视线外的具身智能体：多模态跟踪、传感器融合与轨迹预测
Out-of-Sight Embodied Agents: Multimodal Tracking, Sensor Fusion, and Trajectory Forecasting
AI总结：
本文提出改进的视线外轨迹预测方法，通过视觉定位去噪模块提升轨迹预测性能，实验表明在Vi-Fi和JRDB数据集上达到最优效果，为自动驾驶、机器人和监控提供新方向。
摘要：
轨迹预测是计算机视觉、视觉-语言-动作模型、世界模型和自主系统中的基础问题，对自动驾驶、机器人和监控有广泛影响。然而，现有方法大多假设观测完整且清晰，无法有效处理视线外智能体或由有限摄像头覆盖、遮挡和缺乏地面真实轨迹导致的噪声传感信号。本文在先前工作基础上，将Out-of-Sight Trajectory Prediction（OOSTraj）从行人扩展到行人和车辆，增强其在自动驾驶、机器人和监控中的相关性。改进的视觉定位去噪模块利用相机校准建立视觉-位置对应关系，缓解缺乏直接视觉线索的问题，实现有效无监督去噪。在Vi-Fi和JRDB数据集上的大量实验表明，本方法在轨迹去噪和预测上均取得最优结果，优于先前基线。此外，本文还与经典去噪方法如卡尔曼滤波以及最近的轨迹预测模型进行比较，建立了更强的基准。据我们所知，这是首次利用视觉定位投影来去噪视线外智能体的噪声传感器轨迹的工作，为未来研究开辟了新方向。
英文摘要：
Trajectory prediction is a fundamental problem in computer vision, vision-language-action models, world models, and autonomous systems, with broad impact on autonomous driving, robotics, and surveillance. However, most existing methods assume complete and clean observations, and therefore do not adequately handle out-of-sight agents or noisy sensing signals caused by limited camera coverage, occlusions, and the absence of ground-truth denoised trajectories. These challenges raise safety concerns and reduce robustness in real-world deployment. In this extended study, we introduce major improvements to Out-of-Sight Trajectory (OST), a task for predicting noise-free visual trajectories of out-of-sight objects from noisy sensor observations. Building on our prior work, we expand Out-of-Sight Trajectory Prediction (OOSTraj) from pedestrians to both pedestrians and vehicles, increasing its relevance to autonomous driving, robotics, and surveillance. Our improved Vision-Positioning Denoising Module exploits camera calibration to establish vision-position correspondence, mitigating the lack of direct visual cues and enabling effective unsupervised denoising of noisy sensor signals. Extensive experiments on the Vi-Fi and JRDB datasets show that our method achieves state-of-the-art results for both trajectory denoising and trajectory prediction, with clear gains over prior baselines. We also compare with classical denoising methods, including Kalman filtering, and adapt recent trajectory prediction models to this setting, establishing a stronger benchmark. To the best of our knowledge, this is the first work to use vision-positioning projection to denoise noisy sensor trajectories of out-of-sight agents, opening new directions for future research.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
