AI 中文总结
本研究提出基于Mamba的知识蒸馏框架，通过选择性体素空间特征对齐实现轻量型3D目标检测，在保持精度的同时显著降低计算负载。
AI 中文摘要
采用光探测与测距（LiDAR）传感器的3D目标检测，需在自主驾驶与机器人导航的车载感知中实现精度与计算效率的平衡。现有多数基于LiDAR的检测方法采用复杂架构提取特征，整合大量上下文信息以提升精度，这常导致计算成本显著增加，在资源受限的嵌入式设备上性能欠佳。本研究提出一种知识蒸馏框架，通过选择性体素空间特征对齐，将强教师模型的目标级体素表示迁移至轻量型学生模型。利用选择性状态空间线性时间序列模型（Mamba），设计多分支Mamba教师骨干网络与感知框的特征迁移机制，通过基于Mamba的投影模块对齐教师与学生网络间空间对应的体素特征。在公开数据集与真实世界数据上的实验结果表明，与现有最优方法相比，所提方法在保持竞争力精度的同时，显著降低了计算负载。
英文摘要
3D object detection using light detection and ranging (LiDAR) sensors requires a balance between accuracy and computational efficiency for onboard perception in autonomous driving and robotic navigation. Many existing LiDAR-based detection methods employ complex architectures to extract features, integrating large amounts of contextual information to enhance accuracy. This often results in significant computational costs, leading to suboptimal performance on resource-constrained embedded devices. In this study, we propose a knowledge distillation framework that transfers object-level voxel representations from a strong teacher model to lightweight student models through selective voxel-space feature alignment. Taking advantage of the linear-time sequence model with selective state spaces (Mamba), we design a multi-branch Mamba teacher backbone and a box-aware feature transfer mechanism that aligns spatially corresponding voxel features between teacher and student networks through a Mamba-based projection module. Experimental results on both a public dataset and real-world data show that our approach significantly reduces computational load while maintaining competitive accuracy compared with state-of-the-art methods.
CommentsAccepted for publication in IEEE Robotics and Automation Letters (RA-L), 2026
