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 2010.15469cs.LGcs.AIcs.RO
收藏

通过探索空间坐标的出现

Emergence of Spatial Coordinates via Exploration

AI Lab, SoftBank Robotics Europe(AI实验室,软银机器人欧洲公司)

Alban Laflaquière

摘要:

空间知识是发展高级感知和认知能力的基本组成部分。传统上,在机器人技术中,欧几里得(x,y,z)坐标系和代理的前向模型是先验定义的。我们表明,一个天真的代理可以自主地建立一个内部坐标系,与外部空间相同的尺寸和度量规则,简单地通过学习预测的结果感觉运动过渡的自我监督的方式。

英文摘要:

Spatial knowledge is a fundamental building block for the development of advanced perceptive and cognitive abilities. Traditionally, in robotics, the Euclidean (x,y,z) coordinate system and the agent's forward model are defined a priori. We show that a naive agent can autonomously build an internal coordinate system, with the same dimension and metric regularity as the external space, simply by learning to predict the outcome of sensorimotor transitions in a self-supervised way.

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。

↑