Kairos：4D场景图中存在性与方向性流动的接地预测

中文摘要 AI 辅助

在有人类活动的环境中实现长期自主性，需要预测在机器人尚未观测到的时间点上，人们是否会移动以及如何移动。现有的行人运动表示面临权衡：它们要么预测未来活动，将每个位置简化为标量速率；要么建模完整的定向分布，但将其在时间上保持固定。我们提出Kairos，一种预测性方向流记忆，将分层3D场景图（3DSG）扩展为4D场景图（4DSG）。重建几何的每个观测体素存储方向混合和存在率，频谱预测器针对任何未来查询时间，预测人们存在的概率以及其运动的完整方向分布。相邻体素之间的成对流依赖性支持条件查询，每体素预测方差产生校准的可信区间，随着观测积累而收紧。我们在三个真实行人环境上评估Kairos：机器人收集的校园数据集、购物中心和连续记录十一个月的车站大厅。其学习状态在闭环校正下保持一致，其预测与在完整检测流上训练的专用占用和流模型相比具有竞争力，尽管Kairos仅从巡逻机器人可用的小部分数据中学习。最后，我们在下游遭遇概率规划任务上验证该表示，其中基于Kairos预测计算的计划在相同成功率下比基于任何时间不变地图计算的计划遇到更多人。我们在https://github.com/IacopomC/kairos提供代码。

英文摘要

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.

发表机构

• University of Turku（图尔库大学）
• Centre for Artificial Intelligence, Zürich University of Applied Sciences（苏黎世应用科学大学人工智能中心）
• Instituto Tecnológico de Aragón (ITA)（阿拉贡技术研究所）
• University of Zaragoza（萨拉戈萨大学）

机构由 AI 辅助整理，请以论文原文为准。