Symbolic Learning and Reasoning With Noisy Data for Probabilistic Anchoring
Robotic agents should be able to learn from sub-symbolic sensor data and, at the same time, be able to reason about objects and communicate with humans on a symbolic level. This raises the question of how to overcome the gap between symbolic and sub-symbolic artificial intelligence. We propose a sem...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2020-07-01
|
Series: | Frontiers in Robotics and AI |
Subjects: | |
Online Access: | https://www.frontiersin.org/article/10.3389/frobt.2020.00100/full |
id |
doaj-ba4a3fbdbc1645c886551b8ce23e8334 |
---|---|
record_format |
Article |
spelling |
doaj-ba4a3fbdbc1645c886551b8ce23e83342020-11-25T03:20:36ZengFrontiers Media S.A.Frontiers in Robotics and AI2296-91442020-07-01710.3389/frobt.2020.00100478853Symbolic Learning and Reasoning With Noisy Data for Probabilistic AnchoringPedro Zuidberg Dos Martires0Nitesh Kumar1Andreas Persson2Amy Loutfi3Luc De Raedt4Luc De Raedt5Declaratieve Talen en Artificiele Intelligentie (DTAI), Department of Computer Science, KU Leuven, Leuven, BelgiumDeclaratieve Talen en Artificiele Intelligentie (DTAI), Department of Computer Science, KU Leuven, Leuven, BelgiumCenter for Applied Autonomous Sensor Systems (AASS), Department of Science and Technology, Örebro University, Örebro, SwedenCenter for Applied Autonomous Sensor Systems (AASS), Department of Science and Technology, Örebro University, Örebro, SwedenDeclaratieve Talen en Artificiele Intelligentie (DTAI), Department of Computer Science, KU Leuven, Leuven, BelgiumCenter for Applied Autonomous Sensor Systems (AASS), Department of Science and Technology, Örebro University, Örebro, SwedenRobotic agents should be able to learn from sub-symbolic sensor data and, at the same time, be able to reason about objects and communicate with humans on a symbolic level. This raises the question of how to overcome the gap between symbolic and sub-symbolic artificial intelligence. We propose a semantic world modeling approach based on bottom-up object anchoring using an object-centered representation of the world. Perceptual anchoring processes continuous perceptual sensor data and maintains a correspondence to a symbolic representation. We extend the definitions of anchoring to handle multi-modal probability distributions and we couple the resulting symbol anchoring system to a probabilistic logic reasoner for performing inference. Furthermore, we use statistical relational learning to enable the anchoring framework to learn symbolic knowledge in the form of a set of probabilistic logic rules of the world from noisy and sub-symbolic sensor input. The resulting framework, which combines perceptual anchoring and statistical relational learning, is able to maintain a semantic world model of all the objects that have been perceived over time, while still exploiting the expressiveness of logical rules to reason about the state of objects which are not directly observed through sensory input data. To validate our approach we demonstrate, on the one hand, the ability of our system to perform probabilistic reasoning over multi-modal probability distributions, and on the other hand, the learning of probabilistic logical rules from anchored objects produced by perceptual observations. The learned logical rules are, subsequently, used to assess our proposed probabilistic anchoring procedure. We demonstrate our system in a setting involving object interactions where object occlusions arise and where probabilistic inference is needed to correctly anchor objects.https://www.frontiersin.org/article/10.3389/frobt.2020.00100/fullsemantic world modelingperceptual anchoringprobabilistic anchoringstatistical relational learningprobabilistic logic programmingobject tracking |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Pedro Zuidberg Dos Martires Nitesh Kumar Andreas Persson Amy Loutfi Luc De Raedt Luc De Raedt |
spellingShingle |
Pedro Zuidberg Dos Martires Nitesh Kumar Andreas Persson Amy Loutfi Luc De Raedt Luc De Raedt Symbolic Learning and Reasoning With Noisy Data for Probabilistic Anchoring Frontiers in Robotics and AI semantic world modeling perceptual anchoring probabilistic anchoring statistical relational learning probabilistic logic programming object tracking |
author_facet |
Pedro Zuidberg Dos Martires Nitesh Kumar Andreas Persson Amy Loutfi Luc De Raedt Luc De Raedt |
author_sort |
Pedro Zuidberg Dos Martires |
title |
Symbolic Learning and Reasoning With Noisy Data for Probabilistic Anchoring |
title_short |
Symbolic Learning and Reasoning With Noisy Data for Probabilistic Anchoring |
title_full |
Symbolic Learning and Reasoning With Noisy Data for Probabilistic Anchoring |
title_fullStr |
Symbolic Learning and Reasoning With Noisy Data for Probabilistic Anchoring |
title_full_unstemmed |
Symbolic Learning and Reasoning With Noisy Data for Probabilistic Anchoring |
title_sort |
symbolic learning and reasoning with noisy data for probabilistic anchoring |
publisher |
Frontiers Media S.A. |
series |
Frontiers in Robotics and AI |
issn |
2296-9144 |
publishDate |
2020-07-01 |
description |
Robotic agents should be able to learn from sub-symbolic sensor data and, at the same time, be able to reason about objects and communicate with humans on a symbolic level. This raises the question of how to overcome the gap between symbolic and sub-symbolic artificial intelligence. We propose a semantic world modeling approach based on bottom-up object anchoring using an object-centered representation of the world. Perceptual anchoring processes continuous perceptual sensor data and maintains a correspondence to a symbolic representation. We extend the definitions of anchoring to handle multi-modal probability distributions and we couple the resulting symbol anchoring system to a probabilistic logic reasoner for performing inference. Furthermore, we use statistical relational learning to enable the anchoring framework to learn symbolic knowledge in the form of a set of probabilistic logic rules of the world from noisy and sub-symbolic sensor input. The resulting framework, which combines perceptual anchoring and statistical relational learning, is able to maintain a semantic world model of all the objects that have been perceived over time, while still exploiting the expressiveness of logical rules to reason about the state of objects which are not directly observed through sensory input data. To validate our approach we demonstrate, on the one hand, the ability of our system to perform probabilistic reasoning over multi-modal probability distributions, and on the other hand, the learning of probabilistic logical rules from anchored objects produced by perceptual observations. The learned logical rules are, subsequently, used to assess our proposed probabilistic anchoring procedure. We demonstrate our system in a setting involving object interactions where object occlusions arise and where probabilistic inference is needed to correctly anchor objects. |
topic |
semantic world modeling perceptual anchoring probabilistic anchoring statistical relational learning probabilistic logic programming object tracking |
url |
https://www.frontiersin.org/article/10.3389/frobt.2020.00100/full |
work_keys_str_mv |
AT pedrozuidbergdosmartires symboliclearningandreasoningwithnoisydataforprobabilisticanchoring AT niteshkumar symboliclearningandreasoningwithnoisydataforprobabilisticanchoring AT andreaspersson symboliclearningandreasoningwithnoisydataforprobabilisticanchoring AT amyloutfi symboliclearningandreasoningwithnoisydataforprobabilisticanchoring AT lucderaedt symboliclearningandreasoningwithnoisydataforprobabilisticanchoring AT lucderaedt symboliclearningandreasoningwithnoisydataforprobabilisticanchoring |
_version_ |
1724617722466140160 |