深度雷达：用于自动驾驶车辆感知的端到端MIMO雷达设计与多模态融合
DeeperRadar: End-to-End MIMO Radar Design and Multi-Modal Fusion for Autonomous Vehicle Perception
浏览论文内容
中文总结 AI 辅助
深度雷达以雷达为中心，通过端到端学习稀疏采集模式，共同设计雷达传感与多模态3D检测。其可学习的MIMO设计模块在融合网络中训练，由其他传感器监督。在RADIal数据集上评估，能发现稀疏配置，降低成本与复杂性，表明最优设计取决于融合堆栈和感知任务。
中文摘要 AI 辅助
深度雷达是一个以雷达为中心、受传感器堆栈条件限制的框架，通过与融合模型端到端学习稀疏采集模式，共同设计用于自主移动的雷达传感和多模态3D检测。一个可学习的MIMO设计模块在融合网络中端到端训练，该网络直接对原始雷达ADC数据以及相机图像和激光雷达点云进行操作。训练期间，设计模块由其他传感器监督，使其能学习激活哪些接收天线及其有效数量。部署时，设计模块被学习到的稀疏子采样掩码取代，下游模型架构不变。在RADIal数据集上评估，深度雷达发现稀疏、任务感知的雷达配置，在使用更少接收器时匹配或超过全阵列基线，可能降低雷达成本和集成复杂性。这些结果表明，学习到的最优MIMO雷达设计取决于融合堆栈和下游感知任务。
英文摘要
DeeperRadar is a radar-centric, sensor-stack-conditioned framework that co-designs radar sensing and multi-modal 3D detection for autonomous mobility by learning a sparse acquisition pattern end-to-end with the fusion model. A learnable MIMO design module is trained end-to-end within a fusion network that operates directly on raw radar ADC data together with camera images and LiDAR point clouds. During training, the design module is supervised by the other sensors, enabling the system to learn both which receiver antennas to activate and the effective number of them. At deployment, the design module is removed and replaced by the learned sparse subsampling mask, leaving the downstream model architecture unchanged. Evaluated on the RADIal dataset, DeeperRadar discovers sparse, task-aware radar configurations that match or exceed full-array baselines while using fewer receivers, potentially reducing radar cost and integration complexity. These results show that learned optimal MIMO radar design depends on the fusion stack and the downstream perception task.
发表机构
- Technion–Israel Institute of Technology（以色列理工学院）
- Ben-Gurion University of the Negev（内盖夫本-古里安大学）
机构由 AI 辅助整理，请以论文原文为准。
