.png){kind=icon}
返回
A Sensorimotor Learning Framework for Object Categorization
.png){kind=icon}
OA
AI
DOI：10.1109/TAMD.2015.2463728.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper presents a framework that enables a robot to discover various object categories through interaction. The categories are described using action-effect relations, i.e., sensorimotor contingencies rather than more static shape or appearance representation. The framework provides a functionality to classify objects and the resulting categories, associating a class with a specific module. We demonstrate the performance of the framework by studying a pushing behavior in robots, encoding the sensorimotor contingencies and their predictability with Gaussian Processes. We show how entropy-based action selection can improve object classification and how functional categories emerge from the similarities of effects observed among the objects. We also show how a multidimensional action space can be realized by parameterizing pushing using both position and velocity.
Keyword:
Active perception
categorization
cognitive robotics
developmental robotics
embodiment
learning and adaptive system
object classification
sensorimotor learning
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
4.9
论文数:
1.1K
被引数:
3.9K
机构
引用论文
.png){kind=icon}
分享收藏Tinnitus Retraining Therapy (TRT) as a Method for Treatment of Tinnitus and Hyperacusis Patients耳鸣再训练疗法 (TRT) 作为治疗耳鸣和高亢患者的方法
PREAI
分享收藏
查看更多内容