ProbAnch: A Modular Probabilistic Anchoring Framework
Abstract
Modeling object representations derived from perceptual observations, in a way that is also semantically meaningful for humans as well as autonomous agents, is a prerequisite for joint human-agent understanding of the world. A practical approach that aims to model such representations is perceptual anchoring, which handles the problem of mapping sub-symbolic sensor data to symbols and maintains these mappings over time. In this paper, we present ProbAnch, a modular data-driven anchoring framework, whose implementation requires a variety of well-orchestrated components, including a probabilistic reasoning system.
Cite
Text
Persson et al. "ProbAnch: A Modular Probabilistic Anchoring Framework." International Joint Conference on Artificial Intelligence, 2020. doi:10.24963/IJCAI.2020/771Markdown
[Persson et al. "ProbAnch: A Modular Probabilistic Anchoring Framework." International Joint Conference on Artificial Intelligence, 2020.](https://mlanthology.org/ijcai/2020/persson2020ijcai-probanch/) doi:10.24963/IJCAI.2020/771BibTeX
@inproceedings{persson2020ijcai-probanch,
title = {{ProbAnch: A Modular Probabilistic Anchoring Framework}},
author = {Persson, Andreas and Dos Martires, Pedro Zuidberg and De Raedt, Luc and Loutfi, Amy},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2020},
pages = {5285-5287},
doi = {10.24963/IJCAI.2020/771},
url = {https://mlanthology.org/ijcai/2020/persson2020ijcai-probanch/}
}