提出轨迹感知的追踪框架，让无人机追击更可行
Perception-to-Pursuit: Track-Centric Temporal Reasoning for Open-World Drone Detection and Autonomous Chasing
- 用8维动态符号表示飞行轨迹，通过因果Transformer预测未来行为
- 在真实拦截条件下，追击成功率提升597倍，轨迹误差降低77%
- 适合需要精准追踪与自动追击的安防无人机场景
自主无人机追击不仅需要检测目标，还需预测其轨迹以实现物理上可拦截的追击。现有追踪方法仅优化预测精度，忽略追击可行性，导致99.9%的轨迹无法实际拦截。我们提出感知到追击（Perception-to-Pursuit, P2P）框架，构建以轨迹为中心的时序推理机制。该方法将无人机运动表示为包含速度、加速度、尺度和光滑性的8维紧凑符号，使12帧因果变换器能够推断未来行为。我们引入拦截成功率（ISR）指标，评估在真实拦截器约束下的追击可行性。在包含226个真实无人机序列的Anti-UAV-RGBT数据集上，P2P实现28.12像素平均位移误差和0.597 ISR，相比仅追踪基线，轨迹预测准确率提升77%，追击可行性提高597倍，同时保持100%的无人机分类准确率。结果表明，对运动模式的时序推理能同时实现高精度预测与可执行的追击规划。
原文摘要 · Abstract (English)
Autonomous drone pursuit requires not only detecting drones but also predicting their trajectories in a manner that enables kinematically feasible interception. Existing tracking methods optimize for prediction accuracy but ignore pursuit feasibility, resulting in trajectories that are physically impossible to intercept 99.9% of the time. We propose Perception-to-Pursuit (P2P), a track-centric temporal reasoning framework that bridges detection and actionable pursuit planning. Our method represents drone motion as compact 8-dimensional tokens capturing velocity, acceleration, scale, and smoothness, enabling a 12-frame causal transformer to reason about future behavior. We introduce the Intercept Success Rate (ISR) metric to measure pursuit feasibility under realistic interceptor constraints. Evaluated on the Anti-UAV-RGBT dataset with 226 real drone sequences, P2P achieves 28.12 pixel average displacement error and 0.597 ISR, representing a 77% improvement in trajectory prediction and 597x improvement in pursuit feasibility over tracking-only baselines, while maintaining perfect drone classification accuracy (100%). Our work demonstrates that temporal reasoning over motion patterns enables both accurate prediction and actionable pursuit planning.
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。