IRGNN：用于雷达点云目标检测的高效不变雷达图神经网络
IRGNN: Efficient Invariant Radar Graph Neural Network for Radar Point Cloud Object Detection
浏览论文内容
中文总结 AI 辅助
针对雷达点云稀疏无序、信息不足难以适配现有激光雷达方法的问题，提出IRGNN，通过不变特征设计、改进MPNN及任务头实现目标检测，在RadarScenes数据集上性能更优且推理效率更高。
中文摘要 AI 辅助
感知是自动驾驶系统的核心组成部分。尽管基于激光雷达（LiDAR）的目标检测方法已取得显著进展，但其可靠性在恶劣天气条件下会下降。雷达点云因能抵御恶劣天气和低光照场景，提供了一种鲁棒的替代方案。然而，雷达点云通常比激光雷达数据更稀疏、无序且信息更少，导致直接应用现有的基于激光雷达的感知方法极具挑战性。为解决这些问题，我们提出了IRGNN（Invariant Radar Graph Neural Network，不变雷达图神经网络）用于雷达点云目标检测。IRGNN首先利用平移和旋转不变的特征设计将雷达点云重构为图表示，实现对稀疏雷达测量的鲁棒建模；随后采用改进的消息传递神经网络（MPNN），结合残差连接和虚拟节点层，增强局部特征传播与全局上下文建模；最后将特定任务头应用于学习到的图表示，完成目标分类与边界框预测。在RadarScenes数据集上的实验结果表明，IRGNN的性能优于现有基于雷达的目标检测方法，且达到了具有竞争力的表现。此外，IRGNN在推理阶段大幅降低了计算成本和内存占用，展现出其在自动驾驶领域高效雷达感知方面的有效性与实际应用潜力。
英文摘要
Perception is a fundamental component of autonomous driving systems. While LiDAR-based methods have achieved remarkable progress in object detection, their reliability can degrade under adverse weather conditions. Radar point clouds provide a robust alternative due to their resilience to bad weather and low-illumination scenarios. However, radar point clouds are typically sparse, unordered, and less informative than LiDAR data, making it challenging to directly apply existing LiDAR-based perception methods. To address these challenges, we propose IRGNN, an Invariant Radar Graph Neural Network for radar point cloud object detection. IRGNN first reconstructs radar point clouds into graph representations using translation- and rotation-invariant feature designs, enabling robust modeling of sparse radar measurements. It then employs an improved message passing neural network (MPNN) with residual connections and a virtual node layer to enhance local feature propagation and global context modeling. Finally, task-specific heads are applied to the learned graph representations for object classification and bounding box prediction. Experimental results on the RadarScenes dataset show that IRGNN outperforms existing radar-based object detection methods and achieves competitive performance. In addition, IRGNN significantly reduces computational cost and memory usage during inference, demonstrating its effectiveness and practical potential for efficient radar-based perception in autonomous driving.
发表机构
- China Agricultural University（中国农业大学）
- Tsinghua University（清华大学）
机构由 AI 辅助整理，请以论文原文为准。
