外观
论文arXiv 2609.274671 个月前
Kairos：4D 场景图中存在与方向流的 Grounded 预测
原文链接：Kairos: Grounded Forecasting of Presence and Directional Flow in 4D Scene Graphs（arXiv 2609.27467 · 发布日期：2026-09-23）
Kairos: Grounded Forecasting of Presence and Directional Flow in 4D Scene Graphs
Kairos用预测性方向流记忆扩展3DSG为4DSG，在三类真实行人环境和规划任务中预测人在未来时刻的存在与运动方向。
核心要点
- 动机：机器人长期自主需预判未观测时刻的人是否出现及如何移动。
- 方法：在每个已观测体素存方向混合与存在率，并用谱预测器查询未来。
- 还建模相邻体素成对流依赖，支持条件查询，并给出逐体素预测方差。
- 实验显示三类真实环境中预测具竞争力，同等成功率下规划遇人更多；代码开源。
验证范围与局限：验证范围为三个真实行人环境和一个下游相遇概率规划任务。
英文摘要 (Abstract)
Long-term autonomy in human-populated environments requires anticipating whether and how people will move at times a robot has not yet observed. Existing representations of pedestrian motion face a tradeoff: they either forecast future activity, reducing each location to a scalar rate, or model the full directional distribution, holding it fixed in time. We present Kairos, a predictive directional-flow memory that extends a hierarchical 3D scene graph (3DSG) to a 4D scene graph (4DSG). Every observed voxel of the reconstructed geometry stores a directional mixture and a presence rate, and spectral predictors forecast, for any future query time, both the probability that people are present and the full directional distribution of their motion. Pairwise flow dependence between adjacent voxels supports conditional queries, and per-voxel predictive variances yield calibrated credible intervals that tighten as observations accumulate. We evaluate Kairos on three real pedestrian environments: a robot-collected campus dataset, a shopping mall, and a station concourse recorded continuously for eleven months. Its learned state remains consistent under loop-closure corrections, and its forecasts are competitive with dedicated occupancy and flow models trained on the full detection stream, although Kairos learns from only the small fraction available to a patrolling robot. Finally, we validate the representation on a downstream encounter-probability planning task, where plans computed over the Kairos forecasts encounter more people than plans computed over any time-invariant map at an equal success rate. We provide the code at https://github.com/IacopomC/kairos.
作者：Iacopo Catalano, Julio A. Placed, Javier Civera, Jorge Peña Queralta
来源
本页事实对应的公开页面，以原文为准。