LiDAR data through platform-specific conditioning and cross-dataset class alignment strategies. The model is trained without requiring additional external data. As a result, this approach achieved substantial performance improvements with mIoU increases of up to 22.59% on challenging platforms compared to the baseline PTv3 model, demonstrating the effectiveness of adaptive point cloud understanding for field robotics applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。