基于强化学习的稀疏采样下小型空中目标自适应三维感知
Adaptive 3D Perception for Small Aerial Targets Under Sparse Sampling via Reinforcement Learning
用强化学习策略根据无标签的稀疏度/前景接受率/轨迹稳定性统计，在线调节体素分辨率、检测敏感度与关联门限，为长距离激光雷达小目标在点密度剧变下的检测-跟踪闭环提供了可复用的自适应感知思路。
原文依据 a lightweight 5D policy that jointly adjusts voxel resolution, detection sensitivity, and association gating from label-free statistics
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论在远距离激光雷达中检测小型空中目标（SAT）具有挑战性，因为运动会导致点密度出现极端变化，从而破坏标准三维检测与跟踪中固定体素和静态阈值的假设。为应对这些挑战，我们提出 A3PRL，一个由强化学习驱动的自适应感知框架，它在激光雷达感知与跟踪之间形成闭环。A3PRL 采用带有时间色散特征与速度变化线索的稀疏性感知候选生成阶段，以及一个轻量级 5D 策略，该策略依据稀疏性、前景接受度和轨迹稳定性的无标签统计量，联合调整体素分辨率、检测敏感度和关联门限。该策略利用特权真值轨迹进行训练，以优化一个平衡几何精度、时序稳定性和正则化接受度的奖励，但在测试时完全无标签运行。在公开的 MMAUD 基准上，于 V1 上训练并在未见过的 V2/V3 上评估，A3PRL 相比其非强化学习对应方法将三维定位误差降低约 19%，并在白天和夜间条件下持续优于仅激光雷达和多模态基线。同一策略能够迁移到具有异构扫描模式的其他 SAT 数据集，保持准确且稳定的轨迹。
英文原文摘要 1271 字符
Detecting small aerial targets (SATs) in long-range LiDAR is challenging because motion causes extreme variations in point density, breaking fixed-voxel and static-threshold assumptions in standard 3D detection and tracking. To address the challenges, we introduce A3PRL, an RL-driven adaptive perception framework that closes the loop between LiDAR sensing and tracking. A3PRL uses a sparsity-aware proposal stage with Temporal Dispersion Signatures and velocity-change cues, and a lightweight 5D policy that jointly adjusts voxel resolution, detection sensitivity, and association gating from label-free statistics of sparsity, foreground acceptance, and track stability. The policy is trained with privileged ground-truth trajectories to optimize a reward balancing geometric accuracy, temporal stability, and regularized acceptance, but runs fully label-free at test time. On the public MMAUD benchmark, training on V1 and evaluating on unseen V2/V3, A3PRL reduces 3D localization error by about 19% over its non-RL counterpart and consistently outperforms LiDAR-only and multimodal baselines under both day and night conditions. The same policy is able to transfer to other SAT datasets with heterogeneous scan patterns, maintaining accurate and stable trajectories.