arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.03029cs.RO
收藏

在线机器人属性学习的多模态探索性行为规划

Planning Multimodal Exploratory Actions for Online Robot Attribute Learning

State University of New York at Binghamton(纽约州立大学宾汉姆顿分校);Tufts University(塔夫茨大学)

Xiaohan Zhang, Jivko Sinapov, Shiqi Zhang

摘要:

机器人经常需要感知物体属性,如“红色”,“重”和“空”,使用多模态探索性动作,如“看”,“举”和“摇”。“机器人属性学习算法的目标是在给定探索性动作的情况下为每个可感知属性学习观察模型。一旦学习了属性模型,它们就可以用来识别新对象的属性,回答诸如“这个对象是红色和空的吗?“属性学习和识别在文献中被视为两个独立的问题。在本文中,我们首先定义了一个新的问题,称为在线机器人属性学习(On-RAL),机器人的工作属性学习和属性识别同时进行。然后,我们开发了一种算法,称为信息理论奖励塑造(ITRS),积极解决探索和开发之间的权衡在RAL问题。将ITRS与竞争机器人属性学习基线进行了比较,实验结果表明ITRS在学习效率和识别精度方面具有优势。

英文摘要:

Robots frequently need to perceive object attributes, such as "red," "heavy," and "empty," using multimodal exploratory actions, such as "look," "lift," and "shake." Robot attribute learning algorithms aim to learn an observation model for each perceivable attribute given an exploratory action. Once the attribute models are learned, they can be used to identify attributes of new objects, answering questions, such as "Is this object red and empty?" Attribute learning and identification are being treated as two separate problems in the literature. In this paper, we first define a new problem called online robot attribute learning (On-RAL), where the robot works on attribute learning and attribute identification simultaneously. Then we develop an algorithm called information-theoretic reward shaping (ITRS) that actively addresses the trade-off between exploration and exploitation in On-RAL problems. ITRS was compared with competitive robot attribute learning baselines, and experimental results demonstrate ITRS' superiority in learning efficiency and identification accuracy.

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。

↑