.png){kind=icon}
返回
Anchoring actions using conditional behavior trees and genetic programming
.png){kind=icon}
PRE
AI
DOI：10.1007/s10489-025-06373-w.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Robotic Kitting means the creation of parts assortment to be used later. These parts are selected from one or more containers in which there are different types of them randomly distributed. The Anchoring Problem should be considered if we want to provide a general solution to robotic kitting, since users want that it works with different types of parts that are not known 'a priori'. Therefore, we are working on a human supervised approach in which Behavior Trees, robot learning and human-robot interaction are used to anchor percepts and operations to symbols during commissioning or reconfiguration phases. In this paper we explain: (1) the anchoring mechanisms in our system and how behavior trees can be used to represent an anchor, and (2) how Genetic Programming is used to generate Conditional Behavior Trees that anchor symbolic actions to robot operations.
Keyword:
Intelligent robotics
Automated kitting
Anchoring problem
Behavior trees
Genetic programming
Human-robot interaction
期刊
IF:
3.5
论文数:
7.6K
被引数:
1.7W
机构
引用论文
分享收藏Risk factors for low self‐care self‐efficacy in cancer survivors: Application of latent profile analysis.png)
Nursing Open
OAAI
Nursing OpenIF0
OAAI分享收藏
查看更多内容