SHARP：面向运动预测中精准鲁棒预测的短窗口流式方法
SHARP: Short-Window Streaming for Accurate and Robust Prediction in Motion Forecasting
面向视觉感知的自动驾驶系统，提供了一种实例感知的上下文流式机制：在推理过程中增量维护并更新每个智能体的潜变量表示，使模型在观测窗口长度不一致时仍能保持预测精度；该机制可直接迁移到在线感知与跟踪的时序特征维护中。
原文依据 leverages an instance-aware context streaming to maintain and update latent agent representations across inference steps
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动态交通环境中，运动预测模型必须能够持续、准确地估计未来轨迹。基于流式的方法是一种有前景的解决方案，但尽管近期取得了进展，当面对异构的观测长度时，其性能往往会下降。为解决这一问题，我们提出了一种新颖的基于流式的运动预测框架，显式地关注不断演化的场景。我们的方法增量式地处理不断到来的观测窗口，并利用实例感知的上下文流式机制，在推理步骤之间维护和更新潜变量智能体表示。双重的训练目标进一步使模型在多样的观测时域上保持一致的预测精度。在 Argoverse 2、nuScenes 和 Argoverse 1 上的大量实验表明，我们的方法在演化场景条件下以及在单智能体基准上均具有鲁棒性。我们的模型在 Argoverse 2 多智能体基准的流式推理中取得了最优性能，同时保持极低的延迟，凸显了其面向真实世界部署的适用性。
英文原文摘要 1101 字符
In dynamic traffic environments, motion forecasting models must be able to accurately estimate future trajectories continuously. Streaming-based methods are a promising solution, but despite recent advances, their performance often degrades when exposed to heterogeneous observation lengths. To address this, we propose a novel streaming-based motion forecasting framework that explicitly focuses on evolving scenes. Our method incrementally processes incoming observation windows and leverages an instance-aware context streaming to maintain and update latent agent representations across inference steps. A dual training objective further enables consistent forecasting accuracy across diverse observation horizons. Extensive experiments on Argoverse 2, nuScenes, and Argoverse 1 demonstrate the robustness of our approach under evolving scene conditions and also on the single-agent benchmarks. Our model achieves state-of-the-art performance in streaming inference on the Argoverse 2 multi-agent benchmark, while maintaining minimal latency, highlighting its suitability for real-world deployment.