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 1810.05057cs.AIcs.LGcs.ROstat.ML
收藏

识别不变的感觉运动结构是发现物体的先决条件

Identification of Invariant Sensorimotor Structures as a Prerequisite for the Discovery of Objects

SoftBank Robotics Europe(软银机器人欧洲公司);Sorbonne Université(索邦大学);Institut des Systèmes Intelligents et de Robotique(智能系统与机器人研究所);CNRS(法国国家科学研究中心)

Nicolas Le Hir, Olivier Sigaud, Alban Laflaquière

摘要:

感知周围环境的对象是有用的任何通用智能代理。在本文中,我们研究了一个基本的机制,使对象感知成为可能,即识别的时空不变的结构在感觉运动的经验代理。我们从感觉运动偶然性理论中获得灵感,通过感觉运动、无监督和预测的方法来定义这种机制的计算模型。我们的模型是基于处理人工代理与其环境的无监督交互。我们展示了环境中的时空不变结构如何在代理的感觉运动体验中引起不稳定,以及该代理如何在建立其感觉运动体验的预测模型的同时,将其捕获为由运动命令连接的感觉状态图中的密集连接子图。我们的方法是集中在基本的机制,并说明了一组简单的实验中,代理与环境的相互作用。我们展示了如何代理可以建立一个内部模型的移动,但时空不变的结构,通过执行一个频谱聚类的图形建模其整体感觉运动的经验。我们系统地研究该模型的属性,更全球性地揭示了基于静态图像集合的监督处理方法的范式的特殊性。

英文摘要:

Perceiving the surrounding environment in terms of objects is useful for any general purpose intelligent agent. In this paper, we investigate a fundamental mechanism making object perception possible, namely the identification of spatio-temporally invariant structures in the sensorimotor experience of an agent. We take inspiration from the Sensorimotor Contingencies Theory to define a computational model of this mechanism through a sensorimotor, unsupervised and predictive approach. Our model is based on processing the unsupervised interaction of an artificial agent with its environment. We show how spatio-temporally invariant structures in the environment induce regularities in the sensorimotor experience of an agent, and how this agent, while building a predictive model of its sensorimotor experience, can capture them as densely connected subgraphs in a graph of sensory states connected by motor commands. Our approach is focused on elementary mechanisms, and is illustrated with a set of simple experiments in which an agent interacts with an environment. We show how the agent can build an internal model of moving but spatio-temporally invariant structures by performing a Spectral Clustering of the graph modeling its overall sensorimotor experiences. We systematically examine properties of the model, shedding light more globally on the specificities of the paradigm with respect to methods based on the supervised processing of collections of static images.

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。

↑