arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1912.02149cs.ROcs.LG
收藏

动态希尔伯特映射:变化环境中实时的占领预测

Dynamic Hilbert Maps: Real-Time Occupancy Predictions in Changing Environment

The University of Sydney(悉尼大学);Toyota Research Institute(丰田研究院);NVIDIA Research(英伟达研究院)

Vitor Guizilini, Ransalu Senanayake, Fabio Ramos

摘要:

本文讨论了学习动态环境的瞬时占用水平和预测未来的占用水平的问题。由于大多数现实世界环境的复杂性,例如城市街道或拥挤的区域,将时间依赖性有效且鲁棒地结合到静态占用模型中仍然是一个挑战。我们提出了一种方法来捕捉移动对象的空间不确定性,并将这种不确定性信息到一个连续的占用地图表示在一个丰富的高维特征空间。利用LIDAR数据进行的实验验证了该算法的实时的【形】性能。

英文摘要:

This paper addresses the problem of learning instantaneous occupancy levels of dynamic environments and predicting future occupancy levels. Due to the complexity of most real-world environments, such as urban streets or crowded areas, the efficient and robust incorporation of temporal dependencies into otherwise static occupancy models remains a challenge. We propose a method to capture the spatial uncertainty of moving objects and incorporate this uncertainty information into a continuous occupancy map represented in a rich high-dimensional feature space. Experiments performed using LIDAR data verified the real-time performance of the algorithm.

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。

↑