arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2302.10135cs.RO
收藏

增强动态场景下机器人传感器数据的因果发现

Enhancing Causal Discovery from Robot Sensor Data in Dynamic Scenarios

University of Lincoln(林肯大学);University of Padua(帕多瓦大学)

Luca Castri, Sariah Mghames, Marc Hanheide, Nicola Bellotto

摘要:

从传感器数据的时间序列中识别动态系统的主要特征并学习其因果关系是许多实际机器人应用中的关键问题。在本文中,我们提出了一个扩展的国家的最先进的因果发现方法,PCMCI,嵌入一个额外的特征选择模块的基础上转移熵。从一组预先确定的变量开始,新算法通过只考虑其主要特征而忽略那些被认为对理解系统演化不必要的特征来重建所观察系统的因果模型。我们首先验证的方法上的玩具问题和合成数据的大脑网络,其中地面实况模型是可用的,然后在现实世界的机器人场景中使用大规模的时间序列数据集的人类轨迹。实验表明,我们的解决方案在准确性和计算效率方面优于以前的最先进技术,可以更好,更快地从机器人传感器数据中发现有意义的模型。

英文摘要:

Identifying the main features and learning the causal relationships of a dynamic system from time-series of sensor data are key problems in many real-world robot applications. In this paper, we propose an extension of a state-of-the-art causal discovery method, PCMCI, embedding an additional feature-selection module based on transfer entropy. Starting from a prefixed set of variables, the new algorithm reconstructs the causal model of the observed system by considering only its main features and neglecting those deemed unnecessary for understanding the evolution of the system. We first validate the method on a toy problem and on synthetic data of brain network, for which the ground-truth models are available, and then on a real-world robotics scenario using a large-scale time-series dataset of human trajectories. The experiments demonstrate that our solution outperforms the previous state-of-the-art technique in terms of accuracy and computational efficiency, allowing better and faster causal discovery of meaningful models from robot sensor data.

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。

↑