外观
论文arXiv 2610.1727916 天前
ReForesight：面向动态语义建图的遮挡鲁棒重识别与未来占用预测
原文链接：ReForesight: Occlusion-Robust Re-Identification and Future Occupancy Forecasting for Dynamic Semantic Mapping（arXiv 2610.17279 · 发布日期：2026-10-12）
ReForesight: Occlusion-Robust Re-Identification and Future Occupancy Forecasting for Dynamic Semantic Mapping
ReForesight为粒子式语义建图加入实例级未来占用与遮挡后重识别，并在CODa序列和户外清洁机器人上验证。
核心要点
- 动机是共享步道中的机器人需要知道人将出现的位置，而语义占用图只显示当前位置。
- 方法用36.6k参数MLP预测人或车辆至多3秒未来位姿，并以Kalman回退和静止门控保护。
- 系统将对象自身点移动到预测位姿形成ghost点云，可选跟踪器用关键点描述子和3D门重关联遮挡后对象。
- 在四段保留CODa序列上，MLP的3秒最终位移误差低于Kalman和同规模GRU；代码、模型和ROS-free演示已发布。
验证范围与局限：验证范围包括四段保留CODa序列，以及一台户外清洁机器人的现场演示。
英文摘要 (Abstract)
Robots sharing walkways need to know where people will be, yet semantic occupancy maps show only where they are. We present ReForesight, an open-source ROS 2 toolkit that adds instance-level future occupancy and re-identification after occlusion to a particle-based semantic mapping pipeline. A 36.6k-parameter MLP predicts each tracked person or vehicle up to 3 s ahead, guarded by a Kalman fallback and a stationary gate, and the object's own points are moved to the forecast pose, forming a "ghost" point cloud in the map frame without an occupancy decoder. An optional tracker re-associates objects after occlusion using keypoint descriptors the pipeline already computes and a metric 3D gate. On four held-out CODa sequences, the MLP lowers the mean 3 s final displacement error from 0.728 m (Kalman) to 0.662 m and beats a similar-size GRU (0.692 m) on every sequence, at 0.04 ms per instance on one CPU core. Code, all models, and a ROS-free demo are released; field demonstrations use an outdoor cleaning robot.
作者：Didar Seyidov, Faith Ogunwoye, Hajira Amjad, Danil Tolkachev, Yuri Sarkisov, Dzmitry Tsetserukou
来源
本页事实对应的公开页面，以原文为准。