Symbolic Learning and Reasoning With Noisy Data for Probabilistic Anchoring

Abstract

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.

Learning Distributional Programs for Relational Autocompletion

“…DC programs have been successfully applied in robotics and perceptual anchoring using handcrafted programs or by learning parameters of simple programs with defined structure (Moldovan et al 2018;Persson et al 2019). The technique we present in the present paper has already been successfully applied for structure learning in the perceptual anchoring context (Zuidberg Dos Martires et al 2020) and extends these other results.…”

Design of the Integrated Cognitive Perception Model for Developing Situation-Awareness of an Autonomous Smart Agent

“…Martires et al aimed to establish a semantic scene representation paradigm based on top-down item connectivity, utilizing an item-induced model of the world [31]. Their approach involved processing continuous perceptual sensor data to maintain perceptual connectivity, which correlated with a symbolic model.…”

A semantics for Hybrid Probabilistic Logic programs with function symbols

“…Another proposal based on the DC semantics is HAL-ProbLog [45]. With this language, continuous random variables are represented with clauses of the form D :: t Ð l 1 , .…”

“…One limitation of this solution is that weight functions must be piecewise polynomial. In [45,46] the authors embed knowledge compilation and exact symbolic inference into WMI. However, WMI can only be applied to program without function symbols.…”

“…Hybrid ProbLog [15], Distributional Clauses (DC) [16], Extended PRISM [19], cplint hybrid programs [37], HAL-ProbLog [45] and Probabilistic Constraint Logic Programming (PCLP, for short, in the following) [24,25,26].…”